PyTorch: An Imperative Style, High-Performance Deep Learning Library

Abstract

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several common benchmarks.

12 pages, 3 figures, NeurIPS 2019

Cited by in corpus (3572)

• Array Programming with NumPy
• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Learning Transferable Visual Models From Natural Language Supervision
• Albumentations: fast and flexible image augmentations
• On the Opportunities and Risks of Foundation Models
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Time Series Forecasting With Deep Learning: A Survey
• AutoML: A Survey of the State-of-the-Art
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Graph Contrastive Learning with Adaptive Augmentation
• Transformer in Transformer
• Alias-Free Generative Adversarial Networks
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• AdaBins: Depth Estimation using Adaptive Bins
• Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
• Captum: A unified and generic model interpretability library for PyTorch
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• Contrastive Multiview Coding
• SpeechBrain: A General-Purpose Speech Toolkit
• DeepPurpose: a Deep Learning Library for Drug-Target Interaction Prediction
• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• Self-adaptive loss balanced Physics-informed neural networks for the incompressible Navier-Stokes equations
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements
• Exploring Simple Siamese Representation Learning
• Deep Graph Contrastive Representation Learning
• Conditional Positional Encodings for Vision Transformers
• Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
• Artificial neural networks for neuroscientists: A primer
• In defence of metric learning for speaker recognition
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection
• Visual Transformers: Token-based Image Representation and Processing for Computer Vision
• Prevalence of Neural Collapse during the terminal phase of deep learning training
• Rank consistent ordinal regression for neural networks with application to age estimation
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
• Learnable latent embeddings for joint behavioral and neural analysis
• FedML: A Research Library and Benchmark for Federated Machine Learning
• Mining Latent Structures for Multimedia Recommendation
• DeepViT: Towards Deeper Vision Transformer
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Hierarchical Multi-Scale Attention for Semantic Segmentation
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
• CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
• Adaptive Personalized Federated Learning
• Coordinate Attention for Efficient Mobile Network Design
• A Generalization of Transformer Networks to Graphs
• Accelerating high-throughput virtual screening through molecular pool-based active learning
• From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling
• Balanced Meta-Softmax for Long-Tailed Visual Recognition
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
• Bootstrap Latent Representations for Multi-modal Recommendation
• Deep Gradient Learning for Efficient Camouflaged Object Detection
• Automated Pavement Crack Segmentation Using U-Net-based Convolutional Neural Network
• EDN: Salient Object Detection via Extremely-Downsampled Network
• Tent: Fully Test-time Adaptation by Entropy Minimization
• Point Transformer
• Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
• Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review
• An optical neural network using less than 1 photon per multiplication
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• Mnemonics Training: Multi-Class Incremental Learning without Forgetting
• Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx
• A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives
• AUTSL: A Large Scale Multi-modal Turkish Sign Language Dataset and Baseline Methods
• Inverse-design of nonlinear mechanical metamaterials via video denoising diffusion models
• Reinforcement Learning with Augmented Data
• Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
• CompressAI: a PyTorch library and evaluation platform for end-to-end compression research
• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• Benchmarking Graph Neural Networks
• Deep Residual Learning in Spiking Neural Networks
• Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification
• DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science
• Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
• Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
• Personalized Federated Learning with Moreau Envelopes
• Revisiting Anchor Mechanisms for Temporal Action Localization
• Deep DIC: Deep Learning-Based Digital Image Correlation for End-to-End Displacement and Strain Measurement
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
• A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• One Thousand and One Hours: Self-driving Motion Prediction Dataset
• Federated Neural Collaborative Filtering
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• TabTransformer: Tabular Data Modeling Using Contextual Embeddings
• Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
• GhostNets on Heterogeneous Devices via Cheap Operations
• Deep Learning with Coherent VCSEL Neural Networks
• True Few-Shot Learning with Language Models
• Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-Resolution
• Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
• Deep Hough Transform for Semantic Line Detection
• SIGN: Scalable Inception Graph Neural Networks
• Keeping it Simple: Language Models can learn Complex Molecular Distributions
• Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images
• Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
• Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse
• An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Bifurcated backbone strategy for RGB-D salient object detection
• Predicting Porosity, Permeability, and Tortuosity of Porous Media from Images by Deep Learning
• An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction
• From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
• VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection
• A fully automated method for 3D individual tooth identification and segmentation in dental CBCT
• Gravitational-wave parameter estimation with autoregressive neural network flows
• A Minimalist Approach to Offline Reinforcement Learning
• PalmTree: Learning an Assembly Language Model for Instruction Embedding
• A Label Attention Model for ICD Coding from Clinical Text
• Deep Learning in Photoacoustic Tomography: Current approaches and future directions
• Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs
• J$\hat{\text{A}}$A-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention
• Discrimination-aware Network Pruning for Deep Model Compression
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Regression Transformer: Concurrent sequence regression and generation for molecular language modeling
• Dense Dilated Convolutions Merging Network for Land Cover Classification
• Comparing Different Deep Learning Architectures for Classification of Chest Radiographs
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration
• A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays
• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
• All Tokens Matter: Token Labeling for Training Better Vision Transformers
• Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video
• Explaining Neural Scaling Laws
• Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training
• Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
• Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
• AtomAI: A Deep Learning Framework for Analysis of Image and Spectroscopy Data in (Scanning) Transmission Electron Microscopy and Beyond
• Deep Learning for Automatic Pneumonia Detection
• Neural Quantum States of frustrated magnets: generalization and sign structure
• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning
• Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
• Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection
• Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
• What Sustained Multi-Disciplinary Research Can Achieve: The Space Weather Modeling Framework
• Battery-constrained Federated Edge Learning in UAV-enabled IoT for B5G/6G Networks
• Machine Learning Coarse-Grained Potentials of Protein Thermodynamics
• SinGAN-Seg: Synthetic training data generation for medical image segmentation
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
• Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports
• Structure-Preserving Image Super-Resolution
• Operational Research: Methods and Applications
• QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars
• Classification of Brain Tumours in MR Images using Deep Spatiospatial Models
• Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
• PyTorch Distributed: Experiences on Accelerating Data Parallel Training
• A Dual-Dimer Method for Training Physics-Constrained Neural Networks with Minimax Architecture
• OmiEmbed: a unified multi-task deep learning framework for multi-omics data
• A Gradient-based Deep Neural Network Model for Simulating Multiphase Flow in Porous Media
• NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing
• Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models
• Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learning
• TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging
• Controversial stimuli: pitting neural networks against each other as models of human recognition
• DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction
• Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
• Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization
• Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
• Robust Sound Source Tracking Using SRP-PHAT and 3D Convolutional Neural Networks
• FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• Deep Learning for Automated Experimentation in Scanning Transmission Electron Microscopy
• Machine learning assisted multiscale modeling of composite phase change materials for Li-ion batteries thermal management
• Review: Deep Learning in Electron Microscopy
• Pretrained Transformers for Text Ranking: BERT and Beyond
• Roofpedia: Automatic mapping of green and solar roofs for an open roofscape registry and evaluation of urban sustainability
• Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
• Self-supervised learning of hologram reconstruction using physics consistency
• A General Approach to Seismic Inversion with Automatic Differentiation
• A physics-informed operator regression framework for extracting data-driven continuum models
• TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
• Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
• Torchattacks: A PyTorch Repository for Adversarial Attacks
• Learning the exchange-correlation functional from nature with fully differentiable density functional theory
• Soft Threshold Weight Reparameterization for Learnable Sparsity
• CLIPort: What and Where Pathways for Robotic Manipulation
• Pretrained Transformers as Universal Computation Engines
• Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020
• Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search
• Implicit Full Waveform Inversion with Deep Neural Representation
• Cough Against COVID: Evidence of COVID-19 Signature in Cough Sounds
• SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Graph Information Bottleneck
• RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
• Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination
• Federated Multi-Task Learning under a Mixture of Distributions
• Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
• Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
• LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
• fairseq S2T: Fast Speech-to-Text Modeling with fairseq
• Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Learning Meta Pattern for Face Anti-Spoofing
• VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
• Heterogeneous Graph Representation Learning with Relation Awareness
• Word-Level Coreference Resolution
• Structure-preserving neural networks
• Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
• Self-Adaptive Training: beyond Empirical Risk Minimization
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Deep Graph Matching and Searching for Semantic Code Retrieval
• Local approximate Gaussian process regression for data-driven constitutive laws: Development and comparison with neural networks
• TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation
• A unified framework for machine learning collective variables for enhanced sampling simulations: $\text{mlcolvar}$
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning
• Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
• Deep learning in biomedical optics
• Variational Graph Normalized Auto-Encoders
• In Search of Lost Domain Generalization
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
• Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing
• ViscNet: Neural network for predicting the fragility index and the temperature-dependency of viscosity
• An artificial neural network approach to bifurcating phenomena in computational fluid dynamics
• ProCAN: Progressive Growing Channel Attentive Non-Local Network for Lung Nodule Classification
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• Ansor: Generating High-Performance Tensor Programs for Deep Learning
• Understanding Event-Generation Networks via Uncertainties
• Bayesian Bits: Unifying Quantization and Pruning
• Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
• Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-based Convolutional Neural Networks
• Hopfield Networks is All You Need
• Neural Marching Cubes
• Supervised Compression for Resource-Constrained Edge Computing Systems
• Annotating Columns with Pre-trained Language Models
• Designing High-Tc Superconductors with BCS-inspired Screening, Density Functional Theory and Deep-learning
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Long-Range Transformers for Dynamic Spatiotemporal Forecasting
• Lip-reading with Densely Connected Temporal Convolutional Networks
• Acoustic Hologram Optimisation Using Automatic Differentiation
• Subject-Aware Contrastive Learning for Biosignals
• Dual-Resolution Correspondence Networks
• Unsupervised Cycle-consistent Generative Adversarial Networks for Pan-sharpening
• So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements
• InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images
• Revisiting Adversarially Learned Injection Attacks Against Recommender Systems
• LLM-driven Multimodal Target Volume Contouring in Radiation Oncology
• Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification
• Multi-stage transfer learning for lung segmentation using portable X-ray devices for patients with COVID-19
• SEED: Self-supervised Distillation For Visual Representation
• CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
• Distilled One-Shot Federated Learning
• Spatio-Temporal Self-Attention Network for Video Saliency Prediction
• Data-driven learning of robust nonlocal physics from high-fidelity synthetic data
• Predicting electronic structures at any length scale with machine learning
• Unity Perception: Generate Synthetic Data for Computer Vision
• DRLinFluids -- An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM
• Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data
• Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study
• Physics-informed neural networks (PINNs) for fluid mechanics: A review
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning
• Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion
• Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing
• Computing the Committor with the Committor: an Anatomy of the Transition State Ensemble
• ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
• Learning Graph Models for Retrosynthesis Prediction
• A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
• Full Page Handwriting Recognition via Image to Sequence Extraction
• Wavelet-Packets for Deepfake Image Analysis and Detection
• Generalized Domain Conditioned Adaptation Network
• Generative Networks for Precision Enthusiasts
• Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
• A newcomer's guide to deep learning for inverse design in nano-photonics
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey
• Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
• Universal Linear Intensity Transformations Using Spatially-Incoherent Diffractive Processors
• Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
• Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering
• Using Motion History Images with 3D Convolutional Networks in Isolated Sign Language Recognition
• Boosting Adversarial Training with Hypersphere Embedding
• Domain Generalization via Optimal Transport with Metric Similarity Learning
• RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection
• CEST MR fingerprinting (CEST-MRF) for Brain Tumor Quantification Using EPI Readout and Deep Learning Reconstruction
• Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoil
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
• Using the IBM Analog In-Memory Hardware Acceleration Kit for Neural Network Training and Inference
• Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery
• Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• A Study of Face Obfuscation in ImageNet
• Entropy-based Logic Explanations of Neural Networks
• g2tmn at Constraint@AAAI2021: Exploiting CT-BERT and Ensembling Learning for COVID-19 Fake News Detection
• T-LEAP: Occlusion-robust pose estimation of walking cows using temporal information
• Hurricane Forecasting: A Novel Multimodal Machine Learning Framework
• End-to-End Video Instance Segmentation with Transformers
• Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure
• Deep Vectorization of Technical Drawings
• RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
• NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
• FedLab: A Flexible Federated Learning Framework
• DC3: A learning method for optimization with hard constraints
• A Unified End-to-End Framework for Efficient Deep Image Compression
• GFINNs: GENERIC Formalism Informed Neural Networks for Deterministic and Stochastic Dynamical Systems
• Machine learning the deuteron
• Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
• Overparameterized Neural Networks Implement Associative Memory
• Capabilities of Deep Learning Models on Learning Physical Relationships: Case of Rainfall-Runoff Modeling with LSTM
• Partial success in closing the gap between human and machine vision
• Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification
• Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemes
• Neural Error Mitigation of Near-Term Quantum Simulations
• Combining Deep Reinforcement Learning and Search for Imperfect-Information Games
• Cycle Self-Training for Domain Adaptation
• Learning to Amend Facial Expression Representation via De-albino and Affinity
• CLUE: A Chinese Language Understanding Evaluation Benchmark
• PDE-based Group Equivariant Convolutional Neural Networks
• 6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning
• Learning Transferable Parameters for Unsupervised Domain Adaptation
• Three-dimensional Coherent X-ray Diffraction Imaging via Deep Convolutional Neural Networks
• A posteriori learning for quasi-geostrophic turbulence parametrization
• T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition
• GPU Acceleration of ADMM for Large-Scale Quadratic Programming
• TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation
• Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equations
• Convolutional Neural Networks with Gated Recurrent Connections
• CMT: Convolutional Neural Networks Meet Vision Transformers
• Visual diagnosis of the Varroa destructor parasitic mite in honeybees using object detector techniques
• Segmentation of Satellite Imagery using U-Net Models for Land Cover Classification
• DPFM: Deep Partial Functional Maps
• Complementing Lexical Retrieval with Semantic Residual Embedding
• EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks
• JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
• Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
• Integrating Pattern- and Fact-based Fake News Detection via Model Preference Learning
• Pre-trained Summarization Distillation
• Graph Neural Network Based Coarse-Grained Mapping Prediction
• Choose a Transformer: Fourier or Galerkin
• Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
• DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation
• Self-Supervised Monocular Depth Estimation with Internal Feature Fusion
• Scalable and Flexible Classical Shadow Tomography with Tensor Networks
• Learning Long-Term Dependencies in Irregularly-Sampled Time Series
• Category-Level Metric Scale Object Shape and Pose Estimation
• Space-time Mixing Attention for Video Transformer
• COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
• Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
• Solving Complex Nanostructures With Ptychographic Atomic Electron Tomography
• On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
• GACELA -- A generative adversarial context encoder for long audio inpainting
• On the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition
• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
• Hypercorrelation Squeeze for Few-Shot Segmentation
• Graph Communal Contrastive Learning
• FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration
• ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset
• Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging
• ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
• A first look into the carbon footprint of federated learning
• PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network
• giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration
• Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?
• Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems
• Medical Imaging and Machine Learning
• Provably Consistent Partial-Label Learning
• DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
• pixelNeRF: Neural Radiance Fields from One or Few Images
• Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
• RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model
• A Simple Differentiable Programming Language
• DQC: a Python program package for Differentiable Quantum Chemistry
• Charged particle tracking via edge-classifying interaction networks
• Is Attention Better Than Matrix Decomposition?
• Analytical Characterization and Design Space Exploration for Optimization of CNNs
• autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients
• DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
• MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Graph neural network initialisation of quantum approximate optimisation
• RobustART: Benchmarking Robustness on Architecture Design and Training Techniques
• Robust Peak Detection for Holter ECGs by Self-Organized Operational Neural Networks
• Data Poisoning Attacks Against Federated Learning Systems
• Up or Down? Adaptive Rounding for Post-Training Quantization
• Multi-Modal Multi-Instance Learning for Retinal Disease Recognition
• Pruning and Quantization for Deep Neural Network Acceleration: A Survey
• Generative Modeling of Turbulence
• Multi-modal Fusion for Single-Stage Continuous Gesture Recognition
• Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating
• StyleCariGAN: Caricature Generation via StyleGAN Feature Map Modulation
• Towards duration robust weakly supervised sound event detection
• Deep learning for gravitational wave forecasting of neutron star mergers
• Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
• Data-Efficient Reinforcement Learning with Self-Predictive Representations
• MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
• FedBABU: Towards Enhanced Representation for Federated Image Classification
• Machine Learning for Physics-Informed Generation of Dispersed Multiphase Flow Using Generative Adversarial Networks
• Geoopt: Riemannian Optimization in PyTorch
• A neural network multigrid solver for the Navier-Stokes equations
• MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• Observation of Superconductivity Induced Ferromagnetism in an Fe-Chalcogenide Superconductor
• The Gaussian equivalence of generative models for learning with shallow neural networks
• Tensorized Embedding Layers for Efficient Model Compression
• Attention-Enhanced Cross-Task Network for Analysing Multiple Attributes of Lung Nodules in CT
• Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
• Open-World Semi-Supervised Learning
• Characterizing the Decision Boundary of Deep Neural Networks
• Detecting Dementia from Speech and Transcripts using Transformers
• An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
• Compiling Spiking Neural Networks to Neuromorphic Hardware
• Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis
• Adaptive Optics control using Model-Based Reinforcement Learning
• Compute and memory efficient universal sound source separation
• Scalable Graph Neural Network Training: The Case for Sampling
• medigan: a Python library of pretrained generative models for medical image synthesis
• Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Automating Botnet Detection with Graph Neural Networks
• Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality
• Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model
• No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation
• Semi-Supervised Neural Architecture Search
• Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis
• Low-temperature plasma simulation based on physics-informed neural networks: frameworks and preliminary applications
• Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
• Optimized and autonomous machine learning framework for characterizing pores, particles, grains and grain boundaries in microstructural images
• Lung Segmentation from Chest X-rays using Variational Data Imputation
• MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
• Reducing DNN Labelling Cost using Surprise Adequacy: An Industrial Case Study for Autonomous Driving
• Causal Discovery in Physical Systems from Videos
• The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors
• Identifying Mislabeled Data using the Area Under the Margin Ranking
• Data-driven turbulence modeling in separated flows considering physical mechanism analysis
• Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference
• SurvTRACE: Transformers for Survival Analysis with Competing Events
• Convolutional Neural Nets in Chemical Engineering: Foundations, Computations, and Applications
• Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
• A TensorFlow Simulation Framework for Scientific Computing of Fluid Flows on Tensor Processing Units
• AllenAct: A Framework for Embodied AI Research
• Molecular dynamics simulation with finite electric fields using Perturbed Neural Network Potentials
• Deep learning for thermal plasma simulation: solving 1-D arc model as an example
• Detecting Visual Design Principles in Art and Architecture through Deep Convolutional Neural Networks
• ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
• TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
• Adorym: A multi-platform generic x-ray image reconstruction framework based on automatic differentiation
• ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis
• What Makes Multi-modal Learning Better than Single (Provably)
• Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics
• Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
• A Deep Learning Algorithm for High-Dimensional Exploratory Item Factor Analysis
• Heatmap Regression via Randomized Rounding
• Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
• gradSim: Differentiable simulation for system identification and visuomotor control
• Learning to Control PDEs with Differentiable Physics
• A black-box adversarial attack for poisoning clustering
• Learning the Effect of Registration Hyperparameters with HyperMorph
• PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
• Interpretable Multi-Head Self-Attention model for Sarcasm Detection in social media
• Learning Black-Box Attackers with Transferable Priors and Query Feedback
• Numerical investigation of minimum drag profiles in laminar flow using deep learning surrogates
• Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
• d3rlpy: An Offline Deep Reinforcement Learning Library
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Probabilistic Gradient Boosting Machines for Large-Scale Probabilistic Regression
• Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
• Coordinate-based neural representations for computational adaptive optics in widefield microscopy
• DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation
• Learning the Travelling Salesperson Problem Requires Rethinking Generalization
• Adversarial Patch Attacks on Monocular Depth Estimation Networks
• EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network
• One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision
• Reduced and All-at-Once Approaches for Model Calibration and Discovery in Computational Solid Mechanics
• SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
• Automating the assessment of biofouling in images using expert agreement as a gold standard
• Refiner: Refining Self-attention for Vision Transformers
• Comparing machine learning techniques for predicting glassy dynamics
• A deep convolutional neural network for classification of Aedes albopictus mosquitoes
• Deep learning of systematic sea ice model errors from data assimilation increments
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
• ReDet: A Rotation-equivariant Detector for Aerial Object Detection
• BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis
• Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology
• Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
• E3NE: An End-to-End Framework for Accelerating Spiking Neural Networks with Emerging Neural Encoding on FPGAs
• Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification
• Decoding ECoG signal into 3D hand translation using deep learning
• Advbox: a toolbox to generate adversarial examples that fool neural networks
• A Variational Perspective on Diffusion-Based Generative Models and Score Matching
• DiNNO: Distributed Neural Network Optimization for Multi-Robot Collaborative Learning
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning
• Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
• EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback
• Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer-Grade VR Devices
• Anomalous Jet Identification via Sequence Modeling
• Recent progress in the JARVIS infrastructure for next-generation data-driven materials design
• FcaNet: Frequency Channel Attention Networks
• Continuous Conditional Random Field Convolution for Point Cloud Segmentation
• Neural Ordinary Differential Equation Control of Dynamics on Graphs
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
• Physics-aware Reduced-order Modeling of Transonic Flow via $\beta$-Variational Autoencoder
• PyXtal FF: a Python Library for Automated Force Field Generation
• GSPMD: General and Scalable Parallelization for ML Computation Graphs
• Prototypical Representation Learning for Relation Extraction
• Text-Based Person Search with Limited Data
• A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models
• Data augmented turbulence modeling for three-dimensional separation flows
• Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
• Adversarial Bipartite Graph Learning for Video Domain Adaptation
• Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity
• Modeling nanoconfinement effects using active learning
• Machine learning moment closure models for the radiative transfer equation I: directly learning a gradient based closure
• Quantum Architecture Search via Deep Reinforcement Learning
• Noisy Differentiable Architecture Search
• GINNs: Graph-Informed Neural Networks for Multiscale Physics
• Learning to Extend Molecular Scaffolds with Structural Motifs
• PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking
• TorchXRayVision: A library of chest X-ray datasets and models
• Semi-supervised Federated Learning for Activity Recognition
• Accelerating Material Design with the Generative Toolkit for Scientific Discovery
• An Overview of Indian Spoken Language Recognition from Machine Learning Perspective
• DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval
• Adversarial Unlearning of Backdoors via Implicit Hypergradient
• Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
• The Ivory Tower Lost: How College Students Respond Differently than the General Public to the COVID-19 Pandemic
• learn2learn: A Library for Meta-Learning Research
• Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines
• Efficient and Modular Implicit Differentiation
• Fast offset corrected in-memory training
• Unsupervised Domain Adaptation of Black-Box Source Models
• The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021
• Bipartite Graph Reasoning GANs for Person Image Generation
• Progressive Identification of True Labels for Partial-Label Learning
• Few-shot Domain Adaptation by Causal Mechanism Transfer
• Path sampling of recurrent neural networks by incorporating known physics
• Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
• SenseCare: A Research Platform for Medical Image Informatics and Interactive 3D Visualization
• Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
• Hierarchical Inter-Message Passing for Learning on Molecular Graphs
• Improving Document-Level Sentiment Classification Using Importance of Sentences
• Learning Pair Potentials using Differentiable Simulations
• Semantic segmentation of multispectral photoacoustic images using deep learning
• Machine-learning Iterative Calculation of Entropy for Physical Systems
• Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model
• Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images
• Variational Quantum Classifiers Through the Lens of the Hessian
• Simple and Effective VAE Training with Calibrated Decoders
• TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog
• Quantum semi-supervised generative adversarial network for enhanced data classification
• PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management
• Interior Point Solving for LP-based prediction+optimisation
• Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned
• PHOTONAI -- A Python API for Rapid Machine Learning Model Development
• Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
• Training Binary Neural Networks through Learning with Noisy Supervision
• Network On Network for Tabular Data Classification in Real-world Applications
• Multi-Graph Transformer for Free-Hand Sketch Recognition
• Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping Through Continual Learning
• On Joint Learning for Solving Placement and Routing in Chip Design
• Quantum Reinforcement Learning: the Maze problem
• PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
• Variational Bayes survival analysis for unemployment modelling
• Parametrized classifiers for optimal EFT sensitivity
• Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
• ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
• Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs
• Introspective Distillation for Robust Question Answering
• Learning Continuous Image Representation with Local Implicit Image Function
• Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
• Accelerating Neural ODEs Using Model Order Reduction
• On the design space between molecular mechanics and machine learning force fields
• Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach
• SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration
• Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
• TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
• Pretraining Representations for Data-Efficient Reinforcement Learning
• Physics-driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
• Deep Sketch-guided Cartoon Video Inbetweening
• An Analysis of SVD for Deep Rotation Estimation
• Mind the Pad -- CNNs can Develop Blind Spots
• Dynamic Nanodomains Dictate Macroscopic Properties in Lead Halide Perovskites
• A Deep-learning Model for Fast Prediction of Vacancy Formation in Diverse Materials
• Deep multi-metric learning for text-independent speaker verification
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• A call to arms: making the case for more reusable libraries
• IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration
• A Theoretical Framework for Target Propagation
• Camouflaged Object Segmentation with Distraction Mining
• The Synergy of Complex Event Processing and Tiny Machine Learning in Industrial IoT
• Constrained non-negative matrix factorization enabling real-time insights of $\text{in situ}$ and high-throughput experiments
• Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs
• CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers
• TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
• GRNet: Gridding Residual Network for Dense Point Cloud Completion
• Symplectic Learning for Hamiltonian Neural Networks
• Flexible learning of quantum states with generative query neural networks
• Characterizing soot in TEM images using a convolutional neural network
• Leveraging Machine Learning to Alleviate Hubbard Model Sign Problems
• metric-learn: Metric Learning Algorithms in Python
• TaskNorm: Rethinking Batch Normalization for Meta-Learning
• Incorporating Symbolic Domain Knowledge into Graph Neural Networks
• Deep unfitted Nitsche method for elliptic interface problems
• Towards Explainable Graph Representations in Digital Pathology
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis
• Uncertainty Sets for Image Classifiers using Conformal Prediction
• Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Global sensitivity analysis based on Gaussian-process metamodelling for complex biomechanical problems
• When is invariance useful in an Out-of-Distribution Generalization problem ?
• ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
• Edge-Featured Graph Attention Network
• Ultra Low-Parameter Denoising: Trainable Bilateral Filter Layers in Computed Tomography
• Deep learning for diffusion in porous media
• Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems
• Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
• Automated Identification of Cell Populations in Flow Cytometry Data with Transformers
• QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensors
• Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields
• An Improved Analysis of Stochastic Gradient Descent with Momentum
• FibeR-CNN: Expanding Mask R-CNN to Improve Image-Based Fiber Analysis
• Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions
• AANet: Adaptive Aggregation Network for Efficient Stereo Matching
• Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables
• Compositional Generalization by Learning Analytical Expressions
• Example-Based Named Entity Recognition
• Efficient Exact Verification of Binarized Neural Networks
• CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
• Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval
• The Impact of the Mini-batch Size on the Variance of Gradients in Stochastic Gradient Descent
• Biomarker Discovery with Quantum Neural Networks: A Case-study in CTLA4-Activation Pathways
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
• RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor
• Machine Learning to Predict Aerodynamic Stall
• Information Maximization Clustering via Multi-View Self-Labelling
• Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
• Pose is all you need: The pose only group activity recognition system (POGARS)
• Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
• A Study of Learning Search Approximation in Mixed Integer Branch and Bound: Node Selection in SCIP
• Towards Understanding Label Smoothing
• Learning Certified Individually Fair Representations
• Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey
• Federated Learning with Compression: Unified Analysis and Sharp Guarantees
• Rethinking Weight Decay For Efficient Neural Network Pruning
• NormFormer: Improved Transformer Pretraining with Extra Normalization
• Earth System Data Cubes: Avenues for advancing Earth system research
• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
• ESPnet2-TTS: Extending the Edge of TTS Research
• Fast computation of mutual information in the frequency domain with applications to global multimodal image alignment
• Keys to Accurate Feature Extraction Using Residual Spiking Neural Networks
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Towards Robust Graph Contrastive Learning
• Search for R-parity violating supersymmetry in a final state containing leptons and many jets with the ATLAS experiment using $\sqrt{s}=13$ TeV proton-proton collision data
• RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation
• What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoors
• DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation
• Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
• Semi-supervised source localization with deep generative modeling
• Increasing the Confidence of Deep Neural Networks by Coverage Analysis
• Implementing graph neural networks with TensorFlow-Keras
• Single-frame far-field diffractive imaging with randomized illumination
• Kernel methods through the roof: handling billions of points efficiently
• On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
• Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions
• The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lap
• Highdicom: A Python library for standardized encoding of image annotations and machine learning model outputs in pathology and radiology
• Laplace Redux -- Effortless Bayesian Deep Learning
• An Unsupervised Reconstruction Method For Low-Dose CT Using Deep Generative Regularization Prior
• Deep Indexed Active Learning for Matching Heterogeneous Entity Representations
• An end-to-end attention-based approach for learning on graphs
• RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Conditional Convolutions for Instance Segmentation
• Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction
• Lettuce: PyTorch-based Lattice Boltzmann Framework
• Embedding-based Silhouette Community Detection
• Virtual birefringence imaging and histological staining of amyloid deposits in label-free tissue using autofluorescence microscopy and deep learning
• SketchGen: Generating Constrained CAD Sketches
• Search to aggregate neighborhood for graph neural network
• Predicting fluid-structure interaction with graph neural networks
• Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads
• Tracking perovskite crystallization via deep learning-based feature detection on 2D X-ray scattering data
• Pure Tensor Program Rewriting via Access Patterns (Representation Pearl)
• Nonlinear Invariant Risk Minimization: A Causal Approach
• High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
• Graph Neural Networks with Learnable Structural and Positional Representations
• Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification
• COIN: COmpression with Implicit Neural representations
• Involution: Inverting the Inherence of Convolution for Visual Recognition
• MARS: Multi-macro Architecture SRAM CIM-Based Accelerator with Co-designed Compressed Neural Networks
• Improved Residual Networks for Image and Video Recognition
• Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings
• Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
• Deep Volumetric Ambient Occlusion
• Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia
• Asymptotics of representation learning in finite Bayesian neural networks
• 3D Shape Reconstruction from Vision and Touch
• Improving Multi-Modal Learning with Uni-Modal Teachers
• DS6, Deformation-aware Semi-supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data
• Learning image representations for anomaly detection: application to discovery of histological alterations in drug development
• Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
• GraphCL: Contrastive Self-Supervised Learning of Graph Representations
• PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
• Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims
• PENet: Towards Precise and Efficient Image Guided Depth Completion
• FastONN -- Python based open-source GPU implementation for Operational Neural Networks
• Applying Convolutional Neural Networks to Data on Unstructured Meshes with Space-Filling Curves
• Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning
• Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency
• Deep SVBRDF Estimation on Real Materials
• Improving black-box optimization in VAE latent space using decoder uncertainty
• How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS
• Deep Interactive Learning: An Efficient Labeling Approach for Deep Learning-Based Osteosarcoma Treatment Response Assessment
• Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample
• MusPy: A Toolkit for Symbolic Music Generation
• A community-powered search of machine learning strategy space to find NMR property prediction models
• Bayesian Neural Network Priors Revisited
• Improving Text-to-SQL with Schema Dependency Learning
• Cross-Domain Few-Shot Learning by Representation Fusion
• Learning Neural Event Functions for Ordinary Differential Equations
• Data Movement Is All You Need: A Case Study on Optimizing Transformers
• RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
• Testing the limits of natural language models for predicting human language judgments
• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
• Generalized Planning With Deep Reinforcement Learning
• Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
• Settling the Variance of Multi-Agent Policy Gradients
• Depth-aware Blending of Smoothed Images for Bokeh Effect Generation
• Towards Balanced Learning for Instance Recognition
• Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
• Improving colonoscopy lesion classification using semi-supervised deep learning
• NORESQA: A Framework for Speech Quality Assessment using Non-Matching References
• Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
• HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark
• Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
• Multimodal Metadata Assignment for Cultural Heritage Artifacts
• Automatic Borescope Damage Assessments for Gas Turbine Blades via Deep Learning
• ElephantBook: A Semi-Automated Human-in-the-Loop System for Elephant Re-Identification
• Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
• Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning
• Graph Signal Restoration Using Nested Deep Algorithm Unrolling
• Interactive All-Hex Meshing via Cuboid Decomposition
• HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information
• SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling
• PatchmatchNet: Learned Multi-View Patchmatch Stereo
• Independent Prototype Propagation for Zero-Shot Compositionality
• On the Iteration Complexity of Hypergradient Computation
• Black-Box Optimization with Local Generative Surrogates
• Towards Single Camera Human 3D-Kinematics
• PyRCN: A Toolbox for Exploration and Application of Reservoir Computing Networks
• Point Cloud Registration using Representative Overlapping Points
• Deep Learning for Optical Tweezers
• VOLO: Vision Outlooker for Visual Recognition
• X-volution: On the unification of convolution and self-attention
• Finite element based model order reduction for parametrized one-way coupled steady state linear thermomechanical problems
• Hybrid Quantum-Classical Graph Convolutional Network
• Structure-Enhanced Pop Music Generation via Harmony-Aware Learning
• FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction
• A Selective Review on Statistical Methods for Massive Data Computation: Distributed Computing, Subsampling, and Minibatch Techniques
• HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method
• Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks
• Analyzing analytical methods: The case of phonology in neural models of spoken language
• Visual Grounding of Learned Physical Models
• SplitEasy: A Practical Approach for Training ML models on Mobile Devices
• Constrained Neural Ordinary Differential Equations with Stability Guarantees
• Polygonal Building Segmentation by Frame Field Learning
• Hybrid Discriminative-Generative Training via Contrastive Learning
• ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
• Path Planning using Neural A* Search
• SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios
• Approximation Properties of Deep ReLU CNNs
• PEMNET: A Transfer Learning-based Modeling Approach of High-Temperature Polymer Electrolyte Membrane Electrochemical Systems
• PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
• What's a good imputation to predict with missing values?
• Human-Adversarial Visual Question Answering
• PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time
• Viewmaker Networks: Learning Views for Unsupervised Representation Learning
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
• All You Need is a Good Functional Prior for Bayesian Deep Learning
• Quantifying Disorder One Atom at a Time Using an Interpretable Graph Neural Network Paradigm
• Scalable Rule-Based Representation Learning for Interpretable Classification
• Leveraging the Mathematics of Shape for Solar Magnetic Eruption Prediction
• Permutation Invariant Graph Generation via Score-Based Generative Modeling
• On the relationship between predictive coding and backpropagation
• Meta Transition Adaptation for Robust Deep Learning with Noisy Labels
• QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries
• Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
• Graph-based Solutions with Residuals for Intrusion Detection: the Modified E-GraphSAGE and E-ResGAT Algorithms
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• ADOP: Approximate Differentiable One-Pixel Point Rendering
• Context-Driven Detection of Invertebrate Species in Deep-Sea Video
• Revealing systematics in phenomenologically viable flux vacua with reinforcement learning
• Neural Non-Rigid Tracking
• Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
• Deep Online Correction for Monocular Visual Odometry
• Semi-Conditional Normalizing Flows for Semi-Supervised Learning
• Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
• Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance
• Neutron: An Implementation of the Transformer Translation Model and its Variants
• Data-driven Identification of 2D Partial Differential Equations using extracted physical features
• SLISEMAP: Supervised dimensionality reduction through local explanations
• M3d-CAM: A PyTorch library to generate 3D data attention maps for medical deep learning
• PyTorch Metric Learning
• Characterizing signal propagation to close the performance gap in unnormalized ResNets
• Probabilistic Dual Network Architecture Search on Graphs
• Meta-learning in healthcare: A survey
• Benchmarking Simulation-Based Inference
• Geometric Loss for Deep Multiple Sclerosis lesion Segmentation
• How Does Mixup Help With Robustness and Generalization?
• Pile-Up Mitigation using Attention
• QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
• A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognition
• Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers
• Elucidating proximity magnetism through polarized neutron reflectometry and machine learning
• Randomness In Neural Network Training: Characterizing The Impact of Tooling
• Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders
• End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems
• Local AdaAlter: Communication-Efficient Stochastic Gradient Descent with Adaptive Learning Rates
• SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification
• Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training
• Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
• The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
• Boosting EfficientNets Ensemble Performance via Pseudo-Labels and Synthetic Images by pix2pixHD for Infection and Ischaemia Classification in Diabetic Foot Ulcers
• jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models
• Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
• $\text{ab initio}$ description of bonding for transmission electron microscopy
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• You Impress Me: Dialogue Generation via Mutual Persona Perception
• Learnable Embedding Sizes for Recommender Systems
• Contextualized Perturbation for Textual Adversarial Attack
• DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
• tf-Darshan: Understanding Fine-grained I/O Performance in Machine Learning Workloads
• Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
• Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
• SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
• Multi-Task Reinforcement Learning with Context-based Representations
• Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero
• Differentiable Neural Input Search for Recommender Systems
• HeAT -- a Distributed and GPU-accelerated Tensor Framework for Data Analytics
• An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
• Accelerating Quadratic Optimization with Reinforcement Learning
• Machine Learning for Exploring Small Polaron Configurational Space
• Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis
• The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
• Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
• Gigapixel Whole-Slide Images Classification using Locally Supervised Learning
• Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT
• Extending BrainScaleS OS for BrainScaleS-2
• Full-Duplex Strategy for Video Object Segmentation
• Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs
• Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction
• Feature Learning in Infinite-Width Neural Networks
• DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation
• xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
• Particle streak velocimetry using Ensemble Convolutional Neural Networks
• SwiftLane: Towards Fast and Efficient Lane Detection
• Non-intrusive reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation
• Accelerating Phase Field Simulations Through a Hybrid Adaptive Fourier Neural Operator with U-Net Backbone
• A Dimensionality Reduction Approach for Convolutional Neural Networks
• Taming Visually Guided Sound Generation
• Fast and Accurate Non-Linear Predictions of Universes with Deep Learning
• Multimap targeted free energy estimation
• InstaHide: Instance-hiding Schemes for Private Distributed Learning
• On the Utility of Gradient Compression in Distributed Training Systems
• Global Filter Networks for Image Classification
• On the surprising similarities between supervised and self-supervised models
• Differentiable Model Compression via Pseudo Quantization Noise
• Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
• Local Augmentation for Graph Neural Networks
• GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
• Cardiac Segmentation on CT Images through Shape-Aware Contour Attentions
• Model-Contrastive Federated Learning
• EAST discharge prediction without integrating simulation results
• BNNpriors: A library for Bayesian neural network inference with different prior distributions
• Semi-Supervised Visual Representation Learning for Fashion Compatibility
• Predicting Information Pathways Across Online Communities
• Learning Optimal Representations with the Decodable Information Bottleneck
• Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification
• PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
• Multimodal Anomaly Detection based on Deep Auto-Encoder for Object Slip Perception of Mobile Manipulation Robots
• Neural networks for on-the-fly single-shot state classification
• Machine Learning for Electronic Design Automation: A Survey
• Evaluating uncertainties in electrochemical impedance spectra of solid oxide fuel cells
• A Dataset and Benchmark Towards Multi-Modal Face Anti-Spoofing Under Surveillance Scenarios
• A benchmark for computational analysis of animal behavior, using animal-borne tags
• Reducing Energy Bloat in Large Model Training
• JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment
• Reduced-order modeling of unsteady fluid flow using neural network ensembles
• STAR: Sparse Transformer-based Action Recognition
• CGNN: Traffic Classification with Graph Neural Network
• A robust and scalable framework for hallucination detection in virtual tissue staining and digital pathology
• MUCM-Net: A Mamba Powered UCM-Net for Skin Lesion Segmentation
• BenthicNet: A global compilation of seafloor images for deep learning applications
• AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition
• Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
• Image-level Harmonization of Multi-Site Data using Image-and-Spatial Transformer Networks
• Deep Negative Volume Segmentation
• Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image Segmentation
• Efficient Execution of Quantized Deep Learning Models: A Compiler Approach
• Contrastive estimation reveals topic posterior information to linear models
• Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Dataset
• Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
• BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
• Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
• Knapsack Pruning with Inner Distillation
• Edge Representation Learning with Hypergraphs
• PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
• SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle
• Mish: A Self Regularized Non-Monotonic Activation Function
• Drug-Target Interaction Prediction with Graph Attention networks
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• Strongly Incremental Constituency Parsing with Graph Neural Networks
• Image and Model Transformation with Secret Key for Vision Transformer
• Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction
• Machine learning for metal additive manufacturing: Predicting temperature and melt pool fluid dynamics using physics-informed neural networks
• Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts
• Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
• Rapid Response Crop Maps in Data Sparse Regions
• Central object segmentation by deep learning for fruits and other roundish objects
• Are All Languages Created Equal in Multilingual BERT?
• Learning Deep Features in Instrumental Variable Regression
• SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
• Interpreting Super-Resolution Networks with Local Attribution Maps
• Data augmentation and feature selection for automatic model recommendation in computational physics
• QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
• DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
• Domain Adaptation for Time Series Forecasting via Attention Sharing
• HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
• Continuum: Simple Management of Complex Continual Learning Scenarios
• Many-to-English Machine Translation Tools, Data, and Pretrained Models
• SHREC 2021: Retrieval and classification of protein surfaces equipped with physical and chemical properties
• InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
• Designing Air Flow with Surrogate-assisted Phenotypic Niching
• Topological Semantic Mapping by Consolidation of Deep Visual Features
• Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
• Neural network tokamak equilibria with incompressible flows
• Deeptime: a Python library for machine learning dynamical models from time series data
• Adversarial training approach for local data debiasing
• SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems
• Learning Explicit User Interest Boundary for Recommendation
• SymForce: Symbolic Computation and Code Generation for Robotics
• Effects of Online Self-Disclosure on Social Feedback During the COVID-19 Pandemic
• Lightweight Regression Model with Prediction Interval Estimation for Computer Vision-based Winter Road Surface Condition Monitoring
• Deep Learning Enhanced Quantum Holography with Undetected Photons
• Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation
• C5T5: Controllable Generation of Organic Molecules with Transformers
• High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation
• RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning
• When MAML Can Adapt Fast and How to Assist When It Cannot
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
• Deep Bilateral Retinex for Low-Light Image Enhancement
• Self-Knowledge Distillation with Progressive Refinement of Targets
• The Federated Tumor Segmentation (FeTS) Challenge
• Multi-StyleGAN: Towards Image-Based Simulation of Time-Lapse Live-Cell Microscopy
• FreezeNet: Full Performance by Reduced Storage Costs
• Physics-Coupled Neural Network Magnetic Resonance Electrical Property Tomography (MREPT) for Conductivity Reconstruction
• Neural Termination Analysis
• FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning
• Cubature rules for weakly and fully compressible off-lattice Boltzmann methods
• AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning
• Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs
• How to 0wn NAS in Your Spare Time
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding
• Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
• Checkerboard Context Model for Efficient Learned Image Compression
• On the model-based stochastic value gradient for continuous reinforcement learning
• Scaling up sign spotting through sign language dictionaries
• Demonstrating Analog Inference on the BrainScaleS-2 Mobile System
• Limited Parameter Denoising for Low-dose X-ray Computed Tomography Using Deep Reinforcement Learning
• Solving PDE-constrained Control Problems Using Operator Learning
• Artificial and beneficial -- Exploiting artificial images for aerial vehicle detection
• PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers
• Object-aware Contrastive Learning for Debiased Scene Representation
• WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit
• Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks
• Active Testing: Sample-Efficient Model Evaluation
• Dissipation-induced collective advantage of a quantum thermal machine
• Evaluating Deep Learning-based Melanoma Classification using Immunohistochemistry and Routine Histology: A Three Center Study
• A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks
• Nonsmooth Implicit Differentiation for Machine Learning and Optimization
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Input
• Q${}^2$Chemistry: A quantum computation platform for quantum chemistry
• How to Train Your Energy-Based Model for Regression
• Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts
• Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data
• Rethinking Spatially-Adaptive Normalization
• A Comparative Study of Feature Types for Age-Based Text Classification
• Fusion Models for Improved Visual Captioning
• MBRL-Lib: A Modular Library for Model-based Reinforcement Learning
• Learning Free-Surface Flow with Physics-Informed Neural Networks
• Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
• Variational principle to regularize machine-learned density functionals: the non-interacting kinetic-energy functional
• When Does Self-supervision Improve Few-shot Learning?
• Better Distractions: Transformer-based Distractor Generation and Multiple Choice Question Filtering
• Learning Neural Network Subspaces
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
• torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation
• DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration
• DoWhy: An End-to-End Library for Causal Inference
• Inverse molecular design and parameter optimization with Hückel theory using automatic differentiation
• NFAD: Fixing anomaly detection using normalizing flows
• Towards Generalizable Surgical Activity Recognition Using Spatial Temporal Graph Convolutional Networks
• MixPath: A Unified Approach for One-shot Neural Architecture Search
• Training Algorithm Matters for the Performance of Neural Network Potential: A Case Study of Adam and the Kalman Filter Optimizers
• Machine Learning for Conservative-to-Primitive in Relativistic Hydrodynamics
• Pre-Trained Models: Past, Present and Future
• Multi-fidelity data fusion through parameter space reduction with applications to automotive engineering
• Hybrid Classical-Quantum Deep Learning Models for Autonomous Vehicle Traffic Image Classification Under Adversarial Attack
• Sparse Communication for Training Deep Networks
• Towards Fast and Light-Weight Restoration of Dark Images
• Exploratory Lagrangian-Based Particle Tracing Using Deep Learning
• Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks
• Evaluating Logical Generalization in Graph Neural Networks
• Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)
• KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations
• Plato Dialogue System: A Flexible Conversational AI Research Platform
• Implicit Neural Representation for Physics-driven Actuated Soft Bodies
• A parameter refinement method for Ptychography based on Deep Learning concepts
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• IDRLnet: A Physics-Informed Neural Network Library
• Efficient Neural Network Training via Forward and Backward Propagation Sparsification
• Guiding Cascading Failure Search with Interpretable Graph Convolutional Network
• BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning
• On the Convergence of SGD with Biased Gradients
• Multi-task learning for virtual flow metering
• Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
• A High Probability Analysis of Adaptive SGD with Momentum
• EfficientPhys: Enabling Simple, Fast and Accurate Camera-Based Vitals Measurement
• Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
• A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentation
• Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
• On the effects of biased quantum random numbers on the initialization of artificial neural networks
• GiT: Graph Interactive Transformer for Vehicle Re-identification
• End-to-End Object Detection with Fully Convolutional Network
• AraCOVID19-MFH: Arabic COVID-19 Multi-label Fake News and Hate Speech Detection Dataset
• SpecTNT: a Time-Frequency Transformer for Music Audio
• A Mathematical Analysis of Learning Loss for Active Learning in Regression
• Rotation-Equivariant Deep Learning for Diffusion MRI
• On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers
• Hate-Alert@DravidianLangTech-EACL2021: Ensembling strategies for Transformer-based Offensive language Detection
• Unsupervised Anomaly Localization with Structural Feature-Autoencoders
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
• Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
• Data-driven discovery of multiscale chemical reactions governed by the law of mass action
• FaceX-Zoo: A PyTorch Toolbox for Face Recognition
• Disentangled Representation for Causal Mediation Analysis
• Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
• Auxiliary Task Reweighting for Minimum-data Learning
• Convolutional Neural Network Pruning with Structural Redundancy Reduction
• Generalizable synthetic MRI with physics-informed convolutional networks
• Domain adaptation under structural causal models
• High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times
• IIITT@LT-EDI-EACL2021-Hope Speech Detection: There is always Hope in Transformers
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
• KaoKore: A Pre-modern Japanese Art Facial Expression Dataset
• System Identification Through Lipschitz Regularized Deep Neural Networks
• Progressive Semantic-Aware Style Transformation for Blind Face Restoration
• Asymmetrical estimator for training encapsulated deep photonic neural networks
• Adapting Physics-Informed Neural Networks to Improve ODE Optimization in Mosquito Population Dynamics
• Rethinking Bottleneck Structure for Efficient Mobile Network Design
• Intersymbolic AI: Interlinking Symbolic AI and Subsymbolic AI
• Spatial-Temporal Dynamic Graph Attention Networks for Ride-hailing Demand Prediction
• DeepFEA: Deep Learning for Prediction of Transient Finite Element Analysis Solutions
• Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
• An annotated grain kernel image database for visual quality inspection
• Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
• Directional convergence and alignment in deep learning
• ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
• Using a thousand optimization tasks to learn hyperparameter search strategies
• Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
• SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
• Pixel Difference Networks for Efficient Edge Detection
• LaProp: Separating Momentum and Adaptivity in Adam
• TorchDyn: A Neural Differential Equations Library
• The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
• Structured Reordering for Modeling Latent Alignments in Sequence Transduction
• IoU-aware Single-stage Object Detector for Accurate Localization
• ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
• Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models
• DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition
• Stabilizing Dynamical Systems via Policy Gradient Methods
• CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU
• Weakly-supervised Multi-task Learning for Multimodal Affect Recognition
• AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis
• LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
• Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
• VeRNAl: Mining RNA Structures for Fuzzy Base Pairing Network Motifs
• TensorBNN: Bayesian Inference for Neural Networks using Tensorflow
• SC2EGSet: StarCraft II Esport Replay and Game-state Dataset
• Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function
• Activation Landscapes as a Topological Summary of Neural Network Performance
• Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations
• DeepResp: Deep learning solution for respiration-induced B0 fluctuation artifacts in multi-slice GRE
• hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware
• Improved modularity and new features in ipie: Toward even larger AFQMC calculations on CPUs and GPUs at zero and finite temperatures
• Dynamic backdoor attacks against federated learning
• Pruning via Iterative Ranking of Sensitivity Statistics
• Two-level Group Convolution
• Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing
• Taming Momentum in a Distributed Asynchronous Environment
• Geographic ratemaking with spatial embeddings
• Observation of a rare beta decay of the charmed baryon with a Graph Neural Network
• Centroid Based Concept Learning for RGB-D Indoor Scene Classification
• Online 3D Bin Packing with Constrained Deep Reinforcement Learning
• Neural network relief: a pruning algorithm based on neural activity
• HPC AI500: The Methodology, Tools, Roofline Performance Models, and Metrics for Benchmarking HPC AI Systems
• Self-Supervision Improves Diffusion Models for Tabular Data Imputation
• Categorical Normalizing Flows via Continuous Transformations
• NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
• Search for top squarks in events with a Higgs or $Z$ boson using 139 fb${}^{-1}$ of $pp$ collision data at $\sqrt{s}=13$ TeV with the ATLAS detector
• RNAglib: A Python Package for RNA 2.5D Graphs
• Physical Adversarial Attacks on Deep Neural Networks for Traffic Sign Recognition: A Feasibility Study
• Automatic Kernel Generation for Volta Tensor Cores
• Variational Quanvolutional Neural Networks with enhanced image encoding
• The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
• On Training Implicit Models
• An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks
• Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes
• LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation
• Clinical Relation Extraction Using Transformer-based Models
• Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
• Convolutional Occupancy Networks
• Supervised Learning and the Finite-Temperature String Method for Computing Committor Functions and Reaction Rates
• D2RL: Deep Dense Architectures in Reinforcement Learning
• Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification
• Code Recommendation for Open Source Software Developers
• Partition-based formulations for mixed-integer optimization of trained ReLU neural networks
• Effects of the Nonlinearity in Activation Functions on the Performance of Deep Learning Models
• Generative Models as Distributions of Functions
• When are Deep Networks really better than Decision Forests at small sample sizes, and how?
• MRI-based Material Mass Density and Relative Stopping Power Estimation via Deep Learning for Proton Therapy
• Estimating Model Uncertainty of Neural Networks in Sparse Information Form
• Layer Adaptive Node Selection in Bayesian Neural Networks: Statistical Guarantees and Implementation Details
• Bootstrapping Complete The Look at Pinterest
• DeepFaceEditing: Deep Face Generation and Editing with Disentangled Geometry and Appearance Control
• Single-image Full-body Human Relighting
• What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure
• Contrastive Registration for Unsupervised Medical Image Segmentation
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
• Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
• Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks
• Deep learning-based single-shot computational spectrometer using multilayer thin films
• Probabilistic Multi-modal Trajectory Prediction with Lane Attention for Autonomous Vehicles
• Robust Mutual Learning for Semi-supervised Semantic Segmentation
• Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads
• Flow imaging as an alternative to pressure transducers through vision transformers and convolutional neural networks
• Pipeline Parallelism for Inference on Heterogeneous Edge Computing
• Directional Pruning of Deep Neural Networks
• Physion: Evaluating Physical Prediction from Vision in Humans and Machines
• TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
• FBNetV5: Neural Architecture Search for Multiple Tasks in One Run
• BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning
• Semi-implicit methods for advection equations with explicit forms of numerical solution
• Weakly-supervised Salient Instance Detection
• Layer-wise Characterization of Latent Information Leakage in Federated Learning
• Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
• SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
• Linear Mode Connectivity in Multitask and Continual Learning
• Fisheye Distortion Rectification from Deep Straight Lines
• Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
• CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation
• Lesion Guided Explainable Few Weak-shot Medical Report Generation
• Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspective
• Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
• Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs
• A Competitive Method to VIPriors Object Detection Challenge
• Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses
• An Identifiable Double VAE For Disentangled Representations
• LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection
• In-Place Scene Labelling and Understanding with Implicit Scene Representation
• BoolNet: Minimizing The Energy Consumption of Binary Neural Networks
• A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
• Relax: Composable Abstractions for End-to-End Dynamic Machine Learning
• DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes
• FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
• Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework
• Neural HMMs are all you need (for high-quality attention-free TTS)
• Application of Transfer Learning to Neutrino Interaction Classification
• Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
• How Can CNNs Use Image Position for Segmentation?
• One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation
• Learning Graph Normalization for Graph Neural Networks
• Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
• Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings
• Adversarial Example Games
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
• Certifiable Machine Unlearning for Linear Models
• Neural-network-powered pulse reconstruction from one-dimensional interferometric cross-correlation traces
• A Physical Model for Microstructural Characterization and Segmentation of 3D Tomography Data
• Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation
• Proximity Sensing: Modeling and Understanding Noisy RSSI-BLE Signals and Other Mobile Sensor Data for Digital Contact Tracing
• PAC-Bayes Information Bottleneck
• The mixed deep energy method for resolving concentration features in finite strain hyperelasticity
• Proposal Learning for Semi-Supervised Object Detection
• Neural Radiance Flow for 4D View Synthesis and Video Processing
• AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks
• MICSim: A Modular Simulator for Mixed-signal Compute-in-Memory based AI Accelerator
• What Does CNN Shift Invariance Look Like? A Visualization Study
• Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method
• Training Deep Energy-Based Models with f-Divergence Minimization
• Deep Learning Based Superconductivity: Prediction and Experimental Tests
• LineMVGNN: Anti-Money Laundering with Line-Graph-Assisted Multi-View Graph Neural Networks
• Augmenting Decompiler Output with Learned Variable Names and Types
• Leveraging Subword Embeddings for Multinational Address Parsing
• MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement
• BERTSurv: BERT-Based Survival Models for Predicting Outcomes of Trauma Patients
• Hard-Coded Gaussian Attention for Neural Machine Translation
• Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation
• Operating critical machine learning models in resource constrained regimes
• The Low-Rank Simplicity Bias in Deep Networks
• Enhanced Astronomical Source Classification with Integration of Attention Mechanisms and Vision Transformers
• GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model
• Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
• Does Knowledge Distillation Really Work?
• Efficient Attentions for Long Document Summarization
• Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
• Vectorial phase retrieval in super-resolution polarization microscopy
• SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile
• Hyperbolic Deep Neural Networks: A Survey
• On component interactions in two-stage recommender systems
• A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds
• Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting Robots
• Scalable Bayesian Meta-Learning through Generalized Implicit Gradients
• Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
• Differentiable Physics: A Position Piece
• SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
• Cascaded Text Generation with Markov Transformers
• Convolutional network learning of self-consistent electron density via grid-projected atomic fingerprints
• P${}^2$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
• OCM3D: Object-Centric Monocular 3D Object Detection
• An Improved Yaw Control Algorithm for Wind Turbines via Reinforcement Learning
• HDR Video Reconstruction with Tri-Exposure Quad-Bayer Sensors
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• Unsupervised Discovery of 3D Physical Objects from Video
• Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning
• Behavior From the Void: Unsupervised Active Pre-Training
• Hold me tight! Influence of discriminative features on deep network boundaries
• CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
• Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
• KECRS: Towards Knowledge-Enriched Conversational Recommendation System
• How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization
• Joint Distributions for TensorFlow Probability
• Deep learning polarization distributions in ferroelectrics from STEM data: with and without atom finding
• ODIN: Automated Drift Detection and Recovery in Video Analytics
• BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method
• Towards Better Opioid Antagonists Using Deep Reinforcement Learning
• Automatic cerebral hemisphere segmentation in rat MRI with lesions via attention-based convolutional neural networks
• KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks
• XSepConv: Extremely Separated Convolution
• A Differential-form Pullback Programming Language for Higher-order Reverse-mode Automatic Differentiation
• Differentiable Weighted Finite-State Transducers
• Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee
• SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images
• Optimization of Graph Neural Networks with Natural Gradient Descent
• HooliGAN: Robust, High Quality Neural Vocoding
• Occlusion-Adaptive Deep Network for Robust Facial Expression Recognition
• Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
• Tensor Networks for Medical Image Classification
• TSception: A Deep Learning Framework for Emotion Detection Using EEG
• Semiotic Aggregation in Deep Learning
• COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List
• Training Networks in Null Space of Feature Covariance for Continual Learning
• TransMed: Transformers Advance Multi-modal Medical Image Classification
• A linearized framework and a new benchmark for model selection for fine-tuning
• Eating Garlic Prevents COVID-19 Infection: Detecting Misinformation on the Arabic Content of Twitter
• Cortex: A Compiler for Recursive Deep Learning Models
• MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering
• SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost
• Improving Super-Resolution Performance using Meta-Attention Layers
• AdjointNet: Constraining machine learning models with physics-based codes
• Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring
• HAFLO: GPU-Based Acceleration for Federated Logistic Regression
• HistoCartography: A Toolkit for Graph Analytics in Digital Pathology
• Study of Mass Composition of Cosmic Rays with IceTop and IceCube
• Probabilistic Time Series Forecasting with Implicit Quantile Networks
• Exploring generative atomic models in cryo-EM reconstruction
• Backward-Compatible Prediction Updates: A Probabilistic Approach
• Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China
• Fairness-Aware Node Representation Learning
• Time-Frequency Phase Retrieval for Audio -- The Effect of Transform Parameters
• Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization
• Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
• Differentiable Simulation of Soft Multi-body Systems
• Prescriptive and Descriptive Approaches to Machine-Learning Transparency
• Identifying the Defective: Detecting Damaged Grains for Cereal Appearance Inspection
• CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators
• Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
• Meshfree Variational Physics Informed Neural Networks (MF-VPINN): an adaptive training strategy
• Bexcitonics: Quasi-particle approach to open quantum dynamics
• A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
• High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers
• Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space
• QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
• GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks
• Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning
• Emerging Directions in Geophysical Inversion
• Frame Averaging for Invariant and Equivariant Network Design
• Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain
• A Contrastive Learning Approach to Auroral Identification and Classification
• Unsupervised clothing change adaptive person ReID
• PPGN: Physics-Preserved Graph Networks for Real-Time Fault Location in Distribution Systems with Limited Observation and Labels
• XIRL: Cross-embodiment Inverse Reinforcement Learning
• Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds
• LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface
• DRIVE: One-bit Distributed Mean Estimation
• MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
• Triplet-Watershed for Hyperspectral Image Classification
• Second-order step-size tuning of SGD for non-convex optimization
• Recurrent Localization Networks applied to the Lippmann-Schwinger Equation
• Structure Preservation for the Deep Neural Network Multigrid Solver
• Memory Optimization for Deep Networks
• Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs
• Deep Learning-Based Reconstruction of Interventional Tools from Four X-Ray Projections for Tomographic Interventional Guidance
• Byzantine Fault-Tolerant Distributed Machine Learning Using Stochastic Gradient Descent (SGD) and Norm-Based Comparative Gradient Elimination (CGE)
• Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
• An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
• Cyclic Differentiable Architecture Search
• Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data
• DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling
• A Distributed Multi-GPU System for Large-Scale Node Embedding at Tencent
• Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning
• Towards Persona-Based Empathetic Conversational Models
• Interference and Generalization in Temporal Difference Learning
• Robust Learning with the Hilbert-Schmidt Independence Criterion
• Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks
• Key Protected Classification for Collaborative Learning
• tf.data: A Machine Learning Data Processing Framework
• Monocular, One-stage, Regression of Multiple 3D People
• MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions
• SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification
• Transforming Gaussian Processes With Normalizing Flows
• Theoretical Interpretation of Learned Step Size in Deep-Unfolded Gradient Descent
• Periodic Stochastic Gradient Descent with Momentum for Decentralized Training
• Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks
• On Correctness of Automatic Differentiation for Non-Differentiable Functions
• Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation
• Self-Supervised Learning for Gastritis Detection with Gastric X-ray Images
• Multimodal Fusion Refiner Networks
• Arbitrary Decisions are a Hidden Cost of Differentially Private Training
• Explainable fault and severity classification for rolling element bearings using Kolmogorov-Arnold networks
• Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification
• Learning Convex Optimization Control Policies
• Multi-Time-Scale Input Approaches for Hourly-Scale Rainfall-Runoff Modeling based on Recurrent Neural Networks
• Unsupervised Domain Adaptation in the Absence of Source Data
• Size-Invariant Graph Representations for Graph Classification Extrapolations
• Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
• Convolutional Neural Networks for Shower Energy Prediction in Liquid Argon Time Projection Chambers
• LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
• Reconstructing nodal pressures in water distribution systems with graph neural networks
• Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation
• Self6D: Self-Supervised Monocular 6D Object Pose Estimation
• ESPnet-ST: All-in-One Speech Translation Toolkit
• Personalized Embedding-based e-Commerce Recommendations at eBay
• The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
• DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation
• Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization
• STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation
• Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
• The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest
• Robot Program Parameter Inference via Differentiable Shadow Program Inversion
• Fast and energy-efficient neuromorphic deep learning with first-spike times
• Few-Shot Drum Transcription in Polyphonic Music
• Bayesian Optimization with High-Dimensional Outputs
• Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
• Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks
• SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning
• Disentangling Geometric Deformation Spaces in Generative Latent Shape Models
• Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance
• Intra-model Variability in COVID-19 Classification Using Chest X-ray Images
• Amplitude-assisted tagging of longitudinally polarised bosons using wide neural networks
• VersaGNN: a Versatile accelerator for Graph neural networks
• Evaluating representations by the complexity of learning low-loss predictors
• Asteroid Mining: ACT&Friends' Results for the GTOC 12 Problem
• Balanced-MixUp for Highly Imbalanced Medical Image Classification
• Express Wavenet -- a low parameter optical neural network with random shift wavelet pattern
• ScaDLES: Scalable Deep Learning over Streaming data at the Edge
• Rethinking Global Context in Crowd Counting
• Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI
• OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
• Detection and Classification of mental illnesses on social media using RoBERTa
• TurboTransformers: An Efficient GPU Serving System For Transformer Models
• Unsupervised Domain Adaptation for Automated Knee Osteoarthritis Phenotype Classification
• Stochastic Gradient Descent with Nonlinear Conjugate Gradient-Style Adaptive Momentum
• ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping
• Maximum Likelihood Estimation for Multimodal Learning with Missing Modality
• Modularity in Deep Learning: A Survey
• Lightweight Encoder-Decoder Architecture for Foot Ulcer Segmentation
• Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
• ParaDime: A Framework for Parametric Dimensionality Reduction
• Triple Generative Adversarial Networks
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
• Predictive Scale-Bridging Simulations through Active Learning
• Hierarchical Text Classification As Sub-Hierarchy Sequence Generation
• Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification
• LAMDA-SSL: Semi-Supervised Learning in Python
• Learning to Communicate and Correct Pose Errors
• pyWATTS: Python Workflow Automation Tool for Time Series
• Supervised Learning of Sparsity-Promoting Regularizers for Denoising
• POPDx: An Automated Framework for Patient Phenotyping across 392,246 Individuals in the UK Biobank Study
• ES-Net: An Efficient Stereo Matching Network
• Batch Normalization Orthogonalizes Representations in Deep Random Networks
• Large-Scale Deep Learning Optimizations: A Comprehensive Survey
• MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
• Towards Biologically Plausible Convolutional Networks
• Automatic Testing With Reusable Adversarial Agents
• Efficient Regional Memory Network for Video Object Segmentation
• ASH: A Modern Framework for Parallel Spatial Hashing in 3D Perception
• Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration
• Universal point spread function engineering for 3D optical information processing
• Smart-PGSim: Using Neural Network to Accelerate AC-OPF Power Grid Simulation
• Graph Neural Network Guided Local Search for the Traveling Salesperson Problem
• Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning
• Pipelined Backpropagation at Scale: Training Large Models without Batches
• Learning the structure of wind: A data-driven nonlocal turbulence model for the atmospheric boundary layer
• End-to-end Memory-Efficient Reconstruction for Cone Beam CT
• EPSNet: Efficient Panoptic Segmentation Network with Cross-layer Attention Fusion
• Overinterpretation reveals image classification model pathologies
• Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
• Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
• Asking Crowdworkers to Write Entailment Examples: The Best of Bad Options
• DeepRacing: Parameterized Trajectories for Autonomous Racing
• Open Domain Generalization with Domain-Augmented Meta-Learning
• A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer
• Now You See It, Now You Dont: Adversarial Vulnerabilities in Computational Pathology
• Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation
• Classification with Rejection Based on Cost-sensitive Classification
• Unaligned RGB Guided Hyperspectral Image Super-Resolution with Spatial-Spectral Concordance
• Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking
• Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning
• An RNN-policy gradient approach for quantum architecture search
• Unraveling impacts of polycrystalline microstructures on ionic conductivity of ceramic electrolytes by computational homogenization and machine learning
• Scaling Scaling Laws with Board Games
• Information Obfuscation of Graph Neural Networks
• A Baseline for the Commands For Autonomous Vehicles Challenge
• Stack-based Buffer Overflow Detection using Recurrent Neural Networks
• Performant Automatic Differentiation of Local Coupled Cluster Theories: Response Properties and Ab Initio Molecular Dynamics
• Learning Speaker Embedding with Momentum Contrast
• Preliminary results in using Deep Learning to emulate BLOB, a nuclear interaction model
• Data Distillation for Text Classification
• Neural Machine Translation: A Review of Methods, Resources, and Tools
• Deep Learning with CNNs: A Compact Holistic Tutorial with Focus on Supervised Regression (Preprint)
• SGSeg: Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance
• BoundarySqueeze: Image Segmentation as Boundary Squeezing
• ADiag: Graph Neural Network Based Diagnosis of Alzheimer's Disease
• BaPipe: Exploration of Balanced Pipeline Parallelism for DNN Training
• Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
• SEED: Semantic Graph based Deep detection for type-4 clone
• Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline
• Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
• Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning
• Faster Neural Network Training with Approximate Tensor Operations
• Points2Sound: From mono to binaural audio using 3D point cloud scenes
• Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network
• New Security Challenges on Machine Learning Inference Engine: Chip Cloning and Model Reverse Engineering
• Cross-modal Deep Face Normals with Deactivable Skip Connections
• MS2: Multi-Document Summarization of Medical Studies
• Storchastic: A Framework for General Stochastic Automatic Differentiation
• PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
• Causal Effect Inference for Structured Treatments
• Condenser: a Pre-training Architecture for Dense Retrieval
• Multi-objective Asynchronous Successive Halving
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
• Generalized Negative Correlation Learning for Deep Ensembling
• Prediction Intervals: Split Normal Mixture from Quality-Driven Deep Ensembles
• Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing
• CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
• Lossy compression of statistical data using quantum annealer
• Normalizing flows for random fields in cosmology
• One4all User Representation for Recommender Systems in E-commerce
• S2RMs: Spatially Structured Recurrent Modules
• Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
• Supermasks in Superposition
• COTR: Correspondence Transformer for Matching Across Images
• A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes
• Progressive Point Cloud Deconvolution Generation Network
• Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
• Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
• MixSiam: A Mixture-based Approach to Self-supervised Representation Learning
• MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations
• GenoML: Automated Machine Learning for Genomics
• Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
• Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
• Conditional Extreme Value Theory for Open Set Video Domain Adaptation
• Can Vision Transformers Perform Convolution?
• Robust and Decomposable Average Precision for Image Retrieval
• Shape from Projections via Differentiable Forward Projector for Computed Tomography
• Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detection
• Deep embedded clustering algorithm for clustering PACS repositories
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
• Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT
• Latent Signal Models: Learning Compact Representations of Signal Evolution for Improved Time-Resolved, Multi-contrast MRI
• Simulating the Photon Statistics of Multimode Gaussian States by Automatic Differentiation of Generating Functions
• Towards Full-line Code Completion with Neural Language Models
• PENNI: Pruned Kernel Sharing for Efficient CNN Inference
• GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design
• Ultrahyperbolic Representation Learning
• Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
• Training GANs with Stronger Augmentations via Contrastive Discriminator
• Variational Tensor Neural Networks for Deep Learning
• Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing
• Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
• Generative Adversarial Networks with Physical Evaluators for Spray Simulation of Pintle Injector
• Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks
• Meshless physics-informed deep learning method for three-dimensional solid mechanics
• Inference with Artificial Neural Networks on Analog Neuromorphic Hardware
• Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
• Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme
• A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks
• Predicting Directionality in Causal Relations in Text
• End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering
• Almost Surely Stable Deep Dynamics
• Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections
• Reducing Quantity Hallucinations in Abstractive Summarization
• ComboLoss for Facial Attractiveness Analysis with Squeeze-and-Excitation Networks
• 6D Pose Estimation with Correlation Fusion
• Teaching Robots to Build Simulations of Themselves
• Temporal Context Aggregation for Video Retrieval with Contrastive Learning
• Unsupervised Denoising for Satellite Imagery using Wavelet Subband CycleGAN
• Learnable Spectro-temporal Receptive Fields for Robust Voice Type Discrimination
• Prior choice affects ability of Bayesian neural networks to identify unknowns
• Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision
• An optical diffractive deep neural network with multiple frequency-channels
• A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification
• Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor
• Adaptive Control for Robotic Manipulation of Deformable Linear Objects with Offline and Online Learning of Unknown Models
• On Data Augmentation and Adversarial Risk: An Empirical Analysis
• Bringing Linearly Transformed Cosines to Anisotropic GGX
• Deep Multi-Fidelity Active Learning of High-dimensional Outputs
• MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction
• Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
• The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
• Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods
• AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models
• Convolutional Sparse Coding Fast Approximation with Application to Seismic Reflectivity Estimation
• AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography
• on the effectiveness of generative adversarial network on anomaly detection
• WaveNODE: A Continuous Normalizing Flow for Speech Synthesis
• Streamlining Tensor and Network Pruning in PyTorch
• Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge
• We are More than Our Joints: Predicting how 3D Bodies Move
• It's All Around You: Range-Guided Cylindrical Network for 3D Object Detection
• NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
• Towards Single Stage Weakly Supervised Semantic Segmentation
• Distilling EEG Representations via Capsules for Affective Computing
• Reinforcement Learning for Load-balanced Parallel Particle Tracing
• Fast Transformers with Clustered Attention
• Lesion2Vec: Deep Metric Learning for Few-Shot Multiple Lesions Recognition in Wireless Capsule Endoscopy Video
• Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
• DropCluster: A structured dropout for convolutional networks
• QR-MIX: Distributional Value Function Factorisation for Cooperative Multi-Agent Reinforcement Learning
• Locally Masked Convolution for Autoregressive Models
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks
• Improved RawNet with Feature Map Scaling for Text-independent Speaker Verification using Raw Waveforms
• Monocular Depth Estimators: Vulnerabilities and Attacks
• Storing Encoded Episodes as Concepts for Continual Learning
• EPSILON: An Efficient Planning System for Automated Vehicles in Highly Interactive Environments
• Improving cross-domain brain tissue segmentation in fetal MRI with synthetic data
• Grouped Adaptive Loss Weighting for Person Search
• GOAT: GPU Outsourcing of Deep Learning Training With Asynchronous Probabilistic Integrity Verification Inside Trusted Execution Environment
• Deep Learning for Multi-View Ultrasonic Image Fusion
• Team Phoenix at WASSA 2021: Emotion Analysis on News Stories with Pre-Trained Language Models
• Neural SDEs as Infinite-Dimensional GANs
• AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy
• Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment
• SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
• Visual Time Series Forecasting: An Image-driven Approach
• Assessing Robustness of Deep learning Methods in Dermatological Workflow
• On the use of uncertainty in classifying Aedes Albopictus mosquitoes
• Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
• Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer
• The Differentiable Cross-Entropy Method
• Quantile regression with deep ReLU Networks: Estimators and minimax rates
• Privacy-preserving Decentralized Aggregation for Federated Learning
• Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic
• Deep reinforcement learning for the management of the wall regeneration cycle in wall-bounded turbulent flows
• High-Resolution Optical Flow from 1D Attention and Correlation
• Emotion Recognition for In-the-wild Videos
• TorchKGE: Knowledge Graph Embedding in Python and PyTorch
• Learning A Single Network for Scale-Arbitrary Super-Resolution
• Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
• Framing RNN as a kernel method: A neural ODE approach
• LiDAR Data Enrichment Using Deep Learning Based on High-Resolution Image: An Approach to Achieve High-Performance LiDAR SLAM Using Low-cost LiDAR
• A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
• Image Composition Assessment with Saliency-augmented Multi-pattern Pooling
• Cosmic Background Removal with Deep Neural Networks in SBND
• Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking
• Label Noise SGD Provably Prefers Flat Global Minimizers
• Deep convolutional tensor network
• Better Sign Language Translation with STMC-Transformer
• hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries
• Revisiting consistency for semi-supervised semantic segmentation
• Neural Sentence Ordering Based on Constraint Graphs
• Serverless inferencing on Kubernetes
• Physics-Informed Neural Networks for Transonic Flows around an Airfoil
• Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation
• Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
• Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks
• The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America
• Rock Classification in Petrographic Thin Section Images Based on Concatenated Convolutional Neural Networks
• MEAL: Manifold Embedding-based Active Learning
• Solving Dual Sourcing Problems with Supply Mode Dependent Failure Rates
• Advancing biomolecular understanding and design following human instructions
• Exploring Gradient Flow Based Saliency for DNN Model Compression
• A General Family of Stochastic Proximal Gradient Methods for Deep Learning
• Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
• No RL, No Simulation: Learning to Navigate without Navigating
• Learning to rumble: Automated elephant call classification, detection and endpointing using deep architectures
• Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
• Autograding Mathematical Induction Proofs with Natural Language Processing
• A Framework for Democratizing AI
• Towards Compact CNNs via Collaborative Compression
• A multimodal dataset for understanding the impact of mobile phones on remote online virtual education
• Semantic Segmentation on Swiss3DCities: A Benchmark Study on Aerial Photogrammetric 3D Pointcloud Dataset
• Generalized Bayesian Likelihood-Free Inference
• Multimodal Conditionality for Natural Language Generation
• Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks
• Regularizing Neural Networks via Adversarial Model Perturbation
• Lymph Node Graph Neural Networks for Cancer Metastasis Prediction
• GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
• Positional Encoding as Spatial Inductive Bias in GANs
• Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation
• Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)
• Node Masking: Making Graph Neural Networks Generalize and Scale Better
• An Implicit Physical Face Model Driven by Expression and Style
• Learning State-Dependent Losses for Inverse Dynamics Learning
• Deep Mining External Imperfect Data for Chest X-ray Disease Screening
• Stochastic Aggregation in Graph Neural Networks
• Modeling Ride-Sourcing Matching and Pickup Processes based on Additive Gaussian Process Models
• rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks
• Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters
• Deep Semi-Supervised Learning for Time Series Classification
• CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs
• Facial Affect Recognition in the Wild Using Multi-Task Learning Convolutional Network
• Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
• Visual analogy: Deep learning versus compositional models
• Deep Survival Machines: Fully Parametric Survival Regression and Representation Learning for Censored Data with Competing Risks
• Local and Global Context-Based Pairwise Models for Sentence Ordering
• Learning Rich Features for Gait Recognition by Integrating Skeletons and Silhouettes
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation
• VEGA: Towards an End-to-End Configurable AutoML Pipeline
• Automatic differentiation of Sylvester, Lyapunov, and algebraic Riccati equations
• Frequency-compensated PINNs for Fluid-dynamic Design Problems
• Learning Practically Feasible Policies for Online 3D Bin Packing
• Topographic VAEs learn Equivariant Capsules
• Link Prediction using Graph Neural Networks for Master Data Management
• Commutative Lie Group VAE for Disentanglement Learning
• Adversarial Attack and Defense in Deep Ranking
• Semantic Graph Based Place Recognition for 3D Point Clouds
• A light neural network for modulation detection under impairments
• Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID
• Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
• Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
• End-to-end Learning Improves Static Object Geo-localization in Monocular Video
• Robust Semantic Segmentation with Superpixel-Mix
• Conditional Directed Graph Convolution for 3D Human Pose Estimation
• Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning
• Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
• Neural Methods for Point-wise Dependency Estimation
• Optimizing Prediction Serving on Low-Latency Serverless Dataflow
• Human-in-the-loop Extraction of Interpretable Concepts in Deep Learning Models
• Fast and Flexible Temporal Point Processes with Triangular Maps
• Enhancing Knowledge Tracing via Adversarial Training
• Listen carefully and tell: an audio captioning system based on residual learning and gammatone audio representation
• Multi-Manifold Learning for Large-scale Targeted Advertising System
• GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks
• Enhancing SAT solvers with glue variable predictions
• TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network
• Fluid registration between lung CT and stationary chest tomosynthesis images
• A General Framework for Survival Analysis and Multi-State Modelling
• ECAS-ML: Edge Computing Assisted Adaptation Scheme with Machine Learning for HTTP Adaptive Streaming
• Optimizing Neural Networks via Koopman Operator Theory
• AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning
• Embed Me If You Can: A Geometric Perceptron
• Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage
• QT-Routenet: Improved GNN generalization to larger 5G networks by fine-tuning predictions from queueing theory
• Meta Approach to Data Augmentation Optimization
• Low-light Image Restoration with Short- and Long-exposure Raw Pairs
• Human brain activity for machine attention
• Generalised Interpretable Shapelets for Irregular Time Series
• Interaction-Aware Trajectory Prediction of Connected Vehicles using CNN-LSTM Networks
• Parameter inference for coalescing massive black hole binaries using deep learning
• Amortised Experimental Design and Parameter Estimation for User Models of Pointing
• SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization
• Semi-supervised Image Classification with Grad-CAM Consistency
• Neighbourhood-Insensitive Point Cloud Normal Estimation Network
• Adaptive Learning of Tensor Network Structures
• Improved Lite Audio-Visual Speech Enhancement
• Learning Global and Local Consistent Representations for Unsupervised Image Retrieval via Deep Graph Diffusion Networks
• QR and LQ Decomposition Matrix Backpropagation Algorithms for Square, Wide, and Deep -- Real or Complex -- Matrices and Their Software Implementation
• Spatial-Adaptive Network for Single Image Denoising
• A Photonic-Circuits-Inspired Compact Network: Toward Real-Time Wireless Signal Classification at the Edge
• An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
• Lightning IR: Straightforward Fine-tuning and Inference of Transformer-based Language Models for Information Retrieval
• Ranking over Regression for Bayesian Optimization and Molecule Selection
• Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification
• XLVIN: eXecuted Latent Value Iteration Nets
• Window-based Channel Attention for Wavelet-enhanced Learned Image Compression
• NeCA: 3D Coronary Artery Tree Reconstruction from Two 2D Projections via Neural Implicit Representation
• Open-Set Biometrics: Beyond Good Closed-Set Models
• BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?
• Complementary polynomials in quantum signal processing
• Stroke Constrained Attention Network for Online Handwritten Mathematical Expression Recognition
• Enriched BERT Embeddings for Scholarly Publication Classification
• Optimized higher-order photon state classification by machine learning
• Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders
• Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests
• TextHide: Tackling Data Privacy in Language Understanding Tasks
• Ranking Clarifying Questions Based on Predicted User Engagement
• Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothing
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
• Learning Dynamics from Noisy Measurements using Deep Learning with a Runge-Kutta Constraint
• Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World
• GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training
• Approximating Instance-Dependent Noise via Instance-Confidence Embedding
• ViMQ: A Vietnamese Medical Question Dataset for Healthcare Dialogue System Development
• Self-Supervised Siamese Autoencoders
• Photon-number moments and cumulants of Gaussian states
• Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
• Sequential Neural Posterior and Likelihood Approximation
• NeRD: Neural Representation of Distribution for Medical Image Segmentation
• Multi-modal anticipation of stochastic trajectories in a dynamic environment with Conditional Variational Autoencoders
• Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
• K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
• Towards Deployable OCR models for Indic languages
• LazyTensor: combining eager execution with domain-specific compilers
• What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
• AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
• Nondeterminism and Instability in Neural Network Optimization
• Fast Certified Robust Training with Short Warmup
• Unsupervised Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation via Semi-supervised Learning and Label Fusion
• Validation and Generalizability of Self-Supervised Image Reconstruction Methods for Undersampled MRI
• Temporal Probability Calibration
• Shennong: a Python toolbox for audio speech features extraction
• F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning
• TempoRL: Learning When to Act
• Deep Learning for Moving Blockage Prediction using Real Millimeter Wave Measurements
• A Highly Configurable Hardware/Software Stack for DNN Inference Acceleration
• Performance Comparison for Scientific Computations on the Edge via Relative Performance
• Ivy: Templated Deep Learning for Inter-Framework Portability
• Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
• Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional
• Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
• Measuring Dependence with Matrix-based Entropy Functional
• SceneGen: Learning to Generate Realistic Traffic Scenes
• Reduction of transient noise artifacts in gravitational-wave data using deep learning
• sbp-env: Sampling-based Motion Planners' Testing Environment
• $M^3$T: Multi-Modal Continuous Valence-Arousal Estimation in the Wild
• NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM
• Positional Encoder Graph Neural Networks for Geographic Data
• Bayesian Optimization for Cascade-type Multi-stage Processes
• Differentiable quantum computational chemistry with PennyLane
• ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks
• The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
• Towards Interpretable Attention Networks for Cervical Cancer Analysis
• Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices
• Path Integral Sampler: a stochastic control approach for sampling
• Yelp Review Rating Prediction: Machine Learning and Deep Learning Models
• Adaptive Sample Selection for Robust Learning under Label Noise
• EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
• Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
• Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
• Rethinking Person Re-Identification via Semantic-Based Pretraining
• Trajectory Prediction with Latent Belief Energy-Based Model
• Dependency Aware Filter Pruning
• On Training and Evaluation of Neural Network Approaches for Model Predictive Control
• Object Tracking by Jointly Exploiting Frame and Event Domain
• Investigating the Effects of Sparse Attention on Cross-Encoders
• Event-based Action Recognition Using Timestamp Image Encoding Network
• Efficiency Parameterization with Neural Networks
• Atss-Net: Target Speaker Separation via Attention-based Neural Network
• Synthesizing Particle-in-Cell Simulations Through Learning and GPU Computing for Hybrid Particle Accelerator Beamlines
• A pipeline for fair comparison of graph neural networks in node classification tasks
• Arrhenius.jl: A Differentiable Combustion SimulationPackage
• Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation
• OSP: Boosting Distributed Model Training with 2-stage Synchronization
• Positive-Congruent Training: Towards Regression-Free Model Updates
• Can we Estimate Truck Accident Risk from Telemetric Data using Machine Learning?
• PAC-Bayesian Contrastive Unsupervised Representation Learning
• ACORNS: An Easy-To-Use Code Generator for Gradients and Hessians
• KheOps: Cost-effective Repeatability, Reproducibility, and Replicability of Edge-to-Cloud Experiments
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
• DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification
• ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration
• Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
• Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment
• Deep Reinforcement Learning based Group Recommender System
• On Evolving Attention Towards Domain Adaptation
• CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
• Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms using Learned Interactions
• Exploiting Shared Knowledge from Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation
• Surprisal-Triggered Conditional Computation with Neural Networks
• Going faster to see further: GPU-accelerated value iteration and simulation for perishable inventory control using JAX
• Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition
• Lemmas: Generation, Selection, Application
• Data-Dependent Randomized Smoothing
• Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST)
• Power Consumption Variation over Activation Functions
• Anomaly Detection using Ensemble Classification and Evidence Theory
• YANMTT: Yet Another Neural Machine Translation Toolkit
• Attention-Based Learning on Molecular Ensembles
• Cogradient Descent for Bilinear Optimization
• CNN Acceleration by Low-rank Approximation with Quantized Factors
• GENNAPE: Towards Generalized Neural Architecture Performance Estimators
• Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning
• AraCOVID19-SSD: Arabic COVID-19 Sentiment and Sarcasm Detection Dataset
• Greedy Gradient Ensemble for Robust Visual Question Answering
• Adaptive Approach For Sparse Representations Using The Locally Competitive Algorithm For Audio
• Robust Variational Autoencoder for Tabular Data with Beta Divergence
• Diverse Semantic Image Synthesis via Probability Distribution Modeling
• Collective Learning by Ensembles of Altruistic Diversifying Neural Networks
• Leveraging Event Specific and Chunk Span features to Extract COVID Events from tweets
• Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives
• CL2R: Compatible Lifelong Learning Representations
• Proof-of-Learning: Definitions and Practice
• A physics-defined recurrent neural network to compute coherent light wave scattering on the millimetre scale
• Strength from Weakness: Fast Learning Using Weak Supervision
• Generalizing Downsampling from Regular Data to Graphs
• MomentumRNN: Integrating Momentum into Recurrent Neural Networks
• Non-local Recurrent Regularization Networks for Multi-view Stereo
• Memory-efficient Learning for High-Dimensional MRI Reconstruction
• Deep MRI Reconstruction with Radial Subsampling
• Data Streaming and Traffic Gathering in Mesh-based NoC for Deep Neural Network Acceleration
• Needle tip force estimation by deep learning from raw spectral OCT data
• SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation
• Pufferfish: Communication-efficient Models At No Extra Cost
• DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge
• Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
• Feature Extraction for Novelty Detection in Network Traffic
• Spatio-Temporal Representation Factorization for Video-based Person Re-Identification
• Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
• Learning compositional functions via multiplicative weight updates
• Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms
• Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
• DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
• SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)
• A Study of Compositional Generalization in Neural Models
• Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
• Characteristics of Monte Carlo Dropout in Wide Neural Networks
• Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation
• MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks
• Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
• Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants
• The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers
• IFedAvg: Interpretable Data-Interoperability for Federated Learning
• Antithetic Riemannian Manifold And Quantum-Inspired Hamiltonian Monte Carlo
• Weisfeiler and Lehman Go Cellular: CW Networks
• Automatic airway segmentation from Computed Tomography using robust and efficient 3-D convolutional neural networks
• Kernel Stein Discrepancy Descent
• BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
• Fast Differentiable Clipping-Aware Normalization and Rescaling
• Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry
• Neural Spatio-Temporal Point Processes
• Are Transformers More Robust? Towards Exact Robustness Verification for Transformers
• ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification
• Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks
• Learning with Algorithmic Supervision via Continuous Relaxations
• XCloud: Design and Implementation of AI Cloud Platform with RESTful API Service
• Numerical approaches for investigating quasiconvexity in the context of Morrey's conjecture
• Transferring Domain-Agnostic Knowledge in Video Question Answering
• Evolving to learn: discovering interpretable plasticity rules for spiking networks
• Direction is what you need: Improving Word Embedding Compression in Large Language Models
• Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization
• Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
• Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
• IDOL: Inertial Deep Orientation-Estimation and Localization
• CogDL: A Comprehensive Library for Graph Deep Learning
• Relation Transformer Network
• Do sequence-to-sequence VAEs learn global features of sentences?
• Environment Predictive Coding for Embodied Agents
• Traffic flow prediction using Deep Sedenion Networks
• NeuralProphet: Explainable Forecasting at Scale
• xAI-GAN: Enhancing Generative Adversarial Networks via Explainable AI Systems
• Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing
• Learning Continuous Environment Fields via Implicit Functions
• Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation
• Secure Domain Adaptation with Multiple Sources
• A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI
• Multi-Facet Clustering Variational Autoencoders
• Enabling Automated FPGA Accelerator Optimization Using Graph Neural Networks
• The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective
• Adversarial Examples on Segmentation Models Can be Easy to Transfer
• Shape As Points: A Differentiable Poisson Solver
• Measuring Generalization with Optimal Transport
• MLDemon: Deployment Monitoring for Machine Learning Systems
• A Theoretical Analysis of Fine-tuning with Linear Teachers
• GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy
• Efficient Document Image Classification Using Region-Based Graph Neural Network
• Utilizing Explainable AI for Quantization and Pruning of Deep Neural Networks
• End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
• Reconstructing missing seismic data using Deep Learning
• Generative Zero-shot Network Quantization
• Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning
• Constrained Feedforward Neural Network Training via Reachability Analysis
• Neural-Swarm: Decentralized Close-Proximity Multirotor Control Using Learned Interactions
• Differentiating a Tensor Language
• Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
• The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding
• Few-NERD: A Few-Shot Named Entity Recognition Dataset
• Deep Reinforcement Learning in Fluid Mechanics: a promising method for both Active Flow Control and Shape Optimization
• 3D-to-2D Distillation for Indoor Scene Parsing
• GAN Cocktail: mixing GANs without dataset access
• QDCNN: Quantum Dilated Convolutional Neural Network
• Neural Spectrahedra and Semidefinite Lifts: Global Convex Optimization of Polynomial Activation Neural Networks in Fully Polynomial-Time
• Zero in on Shape: A Generic 2D-3D Instance Similarity Metric learned from Synthetic Data
• Equinox: neural networks in JAX via callable PyTrees and filtered transformations
• Learning Debiased and Disentangled Representations for Semantic Segmentation
• Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
• Optimising for Interpretability: Convolutional Dynamic Alignment Networks
• Impact of individual rater style on deep learning uncertainty in medical imaging segmentation
• DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering
• UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation
• Accelerating SpMM Kernel with Cache-First Edge Sampling for Graph Neural Networks
• Discovery of slow variables in a class of multiscale stochastic systems via neural networks
• SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning
• SSLIDE: Sound Source Localization for Indoors based on Deep Learning
• Meta Learning for Few-Shot One-class Classification
• DeepHunter: A Graph Neural Network Based Approach for Robust Cyber Threat Hunting
• Adaptive Graph Integration for Cross-Domain Recommendation via Heterogeneous Graph Coordinators
• Self-Supervised Pillar Motion Learning for Autonomous Driving
• Mixture Proportion Estimation and PU Learning: A Modern Approach
• DOTS: Decoupling Operation and Topology in Differentiable Architecture Search
• Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
• Energy-Based Models for Code Generation under Compilability Constraints
• Computation on Sparse Neural Networks: an Inspiration for Future Hardware
• Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction
• Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals
• Embedding Adaptation is Still Needed for Few-Shot Learning
• Development and Application of Self-Supervised Machine Learning for Smoke Plume and Active Fire Identification from the FIREX-AQ Datasets
• Interpolating Points on a Non-Uniform Grid using a Mixture of Gaussians
• A First Principles Approach for Data-Efficient System Identification of Spring-Rod Systems via Differentiable Physics Engines
• Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
• Learning Gaussian Maps for Dense Object Detection
• VASARI-auto: equitable, efficient, and economical featurisation of glioma MRI
• Instance-wise Graph-based Framework for Multivariate Time Series Forecasting
• Effect of the output activation function on the probabilities and errors in medical image segmentation
• Can one hear the shape of a neural network?: Snooping the GPU via Magnetic Side Channel
• Integrating Sensing and Communication in Cellular Networks via NR Sidelink
• Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition
• GPT-2C: A GPT-2 parser for Cowrie honeypot logs
• Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
• Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models
• VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
• Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation
• ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills
• DISC: A Dynamic Shape Compiler for Machine Learning Workloads
• Learning Density Distribution of Reachable States for Autonomous Systems
• Statistically Significant Stopping of Neural Network Training
• Better Set Representations For Relational Reasoning
• Machine learning the 2D percolation model
• Globally Optimal Segmentation of Mutually Interacting Surfaces using Deep Learning
• Jet Single Shot Detection
• Assessing Phrasal Representation and Composition in Transformers
• Gradient-based algorithms for multi-objective bi-level optimization
• GLSD: The Global Large-Scale Ship Database and Baseline Evaluations
• Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification
• Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes
• Learning Composable Energy Surrogates for PDE Order Reduction
• Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs
• $\xi$-torch: differentiable scientific computing library
• Deep Reinforcement Learning in Lane Merge Coordination for Connected Vehicles
• Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils
• Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity
• Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours
• Deep Neural Network Training with Frank-Wolfe
• A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
• Deep Relighting Networks for Image Light Source Manipulation
• Rethinking Sampling Strategies for Unsupervised Person Re-identification
• DistStat.jl: Towards Unified Programming for High-Performance Statistical Computing Environments in Julia
• MFEViT: A Robust Lightweight Transformer-based Network for Multimodal 2D+3D Facial Expression Recognition
• Unsupervised Sound Localization via Iterative Contrastive Learning
• Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
• Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting
• Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks
• BeeTLe: An Imbalance-Aware Deep Sequence Model for Linear B-Cell Epitope Prediction and Classification with Logit-Adjusted Losses
• Self-Tuning Hamiltonian Monte Carlo for Accelerated Sampling
• A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data
• Pushing the Envelope of Thin Crack Detection
• M-FAC: Efficient Matrix-Free Approximations of Second-Order Information
• CPOT: Channel Pruning via Optimal Transport
• FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction
• A Generalizable Approach to Learning Optimizers
• IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
• Neural Collaborative Graph Machines for Table Structure Recognition
• Jet tagging in the Lund plane with graph networks
• Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
• Exploring Dense Retrieval for Dialogue Response Selection
• Domain-specific MT for Low-resource Languages: The case of Bambara-French
• Visually Grounded Continual Learning of Compositional Phrases
• Unmixing Convolutional Features for Crisp Edge Detection
• Searching for Fast Model Families on Datacenter Accelerators
• Comparing Machine Learning based Segmentation Models on Jet Fire Radiation Zones
• Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
• TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations
• A Study of Checkpointing in Large Scale Training of Deep Neural Networks
• Deep Tensor CCA for Multi-view Learning
• Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
• Deep differentiable forest with sparse attention for the tabular data
• Efficient, Simple and Automated Negative Sampling for Knowledge Graph Embedding
• Multi-Stage Prototype Learning for Interpretable Time Series Classification
• Deep-RLS: A Model-Inspired Deep Learning Approach to Nonlinear PCA
• EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy
• Bidirectional Projection Network for Cross Dimension Scene Understanding
• Internal Wasserstein Distance for Adversarial Attack and Defense
• Character Queries: A Transformer-based Approach to On-Line Handwritten Character Segmentation
• Sparse Spiking Gradient Descent
• Using differentiable programming to obtain an energy and density-optimized exchange-correlation functional
• Not Color Blind: AI Predicts Racial Identity from Black and White Retinal Vessel Segmentations
• Predicting Terrain Mechanical Properties in Sight for Planetary Rovers with Semantic Clues
• Generating 3D People in Scenes without People
• Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control
• PGMAN: An Unsupervised Generative Multi-adversarial Network for Pan-sharpening
• Scene-Intuitive Agent for Remote Embodied Visual Grounding
• Privacy-preserving Collaborative Learning with Automatic Transformation Search
• Differentiating through Log-Log Convex Programs
• Randomized Overdrive Neural Networks
• TextBox: A Unified, Modularized, and Extensible Framework for Text Generation
• A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow
• Cross-Layer Distillation with Semantic Calibration
• StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision
• MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
• ShadowTutor: Distributed Partial Distillation for Mobile Video DNN Inference
• Knowledge Guided Named Entity Recognition for BioMedical Text
• On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
• Learnable Companding Quantization for Accurate Low-bit Neural Networks
• Evolutionary Augmentation Policy Optimization for Self-supervised Learning
• AstronomicAL: An interactive dashboard for visualisation, integration and classification of data using Active Learning
• Attention module improves both performance and interpretability of 4D fMRI decoding neural network
• Semantic Bilinear Pooling for Fine-Grained Recognition
• PyTorrent: A Python Library Corpus for Large-scale Language Models
• Adversarially Optimized Mixup for Robust Classification
• Adaptive Sampling Distributed Stochastic Variance Reduced Gradient for Heterogeneous Distributed Datasets
• Dynamically Throttleable Neural Networks (TNN)
• Tree Decomposed Graph Neural Network
• Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images
• Personalized acute stress classification from physiological signals with neural processes
• Hardware Acceleration of Explainable Machine Learning using Tensor Processing Units
• Detecting Information Relays in Deep Neural Networks
• Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks
• Deep IDA: A Deep Learning Method for Integrative Discriminant Analysis of Multi-View Data with Feature Ranking -- An Application to COVID-19 severity
• Efficient and Less Centralized Federated Learning
• Hybrid Classical-Quantum method for Diabetic Foot Ulcer Classification
• Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
• Artificial intelligence for improved fitting of trajectories of elementary particles in inhomogeneous dense materials immersed in a magnetic field
• Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks
• OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework
• HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
• Accelerating GMRES with Deep Learning in Real-Time
• Active Perception for Ambiguous Objects Classification
• Learning by Cheating
• FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Framework for Heterogeneous Edge Devices
• PAM: Pose Attention Module for Pose-Invariant Face Recognition
• OkwuGbé: End-to-End Speech Recognition for Fon and Igbo
• Towards Automated Anamnesis Summarization: BERT-based Models for Symptom Extraction
• On the relationship between class selectivity, dimensionality, and robustness
• Heterogeneous Graph Attention Networks for Learning Diverse Communication
• Practical Encrypted Computing for IoT Clients
• Neural Status Registers
• Learning to Deceive in Multi-Agent Hidden Role Games
• A sampling-guided unsupervised learning method to capture percolation in complex networks
• A Runtime-Based Computational Performance Predictor for Deep Neural Network Training
• Generative View Synthesis: From Single-view Semantics to Novel-view Images
• Automated Optical Multi-layer Design via Deep Reinforcement Learning
• Optimal Gradient Quantization Condition for Communication-Efficient Distributed Training
• Locating Cephalometric X-Ray Landmarks with Foveated Pyramid Attention
• Efficient hyperparameter optimization by way of PAC-Bayes bound minimization
• Neural Pharmacodynamic State Space Modeling
• Continuous-Time Model-Based Reinforcement Learning
• ConvNets vs. Transformers: Whose Visual Representations are More Transferable?
• Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
• PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization
• m-RevNet: Deep Reversible Neural Networks with Momentum
• ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
• NeuralMag: an open-source nodal finite-difference code for inverse micromagnetics
• Approximations in Deep Learning
• MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video
• Learning to Predict Trustworthiness with Steep Slope Loss
• Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding
• Brain Atlas Guided Attention U-Net for White Matter Hyperintensity Segmentation
• Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
• VirtualFlow: Decoupling Deep Learning Models from the Underlying Hardware
• In Search of Robust Measures of Generalization
• Scaling Up Exact Neural Network Compression by ReLU Stability
• Distributed Deep Learning in Open Collaborations
• Iterative Amortized Policy Optimization
• Automated Discovery of Adaptive Attacks on Adversarial Defenses
• Sliding Sequential CVAE with Time Variant Socially-aware Rethinking for Trajectory Prediction
• fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
• WDNet: Watermark-Decomposition Network for Visible Watermark Removal
• Lottery Jackpots Exist in Pre-trained Models
• Switching Transferable Gradient Directions for Query-Efficient Black-Box Adversarial Attacks
• Longitudinal Variational Autoencoder
• RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads
• A Diffusion Approximation Theory of Momentum SGD in Nonconvex Optimization
• Instance and Panoptic Segmentation Using Conditional Convolutions
• A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis
• Calibrating LiDAR and Camera using Semantic Mutual information
• DiffRenderGAN: Addressing Training Data Scarcity in Deep Segmentation Networks for Quantitative Nanomaterial Analysis through Differentiable Rendering and Generative Modelling
• Self-supervised Representation Learning with Relative Predictive Coding
• Deep Sinogram Completion with Image Prior for Metal Artifact Reduction in CT Images
• Dynamic population-based meta-learning for multi-agent communication with natural language
• TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications
• Fibro-CoSANet: Pulmonary Fibrosis Prognosis Prediction using a Convolutional Self Attention Network
• A Recipe for Global Convergence Guarantee in Deep Neural Networks
• PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
• Effective Distant Supervision for Temporal Relation Extraction
• MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendation
• Transfer Learning in Electronic Health Records through Clinical Concept Embedding
• Spline parameterization of neural network controls for deep learning
• Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
• Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection
• Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
• Learning Representations that Support Robust Transfer of Predictors
• A Physics-Constrained Deep Learning Model for Simulating Multiphase Flow in 3D Heterogeneous Porous Media
• Deep-learning design of graphene metasurfaces for quantum control and Dirac electron holography
• OAH-Net: A Deep Neural Network for Hologram Reconstruction of Off-axis Digital Holographic Microscope
• PyTorch, Explain! A Python library for Logic Explained Networks
• Biomechanical modelling of brain atrophy through deep learning
• Neural Pruning via Growing Regularization
• Compressing CNN Kernels for Videos Using Tucker Decompositions: Towards Lightweight CNN Applications
• Data-driven Hi2Lo for Coarse-grid System Thermal Hydraulic Modeling
• Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
• COPS: Controlled Pruning Before Training Starts
• Dynamic Group Convolution for Accelerating Convolutional Neural Networks
• A Pragmatic Look at Deep Imitation Learning
• MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Images
• Online Knowledge Distillation via Multi-branch Diversity Enhancement
• A User's Guide to Calibrating Robotics Simulators
• A Novel Training Protocol for Performance Predictors of Evolutionary Neural Architecture Search Algorithms
• Untrained neural networks can demonstrate memorization-independent abstract reasoning
• Unified Framework for Calculating Convex Roof Resource Measures
• DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
• The Base Measure Problem and its Solution
• Federated CycleGAN for Privacy-Preserving Image-to-Image Translation
• Adaptive Feature Alignment for Adversarial Training
• Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
• SDGMNet: Statistic-based Dynamic Gradient Modulation for Local Descriptor Learning
• Deep Canonical Correlation Alignment for Sensor Signals
• Co-Transport for Class-Incremental Learning
• AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding
• IrEne: Interpretable Energy Prediction for Transformers
• Effective Evaluation of Deep Active Learning on Image Classification Tasks
• Deeper Learning By Doing: Integrating Hands-On Research Projects Into a Machine Learning Course
• Linking Common Vulnerabilities and Exposures to the MITRE ATT&CK Framework: A Self-Distillation Approach
• Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference
• On the Interplay Between Fine-tuning and Composition in Transformers
• Exemplar-Based Open-Set Panoptic Segmentation Network
• Accelerating Gossip SGD with Periodic Global Averaging
• Self-Supervised Learning for Fine-Grained Visual Categorization
• Evaluating Transformers for Lightweight Action Recognition
• Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
• Using Graph Neural Networks to model the performance of Deep Neural Networks
• Physics-Informed Graph Convolutional Networks: Towards a generalized framework for complex geometries
• Discovering Fatigued Movements for Virtual Character Animation
• Sim-to-Real Deep Reinforcement Learning with Manipulators for Pick-and-place
• Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning
• Spectral Densities, Structured Noise and Ensemble Averaging within Open Quantum Dynamics
• Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design
• Evaluating Convolutional Neural Networks for COVID-19 classification in chest X-ray images
• PASSION for Dermatology: Bridging the Diversity Gap with Pigmented Skin Images from Sub-Saharan Africa
• Learning Aerodynamics for the Control of Flying Humanoid Robots
• Simultaneous Model-Based Evolution of Constants and Expression Structure in GP-GOMEA for Symbolic Regression
• Deep Learning-Based Transfer Learning for Classification of Cassava Disease
• Implicit Neural Representations for Chemical Reaction Paths
• Community Research Earth Digital Intelligence Twin (CREDIT)
• Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction
• SRG/eROSITA 3D mapping of the ISM using X-ray absorption spectroscopy
• Dreaming of Electrical Waves: Generative Modeling of Cardiac Excitation Waves using Diffusion Models
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks
• SWoTTeD: An Extension of Tensor Decomposition to Temporal Phenotyping
• HyGCN: A GCN Accelerator with Hybrid Architecture
• Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild
• Low-Resource Multi-Granularity Academic Function Recognition Based on Multiple Prompt Knowledge
• Effect of latent space distribution on the segmentation of images with multiple annotations
• Subdimensional Expansion Using Attention-Based Learning For Multi-Agent Path Finding
• Personalized Retrogress-Resilient Framework for Real-World Medical Federated Learning
• Cluster Analysis with Deep Embeddings and Contrastive Learning
• Effectiveness of Optimization Algorithms in Deep Image Classification
• Simplicity Bias Leads to Amplified Performance Disparities
• Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization
• Composition of Relational Features with an Application to Explaining Black-Box Predictors
• Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs
• TESDA: Transform Enabled Statistical Detection of Attacks in Deep Neural Networks
• Dynamic Feature Alignment for Semi-supervised Domain Adaptation
• An Empirical Study of Graph Contrastive Learning
• POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
• Correlation inference attacks against machine learning models
• Exploring Transformer Based Models to Identify Hate Speech and Offensive Content in English and Indo-Aryan Languages
• NeRV: Neural Representations for Videos
• MUNet: Motion Uncertainty-aware Semi-supervised Video Object Segmentation
• COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression
• Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay
• Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
• Implicit SVD for Graph Representation Learning
• Can Information Flows Suggest Targets for Interventions in Neural Circuits?
• A reduced order Schwarz method for nonlinear multiscale elliptic equations based on two-layer neural networks
• Sketch-Driven Regular Expression Generation from Natural Language and Examples
• Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation
• Learning Eye-in-Hand Camera Calibration from a Single Image
• Use of 1D-CNN for input data size reduction of LSTM in Hourly Rainfall-Runoff modeling
• Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification
• Encoding-based Memory Modules for Recurrent Neural Networks
• Problems using deep generative models for probabilistic audio source separation
• Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
• Deep Policies for Online Bipartite Matching: A Reinforcement Learning Approach
• A Continuous Optimisation Benchmark Suite from Neural Network Regression
• Fine-grained Data Distribution Alignment for Post-Training Quantization
• Adversarially Regularized Policy Learning Guided by Trajectory Optimization
• Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes
• MoNet: Motion-based Point Cloud Prediction Network
• A Worrying Analysis of Probabilistic Time-series Models for Sales Forecasting
• Learning C to x86 Translation: An Experiment in Neural Compilation
• CRACT: Cascaded Regression-Align-Classification for Robust Visual Tracking
• Opportunistic Emulation of Computationally Expensive Simulations via Deep Learning
• Data-informed Deep Optimization
• DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
• Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation
• Query Embedding on Hyper-relational Knowledge Graphs
• Finding and Fixing Spurious Patterns with Explanations
• Explainable Link Prediction for Privacy-Preserving Contact Tracing
• Understanding Dynamics of Nonlinear Representation Learning and Its Application
• Learn-Prune-Share for Lifelong Learning
• SAFCAR: Structured Attention Fusion for Compositional Action Recognition
• Partial Graph Reasoning for Neural Network Regularization
• Deep Self-Supervised Representation Learning for Free-Hand Sketch
• Grounding inductive biases in natural images:invariance stems from variations in data
• An End-to-End Document-Level Neural Discourse Parser Exploiting Multi-Granularity Representations
• Agatha: Smart Contract for DNN Computation
• Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Bounds
• Reinforcement Learning and Control of a Lower Extremity Exoskeleton for Squat Assistance
• Security Vulnerability Detection Using Deep Learning Natural Language Processing
• Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss
• Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning
• 3D U-NetR: Low Dose Computed Tomography Reconstruction via Deep Learning and 3 Dimensional Convolutions
• Adaptive Synthetic Characters for Military Training
• Sparse Uncertainty Representation in Deep Learning with Inducing Weights
• Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX
• Neighborhood-Aware Neural Architecture Search
• Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units
• Feasibility-based Fixed Point Networks
• PyTorch Tabular: A Framework for Deep Learning with Tabular Data
• Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning
• PyTorch-Direct: Enabling GPU Centric Data Access for Very Large Graph Neural Network Training with Irregular Accesses
• Improving Few-Shot Learning with Auxiliary Self-Supervised Pretext Tasks
• Categorical semantics of a simple differential programming language
• An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker
• You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries
• Universal Off-Policy Evaluation
• One-Round Active Learning
• Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction
• Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies
• MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks
• The landscape of software for tensor computations
• Multimodal End-to-End Sparse Model for Emotion Recognition
• Handling Missing Observations with an RNN-based Prediction-Update Cycle
• GISE-51: A scalable isolated sound events dataset
• GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software
• BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection
• Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network
• Towards Open World Object Detection
• Swift for TensorFlow: A portable, flexible platform for deep learning
• Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition
• Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks
• A Bayesian neural network predicts the dissolution of compact planetary systems
• Embedded methods for feature selection in neural networks
• MC-LSTM: Mass-Conserving LSTM
• K-Deep Simplex: Deep Manifold Learning via Local Dictionaries
• GPU Accelerated Exhaustive Search for Optimal Ensemble of Black-Box Optimization Algorithms
• A Challenge Obfuscating Interface for Arbiter PUF Variants against Machine Learning Attacks
• GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction
• DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation
• Merchant Category Identification Using Credit Card Transactions
• DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes
• Automatic Graph Partitioning for Very Large-scale Deep Learning
• Where Are You? Localization from Embodied Dialog
• Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
• Interpretable Deep Learning for Automatic Diagnosis of 12-lead Electrocardiogram
• Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation
• MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
• Examining the Ordering of Rhetorical Strategies in Persuasive Requests
• Biomedical Event Extraction with Hierarchical Knowledge Graphs
• Unsupervised Joint $k$-node Graph Representations with Compositional Energy-Based Models
• Principled Interpolation in Normalizing Flows
• Pointwise Binary Classification with Pairwise Confidence Comparisons
• Distributed Learning of Finite Gaussian Mixtures
• Importance Reweighting for Biquality Learning
• Meta-Learning for Domain Generalization in Semantic Parsing
• When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision
• High-Capacity Expert Binary Networks
• ASL Recognition with Metric-Learning based Lightweight Network
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting
• Deep Learning-based Pipeline for Module Power Prediction from EL Measurements
• PyRetri: A PyTorch-based Library for Unsupervised Image Retrieval by Deep Convolutional Neural Networks
• deepSELF: An Open Source Deep Self End-to-End Learning Framework
• Bayesian Hidden Physics Models: Uncertainty Quantification for Discovery of Nonlinear Partial Differential Operators from Data
• The Penalty Imposed by Ablated Data Augmentation
• Revisiting Representation Learning for Singing Voice Separation with Sinkhorn Distances
• Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Efficient Learning of Generative Models via Finite-Difference Score Matching
• Interactive Recommender System via Knowledge Graph-enhanced Reinforcement Learning
• Multilingual Jointly Trained Acoustic and Written Word Embeddings
• Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection
• Graph Neural Networks Including Sparse Interpretability
• Overcoming Statistical Shortcuts for Open-ended Visual Counting
• Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks
• MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform
• The sociospatial factors of death: Analyzing effects of geospatially-distributed variables in a Bayesian mortality model for Hong Kong
• FrostNet: Towards Quantization-Aware Network Architecture Search
• Invertible Zero-Shot Recognition Flows
• Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks
• Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
• Plateau Phenomenon in Gradient Descent Training of ReLU networks: Explanation, Quantification and Avoidance
• MeDaS: An open-source platform as service to help break the walls between medicine and informatics
• Learning Global and Local Features of Normal Brain Anatomy for Unsupervised Abnormality Detection
• Adaptive Traffic Control with Deep Reinforcement Learning: Towards State-of-the-art and Beyond
• Deep UAV Localization with Reference View Rendering
• Graph Drawing via Gradient Descent, $(GD{)}^2$
• TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
• Feature Products Yield Efficient Networks
• Interactive Neural Style Transfer with Artists
• Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning
• Few-Shot Learning with Intra-Class Knowledge Transfer
• Variational Wasserstein Barycenters for Geometric Clustering
• Trajectory Based Podcast Recommendation
• Contradictory Structure Learning for Semi-supervised Domain Adaptation
• Review, Analysis and Design of a Comprehensive Deep Reinforcement Learning Framework
• Probably Approximately Correct Vision-Based Planning using Motion Primitives
• Secure Data Sharing With Flow Model
• Incomplete Utterance Rewriting as Semantic Segmentation
• SketchDesc: Learning Local Sketch Descriptors for Multi-view Correspondence
• TRADI: Tracking deep neural network weight distributions for uncertainty estimation
• Graph and Recurrent Neural Network-based Vehicle Trajectory Prediction For Highway Driving
• BackPACK: Packing more into backprop
• Level generation and style enhancement -- deep learning for game development overview
• DISCERN: Diversity-based Selection of Centroids for k-Estimation and Rapid Non-stochastic Clustering
• Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
• SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure
• Disrupting Model Training with Adversarial Shortcuts
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies
• AI assisted Malware Analysis: A Course for Next Generation Cybersecurity Workforce
• Long-Short Temporal Contrastive Learning of Video Transformers
• Draw your Neural Networks
• Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning
• Learning velocity model for complex media with deep convolutional neural networks
• Fair Normalizing Flows
• Comparing the costs of abstraction for DL frameworks
• Choice Set Optimization Under Discrete Choice Models of Group Decisions
• Subquadratic Overparameterization for Shallow Neural Networks
• SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal
• On the human-recognizability phenomenon of adversarially trained deep image classifiers
• Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation
• On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator
• Video Frame Interpolation Transformer
• Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent Representations
• What's wrong with this video? Comparing Explainers for Deepfake Detection
• Towards Graph Representation Learning in Emergent Communication
• Reinforcement Learning-based N-ary Cross-Sentence Relation Extraction
• Learning emergent PDEs in a learned emergent space
• Semi-Supervised Learning for In-Game Expert-Level Music-to-Dance Translation
• Improving Deep Learning Performance for Predicting Large-Scale Porous-Media Flow through Feature Coarsening
• A Database for Research on Detection and Enhancement of Speech Transmitted over HF links
• On the combination of graph data for assessing thin-file borrowers' creditworthiness
• EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification
• Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media
• Initialization and Regularization of Factorized Neural Layers
• R-BERT-CNN: Drug-target interactions extraction from biomedical literature
• Nonparametric Causal Feature Selection for Spatiotemporal Risk Mapping of Malaria Incidence in Madagascar
• SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation
• Self-supervised Visual-LiDAR Odometry with Flip Consistency
• Scaling Law for Recommendation Models: Towards General-purpose User Representations
• Accelerating Multi-Model Inference by Merging DNNs of Different Weights
• RATT: Leveraging Unlabeled Data to Guarantee Generalization
• MisConv: Convolutional Neural Networks for Missing Data
• Deeplite Neutrino: An End-to-End Framework for Constrained Deep Learning Model Optimization
• The Boombox: Visual Reconstruction from Acoustic Vibrations
• Post-Training Sparsity-Aware Quantization
• Neural Model-based Optimization with Right-Censored Observations
• RapidRead: Global Deployment of State-of-the-art Radiology AI for a Large Veterinary Teleradiology Practice
• Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels
• Anchor-Free Person Search
• Self-Claimed Assumptions in Deep Learning Frameworks: An Exploratory Study
• On the Importance of 3D Surface Information for Remote Sensing Classification Tasks
• Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles
• Content Selection Network for Document-grounded Retrieval-based Chatbots
• LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images
• Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
• A Semantic Segmentation Network for Urban-Scale Building Footprint Extraction Using RGB Satellite Imagery
• BridgeDPI: A Novel Graph Neural Network for Predicting Drug-Protein Interactions
• Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks
• Soft Expectation and Deep Maximization for Image Feature Detection
• Low Rank Forecasting
• Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation
• Touch-based Curiosity for Sparse-Reward Tasks
• Recommending Multiple Positive Citations for Manuscript via Content-Dependent Modeling and Multi-Positive Triplet
• Signed Distance Function Computation from an Implicit Surface
• cuConv: A CUDA Implementation of Convolution for CNN Inference
• ast2vec: Utilizing Recursive Neural Encodings of Python Programs
• Document Layout Analysis with Aesthetic-Guided Image Augmentation
• IWA: Integrated Gradient based White-box Attacks for Fooling Deep Neural Networks
• A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration
• Co-Imitation Learning without Expert Demonstration
• Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data
• Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
• Frame Difference-Based Temporal Loss for Video Stylization
• iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging
• Information-Theoretic Odometry Learning
• PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation
• Rethinking Generalization Performance of Surgical Phase Recognition with Expert-Generated Annotations
• Lower-Bounded Proper Losses for Weakly Supervised Classification
• Continual Inference: A Library for Efficient Online Inference with Deep Neural Networks in PyTorch
• Neural Network Potential Energy Surface for the low temperature Ring Polymer Molecular Dynamics of the H2CO + OH reaction
• Named Tensor Notation
• ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning
• SiMaN: Sign-to-Magnitude Network Binarization
• Multi-task Learning by Leveraging the Semantic Information
• Efficient and Interpretable Robot Manipulation with Graph Neural Networks
• A Neural Network Ensemble Approach to System Identification
• No GPU? No problem: an ultra fast 3D detection of road users with a simple proposal generator and energy-based out-of-distribution PointNets
• Combining CNNs With Transformer for Multimodal 3D MRI Brain Tumor Segmentation With Self-Supervised Pretraining
• DynaDog+T: A Parametric Animal Model for Synthetic Canine Image Generation
• Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers
• Exploring the Effects of Data Augmentation for Drivable Area Segmentation
• SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition
• Should Graph Neural Networks Use Features, Edges, Or Both?
• Deep learning of material transport in complex neurite networks
• Real-Time Panoptic Segmentation from Dense Detections
• TDC: Towards Extremely Efficient CNNs on GPUs via Hardware-Aware Tucker Decomposition
• Reconstruction of Pairwise Interactions using Energy-Based Models
• Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation
• Crossover-SGD: A gossip-based communication in distributed deep learning for alleviating large mini-batch problem and enhancing scalability
• Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval
• Model-Agnostic Learning to Meta-Learn
• Learning to Correspond Dynamical Systems
• Going Beyond Classification Accuracy Metrics in Model Compression
• iGOS++: Integrated Gradient Optimized Saliency by Bilateral Perturbations
• Embedding Power Flow into Machine Learning for Parameter and State Estimation
• Accelerating Machine Learning Queries with Linear Algebra Query Processing
• Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables
• Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
• Multi-source Few-shot Domain Adaptation
• Deep Learning Alternative to Explicit Model Predictive Control for Unknown Nonlinear Systems
• SMG: A Shuffling Gradient-Based Method with Momentum
• Long Document Ranking with Query-Directed Sparse Transformer
• Deep-learning-based decomposition of overlapping-sparse images: application at the vertex of neutrino interactions
• Data-driven discovery of dynamics from time-resolved coherent scattering
• Assessment of Reward Functions in Reinforcement Learning for Multi-Modal Urban Traffic Control under Real-World limitations
• Transformers in Unsupervised Structure-from-Motion
• Being-ahead: Benchmarking and Exploring Accelerators for Hardware-Efficient AI Deployment
• Graph Random Neural Features for Distance-Preserving Graph Representations
• Edge Prior Augmented Networks for Motion Deblurring on Naturally Blurry Images
• Post-Training BatchNorm Recalibration
• EXPATS: A Toolkit for Explainable Automated Text Scoring
• SMYRF: Efficient Attention using Asymmetric Clustering
• Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise
• RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition
• Analysis of the Two-Step Heterogeneous Transfer Learning for Laryngeal Blood Vessel Classification: Issue and Improvement
• Data-Driven Learning of Geometric Scattering Networks
• Contextual HyperNetworks for Novel Feature Adaptation
• Label merge-and-split: A graph-colouring approach for memory-efficient brain parcellation
• Challenging Instances are Worth Learning: Generating Valuable Negative Samples for Response Selection Training
• Efficiently Distributed Federated Learning
• Top-N Recommendation with Counterfactual User Preference Simulation
• Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?
• Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
• Harmonization with Flow-based Causal Inference
• Geometry encoding for numerical simulations
• TEASEL: A Transformer-Based Speech-Prefixed Language Model
• A Novel Technique for Query Plan Representation Based on Graph Neural Nets
• Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
• DeepEMO: Deep Learning for Speech Emotion Recognition
• Learning the Step-size Policy for the Limited-Memory Broyden-Fletcher-Goldfarb-Shanno Algorithm
• SME: A High Productivity FPGA Tool for Software Programmers
• Multi-task Learning Approach for Intracranial Hemorrhage Prognosis
• Characterizing the Value of Information in Medical Notes
• Boosting Asynchronous Decentralized Learning with Model Fragmentation
• In silico discovery of representational relationships across visual cortex
• Enhancing reinforcement learning for population setpoint tracking in co-cultures
• Soft Hoeffding Tree: A Transparent and Differentiable Model on Data Streams
• SpecTf: Transformers Enable Data-Driven Imaging Spectroscopy Cloud Detection
• Utilizing 3D Fast Spin Echo Anatomical Imaging to Reduce the Number of Contrast Preparations in $T_{1\rho }$ Quantification of Knee Cartilage Using Learning-Based Methods
• More Embeddings, Better Sequence Labelers?
• Beacon2Science: Enhancing STEREO/HI beacon data with machine learning for efficient CME tracking
• Practical Federated Learning without a Server
• Competing AI: How does competition feedback affect machine learning?
• Accelerating MoE Model Inference with Expert Sharding
• Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation
• Explainable Image Classification with Reduced Overconfidence for Tissue Characterisation
• SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking
• A neural network-based four-body potential energy surface for parahydrogen
• Step-Ahead Error Feedback for Distributed Training with Compressed Gradient
• Machine learning moment closure models for the radiative transfer equation III: enforcing hyperbolicity and physical characteristic speeds
• Parallel Programming Models for Heterogeneous Many-Cores : A Survey
• Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
• Improving the network traffic classification using the Packet Vision approach
• HindiLLM: Large Language Model for Hindi
• 2kenize: Tying Subword Sequences for Chinese Script Conversion
• PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
• Large Scale Font Independent Urdu Text Recognition System
• BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning
• k-Winners-Take-All Ensemble Neural Network
• Dynamic Sliding Window for Meeting Summarization
• Deep learning approaches for neural decoding: from CNNs to LSTMs and spikes to fMRI
• LIGAR: Lightweight General-purpose Action Recognition
• An Audio-enriched BERT-based Framework for Spoken Multiple-choice Question Answering
• Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms
• Neural Networks at a Fraction with Pruned Quaternions
• Curriculum learning for multilevel budgeted combinatorial problems
• Deep Reinforced Attention Learning for Quality-Aware Visual Recognition
• Uncertainty quantification in medical image segmentation with normalizing flows
• Optimal Transport using GANs for Lineage Tracing
• Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments
• NPLIC: A Machine Learning Approach to Piecewise Linear Interface Construction
• AdaSub: Stochastic Optimization Using Second-Order Information in Low-Dimensional Subspaces
• Path Imputation Strategies for Signature Models of Irregular Time Series
• Learning Hierarchical Graph Neural Networks for Image Clustering
• Learning Illumination Patterns for Coded Diffraction Phase Retrieval
• A Scalable and Cloud-Native Hyperparameter Tuning System
• Data Driven VRP: A Neural Network Model to Learn Hidden Preferences for VRP
• When and how epochwise double descent happens
• Adaptive Periodic Averaging: A Practical Approach to Reducing Communication in Distributed Learning
• Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles
• Federated Survival Analysis with Discrete-Time Cox Models
• Towards Tumour Graph Learning for Survival Prediction in Head & Neck Cancer Patients
• Apache Submarine: A Unified Machine Learning Platform Made Simple
• Real-Time Oil Leakage Detection on Aftermarket Motorcycle Damping System with Convolutional Neural Networks
• Hippo: Taming Hyper-parameter Optimization of Deep Learning with Stage Trees
• Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
• On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures
• GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
• Concept and the implementation of a tool to convert industry 4.0 environments modeled as FSM to an OpenAI Gym wrapper
• Explainable 3D Convolutional Neural Networks by Learning Temporal Transformations
• Target Consistency for Domain Adaptation: when Robustness meets Transferability
• Hypernetwork-Based Augmentation
• Deep Learning based Dimple Segmentation for Quantitative Fractography
• Parkinson's Disease Detection Using Ensemble Architecture from MR Images
• Go with the Flow: Adaptive Control for Neural ODEs
• CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising
• Dynamic Tensor Rematerialization
• NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning
• VTLayout: Fusion of Visual and Text Features for Document Layout Analysis
• LEReg: Empower Graph Neural Networks with Local Energy Regularization
• Composite Localization for Human Pose Estimation
• Provably Robust Metric Learning
• Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual Generator
• Attentive Neural Processes and Batch Bayesian Optimization for Scalable Calibration of Physics-Informed Digital Twins
• LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer
• Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
• Dual-side Sparse Tensor Core
• Hypergraph Pre-training with Graph Neural Networks
• Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs
• Analytic Manifold Learning: Unifying and Evaluating Representations for Continuous Control
• AP20-OLR Challenge: Three Tasks and Their Baselines
• Accelerating variational quantum algorithms with multiple quantum processors
• Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity
• Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
• Controllable Image Synthesis via SegVAE
• Self-similarity Student for Partial Label Histopathology Image Segmentation
• Representation Consolidation for Training Expert Students
• A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks
• A Deep Learning-based Detector for Brown Spot Disease in Passion Fruit Plant Leaves
• Longitudinal Deep Kernel Gaussian Process Regression
• Singer Identification Using Convolutional Acoustic Motif Embeddings
• Incorrect by Construction: Fine Tuning Neural Networks for Guaranteed Performance on Finite Sets of Examples
• LDDMM-Face: Large Deformation Diffeomorphic Metric Learning for Flexible and Consistent Face Alignment
• Learning Sampling in Financial Statement Audits using Vector Quantised Autoencoder Neural Networks
• Automatic Detection of Phonological Errors in Child Speech Using Siamese Recurrent Autoencoder
• Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings
• Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck
• Adversarial Data Augmentation for Disordered Speech Recognition
• A Survey on Large-scale Machine Learning
• Non-Blocking Simultaneous Multithreading: Embracing the Resiliency of Deep Neural Networks
• CLOPS: Continual Learning of Physiological Signals
• An Empirical Study of Pre-trained Transformers for Arabic Information Extraction
• Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks
• Targeted Attack for Deep Hashing based Retrieval
• GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
• Knowledge Base Completion for Constructing Problem-Oriented Medical Records
• Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders
• Variational Depth Search in ResNets
• Active 3D Shape Reconstruction from Vision and Touch
• A Hybrid-Order Distributed SGD Method for Non-Convex Optimization to Balance Communication Overhead, Computational Complexity, and Convergence Rate
• Learning to Abstract and Predict Human Actions
• Latent Space Refinement for Deep Generative Models
• Rectangular Flows for Manifold Learning
• Yet Another Intermediate-Level Attack
• Using Ensemble Classifiers to Detect Incipient Anomalies
• Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines
• Model-Free Episodic Control with State Aggregation
• Learning Slice-Aware Representations with Mixture of Attentions
• MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
• 3rd Place Solution to "Google Landmark Retrieval 2020"
• Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement
• Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusion
• Peri-Diagnostic Decision Support Through Cost-Efficient Feature Acquisition at Test-Time
• Asynchronous Distributed Optimization with Redundancy in Cost Functions
• Defending against substitute model black box adversarial attacks with the 01 loss
• 3D Room Layout Estimation Beyond the Manhattan World Assumption
• Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud
• Reinforcement Learning for Industrial Control Network Cyber Security Orchestration
• Structural Inductive Biases in Emergent Communication
• Neural Lyapunov Model Predictive Control: Learning Safe Global Controllers from Sub-optimal Examples
• Video Moment Retrieval with Text Query Considering Many-to-Many Correspondence Using Potentially Relevant Pair
• A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes
• Text-Independent Speaker Verification with Dual Attention Network
• E-DSSR: Efficient Dynamic Surgical Scene Reconstruction with Transformer-based Stereoscopic Depth Perception
• ResiliNet: Failure-Resilient Inference in Distributed Neural Networks
• Towards Non-Line-of-Sight Photography
• On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision
• Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks
• An analytical diabolo model for robotic learning and control
• SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation
• Derivatives of partial eigendecomposition of a real symmetric matrix for degenerate cases
• Visual Diver Face Recognition for Underwater Human-Robot Interaction
• Self-assembling kinetics: Accessing a new design space via differentiable statistical-physics models
• Progress in deep Markov State Modeling: Coarse graining and experimental data restraints
• Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning
• Generative Inverse Deep Reinforcement Learning for Online Recommendation
• Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time
• Learning Affinity-Aware Upsampling for Deep Image Matting
• Value Function Based Performance Optimization of Deep Learning Workloads
• Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
• CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
• On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications
• Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
• Deep-CR MTLR: a Multi-Modal Approach for Cancer Survival Prediction with Competing Risks
• ANCER: Anisotropic Certification via Sample-wise Volume Maximization
• MAD-VAE: Manifold Awareness Defense Variational Autoencoder
• EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
• Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
• Stochastic Adversarial Gradient Embedding for Active Domain Adaptation
• Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution
• End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization
• Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks
• Deriving Visual Semantics from Spatial Context: An Adaptation of LSA and Word2Vec to generate Object and Scene Embeddings from Images
• Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
• Utilizing dataset affinity prediction in object detection to assess training data
• Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation
• Learning from Similarity-Confidence Data
• Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring
• Cascading Feature Extraction for Fast Point Cloud Registration
• Insights into Ordinal Embedding Algorithms: A Systematic Evaluation
• Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects
• $S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation
• Muddling Labels for Regularization, a novel approach to generalization
• A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization
• Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach
• BERT4SO: Neural Sentence Ordering by Fine-tuning BERT
• R${}^3$Net:Relation-embedded Representation Reconstruction Network for Change Captioning
• OpenICS: Open Image Compressive Sensing Toolbox and Benchmark
• Why Settle for Just One? Extending EL++ Ontology Embeddings with Many-to-Many Relationships
• Osteoporosis Prescreening using Panoramic Radiographs through a Deep Convolutional Neural Network with Attention Mechanism
• Equivariant neural networks for inverse problems
• Monte Carlo simulation studies on Python using the sstudy package with SQL databases as storage
• PTQ-SL: Exploring the Sub-layerwise Post-training Quantization
• Neural Fixed-Point Acceleration for Convex Optimization
• DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting
• Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC
• PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnostics
• Neutral Face Game Character Auto-Creation via PokerFace-GAN
• Adversarially Robust Kernel Smoothing
• Dynamic Resolution Network
• Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate
• Adversarial Purification through Representation Disentanglement
• Texture Generation Using A Graph Generative Adversarial Network And Differentiable Rendering
• Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression Network
• Next-Best-View Estimation based on Deep Reinforcement Learning for Active Object Classification
• ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning
• Multi-layered tensor networks for image classification
• SoftNeuro: Fast Deep Inference using Multi-platform Optimization
• Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemetic Analysis
• Multi-Class Multiple Instance Learning for Predicting Precursors to Aviation Safety Events
• Compressing Sign Information in DCT-based Image Coding via Deep Sign Retrieval
• Solon: Communication-efficient Byzantine-resilient Distributed Training via Redundant Gradients
• Access Control with Encrypted Feature Maps for Object Detection Models
• On the Robustness of Average Losses for Partial-Label Learning
• Cross-document Coreference Resolution over Predicted Mentions
• Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning
• Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study
• Parallel and Flexible Dynamic Programming via the Randomized Mini-Batch Operator
• Learning Canonical Embedding for Non-rigid Shape Matching
• Code Word Detection in Fraud Investigations using a Deep-Learning Approach
• Orthonormal Product Quantization Network for Scalable Face Image Retrieval
• UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning
• Knowledge-Guided Object Discovery with Acquired Deep Impressions
• UNSAT Solver Synthesis via Monte Carlo Forest Search
• Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation
• TextAttack: Lessons learned in designing Python frameworks for NLP
• MLComp: A Methodology for Machine Learning-based Performance Estimation and Adaptive Selection of Pareto-Optimal Compiler Optimization Sequences
• VTAMIQ: Transformers for Attention Modulated Image Quality Assessment
• A Unified Structure for Efficient RGB and RGB-D Salient Object Detection
• Scheduling Optimization Techniques for Neural Network Training
• Dual-CyCon Net: A Cycle Consistent Dual-Domain Convolutional Neural Network Framework for Detection of Partial Discharge
• TyXe: Pyro-based Bayesian neural nets for Pytorch
• Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency
• Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
• Semi-tensor Product-based TensorDecomposition for Neural Network Compression
• Feed-Forward Optimization With Delayed Feedback for Neural Network Training
• Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment
• Conditional Generation of Temporally-ordered Event Sequences
• Trajectory saliency detection using consistency-oriented latent codes from a recurrent auto-encoder
• A Jointed Feature Fusion Framework for Photoacoustic Reconstruction
• Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
• Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation
• Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation
• Visualizing Color-wise Saliency of Black-Box Image Classification Models
• Semi-supervised Learning for Marked Temporal Point Processes
• Rapid Generation of Stochastic Signals with Specified Statistics
• Extended Koopman Models
• Contrastive Learning for Mitochondria Segmentation
• Deep Ensemble Collaborative Learning by using Knowledge-transfer Graph for Fine-grained Object Classification
• Lessons Learned Developing an Assembly System for WRS 2020 Assembly Challenge
• LyricJam: A system for generating lyrics for live instrumental music
• CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Age
• Equipping SBMs with RBMs: An Explainable Approach for Analysis of Networks with Covariates
• Robust Hedging GANs
• PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information
• Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training
• R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
• Unsupervised Domain Expansion for Visual Categorization
• Momentum Contrast Speaker Representation Learning
• A Spectral Nonlocal Block for Neural Networks
• Multiple Organ Failure Prediction with Classifier-Guided Generative Adversarial Imputation Networks
• Bias-Awareness for Zero-Shot Learning the Seen and Unseen
• Deep Reinforcement Learning with Weighted Q-Learning
• Efficient Spatialtemporal Context Modeling for Action Recognition
• Robust 3D U-Net Segmentation of Macular Holes
• S${}^3$VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation
• Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness
• DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
• Transfer Learning using Neural Ordinary Differential Equations
• Two-Level K-FAC Preconditioning for Deep Learning
• Solving an elastic inverse problem using Convolutional Neural Networks
• Neural Group Actions
• A two-stage approach for beam hardening artifact reduction in low-dose dental CBCT
• Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention
• Disentangled Representations for Domain-generalized Cardiac Segmentation
• Improved Few-shot Segmentation by Redefinition of the Roles of Multi-level CNN Features
• CondenseNet V2: Sparse Feature Reactivation for Deep Networks
• Particle gradient descent model for point process generation
• Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
• Meta Matrix Factorization for Federated Rating Predictions
• A Fully Tensorized Recurrent Neural Network
• Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shooting
• Paying Attention to Activation Maps in Camera Pose Regression
• A Blob Method for Mean Field Control With Terminal Constraints
• Program Enhanced Fact Verification with Verbalization and Graph Attention Network
• EMA: Auditing Data Removal from Trained Models
• Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures
• Scaling Distributed Deep Learning Workloads beyond the Memory Capacity with KARMA
• SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings
• Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation
• Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation
• Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
• ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser
• Numerical influence of ReLU'(0) on backpropagation
• Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms
• Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression
• FastSeq: Make Sequence Generation Faster
• ByzShield: An Efficient and Robust System for Distributed Training
• EDNet: Efficient Disparity Estimation with Cost Volume Combination and Attention-based Spatial Residual
• Let's See Clearly: Contaminant Artifact Removal for Moving Cameras
• Cost-effective Deployment of BERT Models in Serverless Environment
• ART: Actually Robust Training
• BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks
• LabelEnc: A New Intermediate Supervision Method for Object Detection
• Ground-truth effects in learning-based fiber orientation distribution estimation in neonatal brains
• Towards the Development of Entropy-Based Anomaly Detection in an Astrophysics Simulation
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution
• Length Scale Control in Topology Optimization using Fourier Enhanced Neural Networks
• Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors
• Score-Based Change Detection for Gradient-Based Learning Machines
• Correcting Momentum in Temporal Difference Learning
• Probing Light Scalars and Vector-like Quarks at the High-Luminosity LHC
• GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization
• MitoVis: A Visually-guided Interactive Intelligent System for Neuronal Mitochondria Analysis
• L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation
• Gated Texture CNN for Efficient and Configurable Image Denoising
• Differentiable Multiple Shooting Layers
• Two pathways to resolve relational inconsistencies
• Image-Based Parking Space Occupancy Classification: Dataset and Baseline
• Learning invariance preserving moment closure model for Boltzmann-BGK equation
• Simulating Unknown Target Models for Query-Efficient Black-box Attacks
• VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network
• ResIST: Layer-Wise Decomposition of ResNets for Distributed Training
• General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference
• Deep Learning-Based Prediction of High Explosive Induced Fluid Dynamics
• Improving axial resolution in SIM using deep learning
• Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS
• CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration
• Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
• Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle
• Segment Aggregation for short utterances speaker verification using raw waveforms
• Latent Behavior Diffusion for Sequential Reaction Generation in Dyadic Setting
• Path-integral Monte Carlo simulations of solid parahydrogen using two-body, three-body, and four-body ab initio interaction potential energy surfaces
• Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory
• Machine Intelligence for Outcome Predictions of Trauma Patients During Emergency Department Care
• AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
• Model Fusion via Neuron Transplantation
• Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition
• Phoneme-aware and Channel-wise Attentive Learning for Text DependentSpeaker Verification
• Efficient Person Search: An Anchor-Free Approach
• Generative Adversarial Networks for photo to Hayao Miyazaki style cartoons
• Memory Based Video Scene Parsing
• Simultaneous Quantum Machine Learning Training and Architecture Discovery
• GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification
• Multi-task Reinforcement Learning with a Planning Quasi-Metric
• Application of Graph Neural Networks in Dark Photon Search with Visible Decays at Future Beam Dump Experiment
• PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR
• PRAFlow_RVC: Pyramid Recurrent All-Pairs Field Transforms for Optical Flow Estimation in Robust Vision Challenge 2020
• Worrisome Properties of Neural Network Controllers and Their Symbolic Representations
• DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging
• Video Reconstruction by Spatio-Temporal Fusion of Blurred-Coded Image Pair
• Gradient-Based Dovetail Joint Shape Optimization for Stiffness
• Machine learning dynamics of phase separation in correlated electron magnets
• Fine-Grained Classroom Activity Detection from Audio with Neural Networks
• Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara
• Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks
• GIPA: A General Information Propagation Algorithm for Graph Learning
• IntraLoss: Further Margin via Gradient-Enhancing Term for Deep Face Recognition
• Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
• Convolutional neural networks compression with low rank and sparse tensor decompositions
• A Distributed Training Algorithm of Generative Adversarial Networks with Quantized Gradients
• Investigating Group Distributionally Robust Optimization for Deep Imbalanced Learning: A Case Study of Binary Tabular Data Classification
• Certifying Strategyproof Auction Networks
• Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video
• There is no Double-Descent in Random Forests
• Resolution Switchable Networks for Runtime Efficient Image Recognition
• Small Object Detection Based on Modified FSSD and Model Compression
• Multilingual Neural RST Discourse Parsing
• Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies
• Is this Dialogue Coherent? Learning from Dialogue Acts and Entities
• BFTrainer: Low-Cost Training of Neural Networks on Unfillable Supercomputer Nodes
• Data Augmentation Using Many-To-Many RNNs for Session-Aware Recommender Systems
• NeVer 2.0: Learning, Verification and Repair of Deep Neural Networks
• Road Network Metric Learning for Estimated Time of Arrival
• AdaL: Adaptive Gradient Transformation Contributes to Convergences and Generalizations
• Wasserstein Learning of Determinantal Point Processes
• Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction
• A simulator-based autoencoder for focal plane wavefront sensing
• Deep Orthogonal Decompositions for Convective Nowcasting
• Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification
• Learning ODEs via Diffeomorphisms for Fast and Robust Integration
• FDNAS: Improving Data Privacy and Model Diversity in AutoML
• An updated hybrid deep learning algorithm for identifying and locating primary vertices
• Programming with Neural Surrogates of Programs
• Flow field tomography with uncertainty quantification using a Bayesian physics-informed neural network
• EventHPE: Event-based 3D Human Pose and Shape Estimation
• Stealed-bid Auctions: Detecting Bid Leakage via Semi-Supervised Learning
• Mirror3D: Depth Refinement for Mirror Surfaces
• Modeling Coreference Relations in Visual Dialog
• Deep interpretability for GWAS
• Deep Contextual Embeddings for Address Classification in E-commerce
• Rotational and Reflectional Equivariant Convolutional Neural Network for data-limited applications: Multiphase Flow demonstration
• CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise
• Quantifying urban streetscapes with deep learning: focus on aesthetic evaluation
• Multi-view Orthonormalized Partial Least Squares: Regularizations and Deep Extensions
• "You eat with your eyes first": Optimizing Yelp Image Advertising
• Integrating Deep Learning in Domain Sciences at Exascale
• Lookahead Acquisition Functions for Finite-Horizon Time-Dependent Bayesian Optimization and Application to Quantum Optimal Control
• Single Plane-Wave Imaging using Physics-Based Deep Learning
• Adaptive Braking for Mitigating Gradient Delay
• GOALS: Gradient-Only Approximations for Line Searches Towards Robust and Consistent Training of Deep Neural Networks
• Expert Knowledge-Guided Length-Variant Hierarchical Label Generation for Proposal Classification
• Density Deconvolution with Normalizing Flows
• On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future
• Self-Supervised Multimodal Opinion Summarization
• Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
• Search Spaces for Neural Model Training
• Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
• Superpixel-Guided Label Softening for Medical Image Segmentation
• Reconstruct high-resolution multi-focal plane images from a single 2D wide field image
• Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation
• PrivFramework: A System for Configurable and Automated Privacy Policy Compliance
• Automatic Standardization of Colloquial Persian
• NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
• GINA: Neural Relational Inference From Independent Snapshots
• Toward Efficient Online Scheduling for Distributed Machine Learning Systems
• Bregman Gradient Policy Optimization
• My House, My Rules: Learning Tidying Preferences with Graph Neural Networks
• Omni-supervised Facial Expression Recognition via Distilled Data
• Resampling and super-resolution of hexagonally sampled images using deep learning
• Convergent Graph Solvers
• Odd-One-Out Representation Learning
• Priberam at MESINESP Multi-label Classification of Medical Texts Task
• ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure
• What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks
• Convolutional Spectral Kernel Learning
• The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization
• LGENet: Local and Global Encoder Network for Semantic Segmentation of Airborne Laser Scanning Point Clouds
• Self-supervised Learning with Fully Convolutional Networks
• Parkinson's Disease Detection with Ensemble Architectures based on ILSVRC Models
• Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks
• APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores
• Design space reparameterization enforces hard geometric constraints in inverse-designed nanophotonic devices
• Deep neural network for optimal retirement consumption in defined contribution pension system
• Universal Policies for Software-Defined MDPs
• Self-Supervised Sketch-to-Image Synthesis
• On the transferability of adversarial examples between convex and 01 loss models
• AutoHOOT: Automatic High-Order Optimization for Tensors
• Knowledge Transfer for Few-shot Segmentation of Novel White Matter Tracts
• Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
• Ellipse Loss for Scene-Compliant Motion Prediction
• Chameleon: A Semi-AutoML framework targeting quick and scalable development and deployment of production-ready ML systems for SMEs
• Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning
• NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning
• Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction
• Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
• Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
• Generalizing electrocardiogram delineation -- Training convolutional neural networks with synthetic data augmentation
• Model discovery in the sparse sampling regime
• Residual-Recursion Autoencoder for Shape Illustration Images
• Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies
• Batch Normalization with Enhanced Linear Transformation
• StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
• Free Energy Node Embedding via Generalized Skip-gram with Negative Sampling
• Gestalt: a Stacking Ensemble for SQuAD2.0
• Comparing methods addressing multi-collinearity when developing prediction models
• On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
• i3DMM: Deep Implicit 3D Morphable Model of Human Heads
• TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation
• Dense Prediction with Attentive Feature Aggregation
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• Dense Regression Activation Maps For Lesion Segmentation in CT scans of COVID-19 patients
• HIVE-Net: Centerline-Aware HIerarchical View-Ensemble Convolutional Network for Mitochondria Segmentation in EM Images
• DeepDoseNet: A Deep Learning model for 3D Dose Prediction in Radiation Therapy
• Deep Multi-view Depth Estimation with Predicted Uncertainty
• DeepACEv2: Automated Chromosome Enumeration in Metaphase Cell Images Using Deep Convolutional Neural Networks
• Deconditional Downscaling with Gaussian Processes
• Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions
• Verifying Quantized Neural Networks using SMT-Based Model Checking
• NuSPAN: A Proximal Average Network for Nonuniform Sparse Model -- Application to Seismic Reflectivity Inversion
• DistIR: An Intermediate Representation and Simulator for Efficient Neural Network Distribution
• Structured Convolutional Kernel Networks for Airline Crew Scheduling
• Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation
• PairConnect: A Compute-Efficient MLP Alternative to Attention
• Multi-Task Learning of Query Intent and Named Entities using Transfer Learning
• Training Image Selection using Recurrent Neural Networks: An Application in Hydrogeology
• Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2
• Fast Adaptation with Linearized Neural Networks
• Proceedings of the 2020 Scheme and Functional Programming Workshop
• Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction
• Multi-Class Classification from Single-Class Data with Confidences
• An Improvement of Object Detection Performance using Multi-step Machine Learnings
• Deep View Synthesis via Self-Consistent Generative Network
• CariMe: Unpaired Caricature Generation with Multiple Exaggerations
• Learning Scene Dynamics from Point Cloud Sequences
• The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video
• Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
• Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?
• An Expectation-Maximization Perspective on Federated Learning
• Privacy Aware Person Detection in Surveillance Data
• Gradient-Induced Co-Saliency Detection
• A Surrogate Objective Framework for Prediction+Optimization with Soft Constraints
• Multi-lingual agents through multi-headed neural networks
• Spectrally Consistent UNet for High Fidelity Image Transformations
• Efficient Latent Representations using Multiple Tasks for Autonomous Driving
• Structured Directional Pruning via Perturbation Orthogonal Projection
• VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction
• Semi-Online Knowledge Distillation
• Text-guided Legal Knowledge Graph Reasoning
• Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE
• Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning
• Rescuing Deep Hashing from Dead Bits Problem
• Orthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks
• A manifold learning perspective on representation learning: Learning decoder and representations without an encoder
• Self-Supervised Regional and Temporal Auxiliary Tasks for Facial Action Unit Recognition
• IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks
• Dynamic Efficient Adversarial Training Guided by Gradient Magnitude
• Functional Space Analysis of Local GAN Convergence
• Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks
• Efficient Neural Radiance Fields for Interactive Free-viewpoint Video
• D3p -- A Python Package for Differentially-Private Probabilistic Programming
• Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation
• Memory-efficient array redistribution through portable collective communication
• Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
• Graph Energy-based Model for Substructure Preserving Molecular Design
• Robustness and Reliability When Training With Noisy Labels
• Continual Speaker Adaptation for Text-to-Speech Synthesis
• Landmark detection in Cardiac Magnetic Resonance Imaging Using A Convolutional Neural Network
• Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case
• Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment
• Spatially Dependent U-Nets: Highly Accurate Architectures for Medical Imaging Segmentation
• Accent Recognition with Hybrid Phonetic Features
• Escaping the abstraction: a foreign function interface for the Unified Form Language [UFL]
• Inverse Problems Leveraging Pre-trained Contrastive Representations
• Importance sampling-based gradient method for dimension reduction in Poisson log-normal model
• Understanding (Non-)Robust Feature Disentanglement and the Relationship Between Low- and High-Dimensional Adversarial Attacks
• Multimodal Medical Volume Colorization from 2D Style
• An Efficient QP Variable Convolutional Neural Network Based In-loop Filter for Intra Coding
• Audio Caption in a Car Setting with a Sentence-Level Loss
• MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
• Improving Graph Property Prediction with Generalized Readout Functions
• Deep Adaptive Inference Networks for Single Image Super-Resolution
• Learning Discriminative Shrinkage Deep Networks for Image Deconvolution
• Enhancing Generalization in Convolutional Neural Networks through Regularization with Edge and Line Features
• From Quantized DNNs to Quantizable DNNs
• Transfer learning in large-scale ocean bottom seismic wavefield reconstruction
• The Benefits of Pairwise Discriminators for Adversarial Training
• Bayesian Sparsification Methods for Deep Complex-valued Networks
• Spatially Attentive Output Layer for Image Classification
• DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation
• Physical world assistive signals for deep neural network classifiers -- neither defense nor attack
• SoQal: Selective Oracle Questioning in Active Learning
• Explore BiLSTM-CRF-Based Models for Open Relation Extraction
• Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
• Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions
• Residual Enhanced Multi-Hypergraph Neural Network
• Optimising Hearing Aid Fittings for Speech in Noise with a Differentiable Hearing Loss Model
• Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
• Consistent Accelerated Inference via Confident Adaptive Transformers
• Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos
• 3D-OOCS: Learning Prostate Segmentation with Inductive Bias
• NeuralMagicEye: Learning to See and Understand the Scene Behind an Autostereogram
• Generalized Operating Procedure for Deep Learning: an Unconstrained Optimal Design Perspective
• Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features
• Solving time-dependent parametric PDEs by multiclass classification-based reduced order model
• The Blessing and the Curse of the Noise behind Facial Landmark Annotations
• Neural Additive and Basis Models with Feature Selection and Interactions
• Hoplite: Efficient and Fault-Tolerant Collective Communication for Task-Based Distributed Systems
• Structure Observation Driven Image-Text Contrastive Learning for Computed Tomography Report Generation
• "Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks
• Adaptive Transfer Learning: a simple but effective transfer learning
• Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention
• MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited Labels
• SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos
• FunMC: A functional API for building Markov Chains
• CDER: Collaborative Evidence Retrieval for Document-level Relation Extraction
• A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing
• Delta Sampling R-BERT for limited data and low-light action recognition
• Towards Unsupervised Sketch-based Image Retrieval
• Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations
• Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing
• Multiple Code Hashing for Efficient Image Retrieval
• Greedy Bayesian Posterior Approximation with Deep Ensembles
• Ripple Attention for Visual Perception with Sub-quadratic Complexity
• On-target Adaptation
• AQP: An Open Modular Python Platform for Objective Speech and Audio Quality Metrics
• Learning Structured Representations of Entity Names using Active Learning and Weak Supervision
• More than just an auxiliary loss: Anti-spoofing Backbone Training via Adversarial Pseudo-depth Generation
• Dif4FF: Leveraging Multimodal Diffusion Models and Graph Neural Networks for Accurate New Fashion Product Performance Forecasting
• HittER: Hierarchical Transformers for Knowledge Graph Embeddings
• EEG-Based Mental Imagery Task Adaptation via Ensemble of Weight-Decomposed Low-Rank Adapters
• Online trajectory recovery from offline handwritten Japanese kanji characters
• Equivariant Manifold Flows
• Quantum Machine Learning with SQUID
• Prediction of Individual Halo Concentrations Across Cosmic Time Using Neural Networks
• Log-Polar Space Convolution for Convolutional Neural Networks
• MCSAE: Masked Cross Self-Attentive Encoding for Speaker Embedding
• Tokamak disruption prediction using different machine learning techniques
• Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation
• What classifiers know what they don't?
• Train and Deploy an Image Classifier for Disaster Response
• Using a one dimensional parabolic model of the full-batch loss to estimate learning rates during training
• Deep ${\mathcal{L}}^1$ Stochastic Optimal Control Policies for Planetary Soft-landing
• Fit to Measure: Reasoning about Sizes for Robust Object Recognition
• CNN with large memory layers
• TensorX: Extensible API for Neural Network Model Design and Deployment
• A Genetic Feature Selection Based Two-stream Neural Network for Anger Veracity Recognition
• Enhancing Fiber Orientation Distributions using convolutional Neural Networks
• Meta-Learning Conjugate Priors for Few-Shot Bayesian Optimization
• DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions
• Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text
• Cross-Modal Knowledge Transfer via Inter-Modal Translation and Alignment for Affect Recognition
• ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groups
• Group Equivariant Subsampling
• Background-Click Supervision for Temporal Action Localization
• Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound
• On the Expected Complexity of Maxout Networks
• Adaptive Hierarchical Similarity Metric Learning with Noisy Labels
• Neural Differential Equations for Inverse Modeling in Model Combustors
• Non-Parametric Neural Style Transfer
• Self-Denoising Neural Networks for Few Shot Learning
• Semi-Automating Knowledge Base Construction for Cancer Genetics
• Fine-Grained Chemical Entity Typing with Multimodal Knowledge Representation
• Domain Knowledge Integration By Gradient Matching For Sample-Efficient Reinforcement Learning
• Learning to Combine Per-Example Solutions for Neural Program Synthesis
• gym-saturation: Gymnasium environments for saturation provers (System description)
• ARCH: Efficient Adversarial Regularized Training with Caching
• diagNNose: A Library for Neural Activation Analysis
• A stepped sampling method for video detection using LSTM
• Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge
• Data-driven modeling of time-domain induced polarization
• Learning to Give Checkable Answers with Prover-Verifier Games
• Maximum Likelihood Estimation of Differentiated Products Demand Systems
• IGLU: Efficient GCN Training via Lazy Updates
• Gradient-based Hyperparameter Optimization Over Long Horizons
• Investigation of Nonlinear Model Order Reduction of the Quasigeostrophic Equations through a Physics-Informed Convolutional Autoencoder
• Type-driven Neural Programming by Example
• XConv: Low-memory stochastic backpropagation for convolutional layers
• Deep Learning Framework From Scratch Using Numpy
• SPARQLing Database Queries from Intermediate Question Decompositions
• Improving Visual Recognition using Ambient Sound for Supervision
• Compositional federated learning: Applications in distributionally robust averaging and meta learning
• DAReN: A Collaborative Approach Towards Reasoning And Disentangling
• Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations
• Minimizing Oracle-Structured Composite Functions
• Master Thesis: Neural Sign Language Translation by Learning Tokenization
• Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extraction
• Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation
• Meta-Learning with Adjoint Methods
• Host-Pathongen Co-evolution Inspired Algorithm Enables Robust GAN Training
• A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
• End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs
• PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition
• Diff2Dist: Learning Spectrally Distinct Edge Functions, with Applications to Cell Morphology Analysis
• Modularized Transfomer-based Ranking Framework
• PointManifoldCut: Point-wise Augmentation in the Manifold for Point Clouds
• Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization
• Obstacle Detection for BVLOS Drones
• OXnet: Omni-supervised Thoracic Disease Detection from Chest X-rays
• Optimizing generalization on the train set: a novel gradient-based framework to train parameters and hyperparameters simultaneously
• Unsupervised Part Discovery via Feature Alignment
• Bridged Adversarial Training
• Accelerated Computation of a High Dimensional Kolmogorov-Smirnov Distance
• A moment-matching metric for latent variable generative models
• From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting
• DoLFIn: Distributions over Latent Features for Interpretability
• HMM-Free Encoder Pre-Training for Streaming RNN Transducer
• Accounting for data heterogeneity in integrative analysis and prediction methods: An application to Chronic Obstructive Pulmonary Disease
• Deep Learning Tools for Audacity: Helping Researchers Expand the Artist's Toolkit
• Isometric Graph Neural Networks
• Physics-Based Causal Lifting Linearization of Nonlinear Control Systems Underpinned by the Koopman Operator
• Improving Differentially Private SGD via Randomly Sparsified Gradients
• Rethinking PointNet Embedding for Faster and Compact Model
• Spring-Rod System Identification via Differentiable Physics Engine
• Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings
• Generative Optimization Networks for Memory Efficient Data Generation
• Graph Convolutional Memory using Topological Priors
• Facilitate the Parametric Dimension Reduction by Gradient Clipping
• Balanced Depth Completion between Dense Depth Inference and Sparse Range Measurements via KISS-GP
• Self-Regulation for Semantic Segmentation
• Dispatcher: A Message-Passing Approach To Language Modelling
• 3rd Place Scheme on Instance Segmentation Track of ICCV 2021 VIPriors Challenges
• Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
• LSP : Acceleration and Regularization of Graph Neural Networks via Locality Sensitive Pruning of Graphs
• Oriental Language Recognition (OLR) 2020: Summary and Analysis
• Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness
• SIM-ECG: A Signal Importance Mask-driven ECGClassification System
• MARS: Masked Automatic Ranks Selection in Tensor Decompositions
• Efficient Semi-Implicit Variational Inference
• Painting Style-Aware Manga Colorization Based on Generative Adversarial Networks
• Orthogonal Deep Models As Defense Against Black-Box Attacks
• Structured Outdoor Architecture Reconstruction by Exploration and Classification
• Dual Projection Generative Adversarial Networks for Conditional Image Generation
• Accumulated Decoupled Learning: Mitigating Gradient Staleness in Inter-Layer Model Parallelization
• Putting 3D Spatially Sparse Networks on a Diet
• Deep Learning-based Stress Determinator for Mouse Psychiatric Analysis using Hippocampus Activity
• Reservoir Stack Machines
• Empirical Evaluation of Deep Learning Model Compression Techniques on the WaveNet Vocoder
• Discovering Latent Representations of Relations for Interacting Systems
• Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models
• Syntax Customized Video Captioning by Imitating Exemplar Sentences
• Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version)
• Comparing One-step and Two-step Scatter Correction and Density Reconstruction in X-ray CT
• Quantile Filtered Imitation Learning
• How BPE Affects Memorization in Transformers
• A Mechanism for Producing Aligned Latent Spaces with Autoencoders
• Offline Contextual Bandits for Wireless Network Optimization
• An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks
• Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks
• Nonlinear Tensor Ring Network
• Target Propagation via Regularized Inversion
• Offline Contextual Bandits with Overparameterized Models
• Dual Correction Strategy for Ranking Distillation in Top-N Recommender System
• Density Fixing: Simple yet Effective Regularization Method based on the Class Prior
• PrototypeML: A Neural Network Integrated Design and Development Environment
• deepstruct -- linking deep learning and graph theory
• Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data
• Simultaneous Denoising and Localization Network for Photoacoustic Target Localization
• Cooperative Bi-path Metric for Few-shot Learning
• STDI-Net: Spatial-Temporal Network with Dynamic Interval Mapping for Bike Sharing Demand Prediction
• Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance
• A method of supervised learning from conflicting data with hidden contexts
• A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation
• Signed Bipartite Graph Neural Networks
• PICCOLO: Point Cloud-Centric Omnidirectional Localization
• Attribute-aware Explainable Complementary Clothing Recommendation
• EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder
• Spatially-Varying Outdoor Lighting Estimation from Intrinsics
• Effective GPU Sharing Under Compiler Guidance
• Solving Graph-based Public Good Games with Tree Search and Imitation Learning
• Self-Calibration Supported Robust Projective Structure-from-Motion
• DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings
• Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
• Logit Attenuating Weight Normalization
• Learning Mechanically Driven Emergent Behavior with Message Passing Neural Networks
• Enhancing WiFi Multiple Access Performance with Federated Deep Reinforcement Learning
• Image denoising by Super Neurons: Why go deep?
• Exploring Task Difficulty for Few-Shot Relation Extraction
• Neural networks with trainable matrix activation functions
• Learning Models of Model Predictive Controllers using Gradient Data
• Hotel Recognition via Latent Image Embedding
• Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs
• Coordinate-wise Control Variates for Deep Policy Gradients
• Message Passing Descent for Efficient Machine Learning
• Accelerating convolutional neural network by exploiting sparsity on GPUs
• An empirical study of neural networks for trend detection in time series
• Adversarial Context Aware Network Embeddings for Textual Networks
• Twin Augmented Architectures for Robust Classification of COVID-19 Chest X-Ray Images
• Self-Attentive 3D Human Pose and Shape Estimation from Videos
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction
• Reciprocal Supervised Learning Improves Neural Machine Translation
• Diversity-Aware Batch Active Learning for Dependency Parsing
• Voxel-level Siamese Representation Learning for Abdominal Multi-Organ Segmentation
• Introducing the Hidden Neural Markov Chain framework
• U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction
• Self Training with Ensemble of Teacher Models
• A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction
• Generative Particle Variational Inference via Estimation of Functional Gradients
• Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP
• Locality-Sensitive Experience Replay for Online Recommendation
• Bayesian Meta-Learning Through Variational Gaussian Processes
• Optical Wavelength Guided Self-Supervised Feature Learning For Galaxy Cluster Richness Estimate
• Differentiable Computational Geometry for 2D and 3D machine learning
• Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation
• User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis
• Class Incremental Online Streaming Learning
• ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks
• Learning Novel Objects Continually Through Curiosity
• SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama
• EffCNet: An Efficient CondenseNet for Image Classification on NXP BlueBox
• SynFace: Face Recognition with Synthetic Data
• Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path
• Abelian Neural Networks
• Dynamically Modelling Heterogeneous Higher-Order Interactions for Malicious Behavior Detection in Event Logs
• COVID-view: Diagnosis of COVID-19 using Chest CT
• Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks
• Session-aware Item-combination Recommendation with Transformer Network
• Tensors Fitting Perfectly
• MG-WFBP: Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning
• Who calls the shots? Rethinking Few-Shot Learning for Audio
• On the Generative Utility of Cyclic Conditionals
• Go Small and Similar: A Simple Output Decay Brings Better Performance
• Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories
• How to use Machine Learning to improve the discrimination between signal and background at particle colliders
• Aggregate Learning for Mixed Frequency Data
• Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization
• Risk factor identification for incident heart failure using neural network distillation and variable selection
• Non-autoregressive electron flow generation for reaction prediction
• End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning
• Graph Convolution Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy Videos
• Cogradient Descent for Dependable Learning
• A Probabilistic Approach to Neural Network Pruning
• Simulating time to event prediction with spatiotemporal echocardiography deep learning
• Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning
• Predicting Human Trajectories by Learning and Matching Patterns
• Compressed Object Detection
• AE-StyleGAN: Improved Training of Style-Based Auto-Encoders
• Improve SGD Training via Aligning Mini-batches
• Deep Learning-based Resource Allocation for Infrastructure Resilience
• SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries
• Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation
• Cross-Lingual Fine-Grained Entity Typing
• Sentence Semantic Regression for Text Generation
• Distributed Reconstruction Algorithm for Electron Tomography with Multiple-scattering Samples
• Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise
• GaussED: A Probabilistic Programming Language for Sequential Experimental Design
• On the Evaluation of Prohibited Item Classification and Detection in Volumetric 3D Computed Tomography Baggage Security Screening Imagery
• Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability
• Appearance Editing with Free-viewpoint Neural Rendering
• Diffusion Normalizing Flow
• Leveraging Review Properties for Effective Recommendation
• Deep Controllable Backlight Dimming
• Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation
• Inductive Predictions of Extreme Hydrologic Events in The Wabash River Watershed
• Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation
• The Weighting Game: Evaluating Quality of Explainability Methods
• Generative Tomography Reconstruction
• Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization
• Generation of tubular and membranous shape textures with curvature functionals
• Audiovisual transfer learning for audio tagging and sound event detection
• Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition
• Interpretable Attention Guided Network for Fine-grained Visual Classification
• Scalable Online Recurrent Learning Using Columnar Neural Networks
• Inner Ensemble Networks: Average Ensemble as an Effective Regularizer
• DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications
• Neural Algorithmic Reasoners are Implicit Planners
• Temporal Clustering with External Memory Network for Disease Progression Modeling
• Transformation Driven Visual Reasoning
• SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation
• Vampire With a Brain Is a Good ITP Hammer
• DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing
• Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
• Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning
• Improving Multi-Party Dialogue Discourse Parsing via Domain Integration
• A Quadratic Actor Network for Model-Free Reinforcement Learning
• Discovery of Physics and Characterization of Microstructure from Data with Bayesian Hidden Physics Models
• Towards adversarial robustness with 01 loss neural networks
• Width Transfer: On the (In)variance of Width Optimization
• Knowledge Generation -- Variational Bayes on Knowledge Graphs
• Photon-Driven Neural Path Guiding
• JUWELS Booster -- A Supercomputer for Large-Scale AI Research
• Targeted Deep Learning: Framework, Methods, and Applications
• Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling
• No-Press Diplomacy from Scratch
• Adaptive Cost-Sensitive Learning in Neural Networks for Misclassification Cost Problems
• Phoneme-Based Ratio Mask Estimation for Reverberant Speech Enhancement in Cochlear Implant Processors
• Efficient Modelling Across Time of Human Actions and Interactions
• Traveling Wave Solutions of Partial Differential Equations via Neural Networks
• SPIRAL2 Cryomodules Models: a Gateway to Process Control and Machine Learning
• MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes
• Let Your Heart Speak in its Mother Tongue: Multilingual Captioning of Cardiac Signals
• A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines
• High resolution functional imaging through Lorentz transmission electron microscopy and differentiable programming
• Locating Faulty Methods with a Mixed RNN and Attention Model
• Secure Distributed Training at Scale
• Noise Modulation: Let Your Model Interpret Itself
• Incremental Class Learning using Variational Autoencoders with Similarity Learning
• Open-Set Representation Learning through Combinatorial Embedding
• Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction
• Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning
• Learning Model Predictive Controllers for Real-Time Ride-Hailing Vehicle Relocation and Pricing Decisions
• Global2Local: Efficient Structure Search for Video Action Segmentation
• The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks
• An Analysis of Super-Net Heuristics in Weight-Sharing NAS
• Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics
• RocNet: Recursive Octree Network for Efficient 3D Deep Representation
• An Odor Labeling Convolutional Encoder-Decoder for Odor Sensing in Machine Olfaction
• An Adaptive Remote Stochastic Gradient Method for Training Neural Networks
• AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision
• Towards Unified Surgical Skill Assessment
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• Unsupervised Deep Learning by Injecting Low-Rank and Sparse Priors
• Nonprehensile Riemannian Motion Predictive Control
• Transferable Semantic Augmentation for Domain Adaptation
• Cross-Correlation Based Discriminant Criterion for Channel Selection in Motor Imagery BCI Systems
• ShapeY: Measuring Shape Recognition Capacity Using Nearest Neighbor Matching
• On new data sources for the production of official statistics
• Spatio-Temporal Sparsification for General Robust Graph Convolution Networks
• Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning
• Conditional Deep Convolutional Neural Networks for Improving the Automated Screening of Histopathological Images
• Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training
• 3D Scattering Tomography by Deep Learning with Architecture Tailored to Cloud Fields
• Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection
• Importance Estimation from Multiple Perspectives for Keyphrase Extraction
• Pulling back information geometry
• Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters
• Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
• Towards Automatic Speech to Sign Language Generation
• On Deep Neural Network Calibration by Regularization and its Impact on Refinement
• Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP)
• Input Invex Neural Network
• HRFA: High-Resolution Feature-based Attack
• On the Variance of the Fisher Information for Deep Learning
• Hierarchical Character Tagger for Short Text Spelling Error Correction
• $f$-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
• A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters
• Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance
• Neural Motion Planning for Autonomous Parking
• Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
• Controllable Neural Dialogue Summarization with Personal Named Entity Planning
• Does Thermal data make the detection systems more reliable?
• Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification
• Learning landmark geodesics using Kalman ensembles
• Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound
• JUMBO: Scalable Multi-task Bayesian Optimization using Offline Data
• KL Guided Domain Adaptation
• Under the Skin of Foundation NFT Auctions
• Coarse-Grained Nonlinear System Identification
• Robustness and Overfitting Behavior of Implicit Background Models
• Interactive Radiotherapy Target Delineation with 3D-Fused Context Propagation
• Mining Domain Knowledge: Improved Framework towards Automatically Standardizing Anatomical Structure Nomenclature in Radiotherapy
• CAR -- Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehicles
• Online Descriptor Enhancement via Self-Labelling Triplets for Visual Data Association
• Deep Learning-Based Detection of the Acute Respiratory Distress Syndrome: What Are the Models Learning?
• Parallelized Computation and Backpropagation Under Angle-Parametrized Orthogonal Matrices
• Robust Vision Challenge 2020 -- 1st Place Report for Panoptic Segmentation
• Dynamic Domain Adaptation for Efficient Inference
• OpenGraphGym-MG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems
• Progressive Compressed Records: Taking a Byte out of Deep Learning Data
• Efficient and Transferable Adversarial Examples from Bayesian Neural Networks
• Neural Search: Learning Query and Product Representations in Fashion E-commerce
• MergeComp: A Compression Scheduler for Scalable Communication-Efficient Distributed Training
• Priberam Labs at the NTCIR-15 SHINRA2020-ML: Classification Task
• Uncertainty Estimation in Deep Neural Networks for Point Cloud Segmentation in Factory Planning
• A Systematic Investigation of KB-Text Embedding Alignment at Scale
• Zero Cost Improvements for General Object Detection Network
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Scalable Probabilistic Routes
• SyReNets: Symbolic Residual Neural Networks
• Deep Compression for PyTorch Model Deployment on Microcontrollers
• Generalized Organ Segmentation by Imitating One-shot Reasoning using Anatomical Correlation
• Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool
• Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bit-wise Regularization
• SD-6DoF-ICLK: Sparse and Deep Inverse Compositional Lucas-Kanade Algorithm on SE(3)
• MIIDL: a Python package for microbial biomarkers identification powered by interpretable deep learning
• Convolutional Hough Matching Networks
• Evidential Turing Processes
• Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
• Training Automatic View Planner for Cardiac MR Imaging via Self-Supervision by Spatial Relationship between Views
• Self Normalizing Flows
• Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
• Towards Imbalanced Motion: Part-Decoupling Network for Video Portrait Segmentation
• Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
• Fast and Real-time End to End Control in Autonomous Racing Cars Through Representation Learning
• Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data
• Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models
• Scene Text Recognition with Temporal Convolutional Encoder
• Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing
• Automatically detecting anomalous exoplanet transits
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• Using context to adapt to sensor drift
• Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes
• 3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
• Unsupervised Cross-Lingual Speech Emotion Recognition Using Pseudo Multilabel
• Flexible numerical optimization with ensmallen
• Empirical Analysis of Korean Public AI Hub Parallel Corpora and in-depth Analysis using LIWC
• Examining the rhetorical capacities of neural language models
• Monte Carlo Simulation of SDEs using GANs
• Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection
• Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers
• DEM Super-Resolution with EfficientNetV2
• Implicit recurrent networks: A novel approach to stationary input processing with recurrent neural networks in deep learning
• AGNES: Abstraction-guided Framework for Deep Neural Networks Security
• Improving Text-Independent Speaker Verification with Auxiliary Speakers Using Graph
• Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling
• Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep Learning
• TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling
• Learning to solve TV regularized problems with unrolled algorithms
• Discovering Invariances in Healthcare Neural Networks
• Novelty Detection via Contrastive Learning with Negative Data Augmentation
• An initial investigation on optimizing tandem speaker verification and countermeasure systems using reinforcement learning
• Gabor filter incorporated CNN for compression
• MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms
• Tongji University Team for the VoxCeleb Speaker Recognition Challenge 2020
• Efficient estimates of optimal transport via low-dimensional embeddings
• Beyond Categorical Label Representations for Image Classification
• Tensor Normal Training for Deep Learning Models
• Autoregressive Reasoning over Chains of Facts with Transformers
• A Comparative Evaluation of Additive Separability Tests for Physics-Informed Machine Learning
• A Novel Deep ML Architecture by Integrating Visual Simultaneous Localization and Mapping (vSLAM) into Mask R-CNN for Real-time Surgical Video Analysis
• Molecular Attributes Transfer from Non-Parallel Data
• Atlas Based Representation and Metric Learning on Manifolds
• Lightweight Dual-channel Target Speaker Separation for Mobile Voice Communication
• Learning to Explore by Reinforcement over High-Level Options
• [RE] CNN-generated images are surprisingly easy to spot...for now
• reproducing "ner and pos when nothing is capitalized"
• Periodic Spectral Ergodicity: A Complexity Measure for Deep Neural Networks and Neural Architecture Search
• AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
• IC-Network: Efficient Structure for Convolutional Neural Networks
• Convolutions for Spatial Interaction Modeling
• Interpretable Local Tree Surrogate Policies
• MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection
• A Deep Learning Algorithm for Piecewise Linear Interface Construction (PLIC)
• Task-adaptive Pre-training of Language Models with Word Embedding Regularization
• An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks
• KML: Using Machine Learning to Improve Storage Systems
• Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling
• Think about boundary: Fusing multi-level boundary information for landmark heatmap regression
• Accumulative Poisoning Attacks on Real-time Data
• Dynamic Traffic Modeling From Overhead Imagery
• VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling
• Contact and Human Dynamics from Monocular Video
• Less is more: Faster and better music version identification with embedding distillation
• HetSeq: Distributed GPU Training on Heterogeneous Infrastructure
• Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
• Inverse Problem of Nonlinear Schrödinger Equation as Learning of Convolutional Neural Network
• Reinforced Attention for Few-Shot Learning and Beyond
• Experiments with graph convolutional networks for solving the vertex $p$-center problem
• WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach
• Adaptive Latent Space Tuning for Non-Stationary Distributions
• Nonseparable Symplectic Neural Networks
• A Multi-Scale Conditional Deep Model for Tumor Cell Ratio Counting
• Voting of predictive models for clinical outcomes: consensus of algorithms for the early prediction of sepsis from clinical data and an analysis of the PhysioNet/Computing in Cardiology Challenge 2019
• A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations
• Stable Anderson Acceleration for Deep Learning
• Adaptive Optimization with Examplewise Gradients
• Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction
• Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora
• Written Justifications are Key to Aggregate Crowdsourced Forecasts
• A scalable framework for learning from implicit user feedback to improve natural language understanding in large-scale conversational AI systems
• High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm
• Meta Auxiliary Learning for Facial Action Unit Detection
• Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks
• Tesla-Rapture: A Lightweight Gesture Recognition System from mmWave Radar Point Clouds
• Gradient Kernel Regression
• Detection of Consonant Errors in Disordered Speech Based on Consonant-vowel Segment Embedding
• Carrying out CNN Channel Pruning in a White Box
• PCPs: Patient Cardiac Prototypes
• Full-Body Visual Self-Modeling of Robot Morphologies
• Motion Prediction Performance Analysis for Autonomous Driving Systems and the Effects of Tracking Noise
• Freudian and Newtonian Recurrent Cell for Sequential Recommendation
• How semantic and geometric information mutually reinforce each other in ToF object localization
• Planning the path with Reinforcement Learning: Optimal Robot Motion Planning in RoboCup Small Size League Environments
• A Temporal Variational Model for Story Generation
• ADNet: Temporal Anomaly Detection in Surveillance Videos
• Learning Model-Based Vehicle-Relocation Decisions for Real-Time Ride-Sharing: Hybridizing Learning and Optimization
• One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification
• Physics Driven Domain Specific Transporter Framework with Attention Mechanism for Ultrasound Imaging
• Lossless Compression with Probabilistic Circuits
• Speech-dependent Data Augmentation for Own Voice Reconstruction with Hearable Microphones in Noisy Environments
• A finite element / neural network framework for modeling suspensions of non-spherical particles. Concepts and medical applications
• Towards Low-Resource StarGAN Voice Conversion using Weight Adaptive Instance Normalization
• Multitasking Inhibits Semantic Drift
• Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation
• Taking A Closer Look at Synthesis: Fine-grained Attribute Analysis for Person Re-Identification
• Exploiting Temporal Attention Features for Effective Denoising in Videos
• Teaching a Machine to Diagnose a Heart Disease; Beginning from digitizing scanned ECGs to detecting the Brugada Syndrome (BrS)
• Does Putting a Linguist in the Loop Improve NLU Data Collection?
• Automated Decision-based Adversarial Attacks
• Unsupervised Domain Adaptation: A Reality Check
• Structured Stochastic Gradient MCMC
• Langevin Cooling for Domain Translation
• iLGaCo: Incremental Learning of Gait Covariate Factors
• Towards Unbiased Visual Emotion Recognition via Causal Intervention
• Matrix Engines for High Performance Computing:A Paragon of Performance or Grasping at Straws?
• Conifer Seedling Detection in UAV-Imagery with RGB-Depth Information
• StylePart: Image-based Shape Part Manipulation
• Apply Artificial Neural Network to Solving Manpower Scheduling Problem
• Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation
• Neural Scene Flow Prior
• Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
• ds-array: A Distributed Data Structure for Large Scale Machine Learning
• Development of digitally obtainable 10-year risk scores for depression and anxiety in the general population
• Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs
• Optimizing Graph Transformer Networks with Graph-based Techniques
• Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
• VeriMedi: Pill Identification using Proxy-based Deep Metric Learning and Exact Solution
• Frustratingly Simple Pretraining Alternatives to Masked Language Modeling
• A reproducibility study of "Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space"
• Relative Flatness and Generalization
• MapReader: A Computer Vision Pipeline for the Semantic Exploration of Maps at Scale
• Hashing Modulo Alpha-Equivalence
• LAIF: AI, Deep Learning for Germany Suetterlin Letter Recognition and Generation
• FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond
• Dual Attention Model for Citation Recommendation
• Training Graph Neural Networks by Graphon Estimation
• Duluth at SemEval-2020 Task 7: Using Surprise as a Key to Unlock Humorous Headlines
• Contrastive String Representation Learning using Synthetic Data