Auto-Encoding Variational Bayes

Abstract

How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.

Fixes a typo in the abstract, no other changes

References in corpus (2)

• Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition
• Variational Bayesian Inference with Stochastic Search

Cited by in corpus (3564)

• A Survey on Deep Learning in Medical Image Analysis
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Generative Adversarial Networks: An Overview
• A Brief Survey of Deep Reinforcement Learning
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• An Introduction to Variational Autoencoders
• On the Opportunities and Risks of Foundation Models
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Diffusion Models in Vision: A Survey
• Neural Architecture Search: A Survey
• Deep Facial Expression Recognition: A Survey
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Unsupervised Learning of Video Representations using LSTMs
• Pixel Recurrent Neural Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Semi-Supervised Learning with Deep Generative Models
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• Tutorial on Variational Autoencoders
• NICE: Non-linear Independent Components Estimation
• Generative AI
• Variational Inference with Normalizing Flows
• Weight Uncertainty in Neural Networks
• Normalizing Flows: An Introduction and Review of Current Methods
• Deep Learning for Single Image Super-Resolution: A Brief Review
• Generative Modeling by Estimating Gradients of the Data Distribution
• Toward Multimodal Image-to-Image Translation
• DRAW: A Recurrent Neural Network For Image Generation
• BEiT: BERT Pre-Training of Image Transformers
• Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics -- A Comprehensive Review
• Variational Graph Auto-Encoders
• Applications of Deep Learning and Reinforcement Learning to Biological Data
• Contrastive Representation Learning: A Framework and Review
• TransMorph: Transformer for unsupervised medical image registration
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Deep neural network models for computational histopathology: A survey
• Deep Convolutional Inverse Graphics Network
• Deep Image Prior
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Neural Volumes: Learning Dynamic Renderable Volumes from Images
• A Recurrent Latent Variable Model for Sequential Data
• Disentangling by Factorising
• Autoencoding beyond pixels using a learned similarity metric
• Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
• KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
• A Survey on Dialogue Systems: Recent Advances and New Frontiers
• Pyro: Deep Universal Probabilistic Programming
• Neural Ordinary Differential Equations
• Semi-Supervised Learning with Generative Adversarial Networks
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Deep Reinforcement Learning: An Overview
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
• Graph Self-Supervised Learning: A Survey
• Unsupervised Image-to-Image Translation Networks
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• Discovering physical concepts with neural networks
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• Cascaded Diffusion Models for High Fidelity Image Generation
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• Deep Learning for Deepfakes Creation and Detection: A Survey
• Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
• Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
• Variational Dropout and the Local Reparameterization Trick
• The State of Sparsity in Deep Neural Networks
• Scalable Bayesian Optimization Using Deep Neural Networks
• Energy-based Out-of-distribution Detection
• A Review of Generalized Zero-Shot Learning Methods
• Model-Based Reinforcement Learning for Atari
• Artificial neural networks for neuroscientists: A primer
• Perceptual Adversarial Networks for Image-to-Image Transformation
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
• Deep Learning Based Text Classification: A Comprehensive Review
• CogView: Mastering Text-to-Image Generation via Transformers
• Large Scale Adversarial Representation Learning
• Generative Moment Matching Networks
• Learning Graph Embedding with Adversarial Training Methods
• Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
• NVAE: A Deep Hierarchical Variational Autoencoder
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
• Machine Learning in Aerodynamic Shape Optimization
• Recent Advances in Autoencoder-Based Representation Learning
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Robustness May Be at Odds with Accuracy
• Deep and Confident Prediction for Time Series at Uber
• Predictive Uncertainty Estimation via Prior Networks
• Deep Variational Information Bottleneck
• Normalizing Flows for Probabilistic Modeling and Inference
• A Survey of Sound Source Localization with Deep Learning Methods
• Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision
• A Comprehensive Survey on Deep Graph Representation Learning
• Bayesian Compression for Deep Learning
• MADE: Masked Autoencoder for Distribution Estimation
• Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors
• Constrained Graph Variational Autoencoders for Molecule Design
• Recent Advances in Convolutional Neural Networks
• Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity
• GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
• A Gentle Introduction to Deep Learning for Graphs
• Compute Trends Across Three Eras of Machine Learning
• A Review on Deep Learning Techniques for Video Prediction
• Adversarial Autoencoders
• Visual Reinforcement Learning with Imagined Goals
• State Representation Learning for Control: An Overview
• A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
• Deep Appearance Models for Face Rendering
• GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
• MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• A Survey of End-to-End Driving: Architectures and Training Methods
• Towards Biologically Plausible Deep Learning
• Variational Diffusion Models
• Causal Effect Inference with Deep Latent-Variable Models
• Combining EfficientNet and Vision Transformers for Video Deepfake Detection
• Mobile Sensor Data Anonymization
• Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
• On Mutual Information Maximization for Representation Learning
• Unsupervised Visual Representation Learning by Context Prediction
• Off-Policy Deep Reinforcement Learning without Exploration
• Graph networks as learnable physics engines for inference and control
• Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network
• Searching for New Physics with Deep Autoencoders
• Guided Image Generation with Conditional Invertible Neural Networks
• Character Controllers Using Motion VAEs
• Unsupervised Generative Modeling Using Matrix Product States
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Lossy Image Compression with Compressive Autoencoders
• Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Identification of Deep Network Generated Images Using Disparities in Color Components
• Neural Image Compression for Gigapixel Histopathology Image Analysis
• Learning by Playing - Solving Sparse Reward Tasks from Scratch
• A Survey of Knowledge-Enhanced Text Generation
• Disentangling factors of variation in deep representations using adversarial training
• Learning a Probabilistic Model for Diffeomorphic Registration
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Neural Relational Inference for Interacting Systems
• Neural Photo Editing with Introspective Adversarial Networks
• Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization
• An Overview of Deep Semi-Supervised Learning
• TensorFlow Distributions
• Learning feed-forward one-shot learners
• Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• A Survey of Privacy Attacks in Machine Learning
• Video Compression With Rate-Distortion Autoencoders
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
• Composing graphical models with neural networks for structured representations and fast inference
• Discovering Discrete Latent Topics with Neural Variational Inference
• CURL: Contrastive Unsupervised Representations for Reinforcement Learning
• Memory-based control with recurrent neural networks
• Conditional molecular design with deep generative models
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• Learning What and Where to Draw
• Soft Actor-Critic for Discrete Action Settings
• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
• Stochastic Adversarial Video Prediction
• Adversarial Text-to-Image Synthesis: A Review
• Masked Autoregressive Flow for Density Estimation
• A Deep Reinforcement Learning Chatbot
• Disentangled Representation Learning in Cardiac Image Analysis
• Harnessing Deep Neural Networks with Logic Rules
• Automatic Differentiation Variational Inference
• MONet: Unsupervised Scene Decomposition and Representation
• An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
• Wasserstein Auto-Encoders
• SPICE: Semantic Pseudo-labeling for Image Clustering
• Neural Variational Inference and Learning in Belief Networks
• Keeping it Simple: Language Models can learn Complex Molecular Distributions
• Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks
• Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
• Tensor Methods in Computer Vision and Deep Learning
• DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
• Molecular graph generation with Graph Neural Networks
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother
• Glow: Generative Flow with Invertible 1x1 Convolutions
• Unmasking DeepFakes with simple Features
• Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks
• Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery
• A Simple Baseline for Bayesian Uncertainty in Deep Learning
• MR image reconstruction using deep density priors
• Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks
• SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery
• Dynamical Variational Autoencoders: A Comprehensive Review
• GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
• Causal Contextual Prediction for Learned Image Compression
• Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
• DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
• Dynamic Word Embeddings
• Gravitational-wave parameter estimation with autoregressive neural network flows
• Quantum generative adversarial network for generating discrete distribution
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• Differentiable Quantum Architecture Search
• Deep Learning on Graphs: A Survey
• Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neurons
• A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
• Pre-training Molecular Graph Representation with 3D Geometry
• Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures
• Least Squares Generative Adversarial Networks
• Latent ODEs for Irregularly-Sampled Time Series
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Nonlinear Information Bottleneck
• SpaText: Spatio-Textual Representation for Controllable Image Generation
• A Review on Neural Network Models of Schizophrenia and Autism Spectrum Disorder
• Twin Contrastive Learning for Online Clustering
• Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities
• A Probabilistic U-Net for Segmentation of Ambiguous Images
• Learning Sparse Neural Networks through $L_0$ Regularization
• WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs
• High-throughput discovery of novel cubic crystal materials using deep generative neural networks
• Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
• Swapping Autoencoder for Deep Image Manipulation
• VideoGPT: Video Generation using VQ-VAE and Transformers
• Dense 3D Object Reconstruction from a Single Depth View
• Re-thinking Co-Salient Object Detection
• Deep Learning for Procedural Content Generation
• Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
• Towards a Neural Statistician
• Variational inference for Monte Carlo objectives
• PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting
• On Adaptive Attacks to Adversarial Example Defenses
• Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation
• Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
• adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection
• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
• Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review
• Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
• Deep Learning for Computational Cytology: A Survey
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
• Deep Learning in Mobile and Wireless Networking: A Survey
• A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams
• Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
• Emotion Intensity and its Control for Emotional Voice Conversion
• Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
• Learning Representation for Clustering via Prototype Scattering and Positive Sampling
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
• Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
• Learning on Attribute-Missing Graphs
• Tree Tensor Networks for Generative Modeling
• Do GANs actually learn the distribution? An empirical study
• StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
• Deep Generative Dual Memory Network for Continual Learning
• Learning Disentangled Semantic Representation for Domain Adaptation
• Adversarial Feature Matching for Text Generation
• Explaining by Removing: A Unified Framework for Model Explanation
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs
• Compressing Neural Networks using the Variational Information Bottleneck
• Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
• DiffWave: A Versatile Diffusion Model for Audio Synthesis
• Early Visual Concept Learning with Unsupervised Deep Learning
• Random Feature Attention
• Graph Convolutional Networks for Graphs Containing Missing Features
• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
• Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition
• Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder
• Generative Visual Manipulation on the Natural Image Manifold
• MLIC: Multi-Reference Entropy Model for Learned Image Compression
• Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
• Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities
• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Sampling using $SU(N)$ gauge equivariant flows
• Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters
• Adapting Mask-RCNN for Automatic Nucleus Segmentation
• OmiEmbed: a unified multi-task deep learning framework for multi-omics data
• Are Disentangled Representations Helpful for Abstract Visual Reasoning?
• Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
• LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving
• A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
• Grammar Variational Autoencoder
• Deep Knockoffs
• Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Generating and designing DNA with deep generative models
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• RPC: A Large-Scale Retail Product Checkout Dataset
• Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
• Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
• Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification
• Lifelong Generative Modeling
• Learning to Decompose and Disentangle Representations for Video Prediction
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Jukebox: A Generative Model for Music
• Review: Deep Learning in Electron Microscopy
• STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
• Diffusion Models, Image Super-Resolution And Everything: A Survey
• Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
• Stochastic Gradient Descent as Approximate Bayesian Inference
• Crystal Diffusion Variational Autoencoder for Periodic Material Generation
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• The Consciousness Prior
• From Variational to Deterministic Autoencoders
• Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder
• Coupled Generative Adversarial Networks
• Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
• IoT Malware Network Traffic Classification using Visual Representation and Deep Learning
• Machine learning non-Markovian quantum dynamics
• Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
• Roundtrip: A Deep Generative Neural Density Estimator
• Learning Disentangled Representations in the Imaging Domain
• Conditional Variational Image Deraining
• A Deep Generative Model for Molecule Optimization via One Fragment Modification
• Diffusion Model-Based Image Editing: A Survey
• Machine learning with neural networks
• The Conditional Entropy Bottleneck
• Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction
• CausalRCA: Causal Inference based Precise Fine-grained Root Cause Localization for Microservice Applications
• Temporal Knowledge Graph Completion: A Survey
• From optimal transport to generative modeling: the VEGAN cookbook
• Implicit Generation and Generalization in Energy-Based Models
• Generative Image Modeling Using Spatial LSTMs
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Probabilistic Logic Neural Networks for Reasoning
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space
• Deep Active Inference
• Deep learning of thermodynamics-aware reduced-order models from data
• Unsupervised Learning of 3D Structure from Images
• Symbol Emergence in Cognitive Developmental Systems: a Survey
• Recurrent Inference Machines for Solving Inverse Problems
• Modeling Tabular data using Conditional GAN
• A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
• Population-Based Black-Box Optimization for Biological Sequence Design
• Information Constraints on Auto-Encoding Variational Bayes
• Attribute2Image: Conditional Image Generation from Visual Attributes
• Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
• Neural Predictor based Quantum Architecture Search
• Reversing the Irreversible: A Survey on Inverse Biometrics
• Vector-quantized Image Modeling with Improved VQGAN
• Loss is its own Reward: Self-Supervision for Reinforcement Learning
• Adversarial Attacks Against Deep Generative Models on Data: A Survey
• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
• Learning to design from humans: Imitating human designers through deep learning
• Diagnosing and Enhancing VAE Models
• Image Synthesis with a Single (Robust) Classifier
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
• Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
• DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal
• DIVA: Domain Invariant Variational Autoencoders
• Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification
• PathVQA: 30000+ Questions for Medical Visual Question Answering
• Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
• Deep Learning for Genomics: A Concise Overview
• On the Quantum versus Classical Learnability of Discrete Distributions
• MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
• Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
• Low-Resource Knowledge-Grounded Dialogue Generation
• In Search of Lost Domain Generalization
• Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset
• Random Feature Expansions for Deep Gaussian Processes
• Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
• SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
• An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Learning Robust Representations via Multi-View Information Bottleneck
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Generalisation error in learning with random features and the hidden manifold model
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• Emotional Speech-Driven Animation with Content-Emotion Disentanglement
• How to Train Your Energy-Based Models
• Bayesian Bits: Unifying Quantization and Pruning
• HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
• Monte Carlo Gradient Estimation in Machine Learning
• Unsupervised machine learning of topological phase transitions from experimental data
• Strategic Attentive Writer for Learning Macro-Actions
• Machine Learning for Spatiotemporal Sequence Forecasting: A Survey
• ChatPainter: Improving Text to Image Generation using Dialogue
• Copyright in Generative Deep Learning
• Inference Suboptimality in Variational Autoencoders
• Overlearning Reveals Sensitive Attributes
• Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
• Deep Survival Analysis
• Learning Conditional Deformable Templates with Convolutional Networks
• Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
• T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography
• Supervised Compression for Resource-Constrained Edge Computing Systems
• Bayesian Layers: A Module for Neural Network Uncertainty
• Machine learning-assisted design of material properties
• Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
• FSNet: An Identity-Aware Generative Model for Image-based Face Swapping
• Concrete Autoencoders for Differentiable Feature Selection and Reconstruction
• Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification
• An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection
• Exploring order parameters and dynamic processes in disordered systems via variational autoencoders
• A Graph to Graphs Framework for Retrosynthesis Prediction
• Optimizing Molecules using Efficient Queries from Property Evaluations
• PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
• Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network
• Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problems
• One-Shot Generalization in Deep Generative Models
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• Semi-supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data
• Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
• LDMVFI: Video Frame Interpolation with Latent Diffusion Models
• Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization
• Associative Learning Mechanism for Drug-Target Interaction Prediction
• Structured Pruning of a BERT-based Question Answering Model
• Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• Generating Images from Captions with Attention
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
• Stochastic Variational Video Prediction
• Factorizable Graph Convolutional Networks
• A Survey on Deep Learning for Skeleton-Based Human Animation
• A causal view of compositional zero-shot recognition
• Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
• Variational Inference using Implicit Distributions
• Semantic Facial Expression Editing using Autoencoded Flow
• Measuring and modeling the motor system with machine learning
• Adversarial Network Embedding
• Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and Privacy
• Variational Deep Image Restoration
• Adversarial Robustness as a Prior for Learned Representations
• Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
• CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
• SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions
• Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder
• A Deep Generative Model for Graph Layout
• Unrestricted Adversarial Examples via Semantic Manipulation
• Sliced Score Matching: A Scalable Approach to Density and Score Estimation
• Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
• Open Domain Event Extraction Using Neural Latent Variable Models
• Unsupervised Deep Learning for IoT Time Series
• PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
• Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• Hypernetwork functional image representation
• Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space
• Contracting Arbitrary Tensor Networks: General Approximate Algorithm and Applications in Graphical Models and Quantum Circuit Simulations
• DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech
• Fast differentiable DNA and protein sequence optimization for molecular design
• A review of radar-based nowcasting of precipitation and applicable machine learning techniques
• A Framework for Interdomain and Multioutput Gaussian Processes
• NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
• DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data
• VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
• Stabilizing Generative Adversarial Networks: A Survey
• Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
• Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
• Implicit Weight Uncertainty in Neural Networks
• Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
• Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
• Content and Style Aware Generation of Text-line Images for Handwriting Recognition
• Machine Learning for Anomaly Detection in Particle Physics
• Variational Autoencoder with Arbitrary Conditioning
• Intriguing Properties of Contrastive Losses
• Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors
• A Probabilistic Formulation of Unsupervised Text Style Transfer
• Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data
• On denoising autoencoders trained to minimise binary cross-entropy
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
• Lifelong Teacher-Student Network Learning
• Deep Diffusion Models for Seismic Processing
• Variational Temporal Deep Generative Model for Radar HRRP Target Recognition
• A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• Maximum Entropy Generators for Energy-Based Models
• Deep Temporal Sigmoid Belief Networks for Sequence Modeling
• ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
• Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
• NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
• Adversarial Images for Variational Autoencoders
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• Classification Aware Neural Topic Model and its Application on a New COVID-19 Disinformation Corpus
• Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
• PoNA: Pose-guided Non-local Attention for Human Pose Transfer
• von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
• PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
• FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs
• Improving Outfit Recommendation with Co-supervision of Fashion Generation
• Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction
• Controllable Invariance through Adversarial Feature Learning
• Pathwise Derivatives Beyond the Reparameterization Trick
• FIGR: Few-shot Image Generation with Reptile
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Deep Factors for Forecasting
• Generalized Variational Inference: Three arguments for deriving new Posteriors
• A joint model of unpaired data from scRNA-seq and spatial transcriptomics for imputing missing gene expression measurements
• Conditional Flow Variational Autoencoders for Structured Sequence Prediction
• Improving Generalization in Meta Reinforcement Learning using Learned Objectives
• Learning Implicit Fields for Generative Shape Modeling
• Multi-modal Deep Analysis for Multimedia
• Dual Adversarial Auto-Encoders for Clustering
• Towards Zero-shot Sign Language Recognition
• Variational Bayes with Synthetic Likelihood
• Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priors
• Cardiac MRI Segmentation with Strong Anatomical Guarantees
• Reinforcement Learning through Active Inference
• StructureNet: Hierarchical Graph Networks for 3D Shape Generation
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm
• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control
• End-to-End Pixel-Based Deep Active Inference for Body Perception and Action
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• 6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning
• LMQFormer: A Laplace-Prior-Guided Mask Query Transformer for Lightweight Snow Removal
• Operator Variational Inference
• Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
• Learning to Perform Physics Experiments via Deep Reinforcement Learning
• Small Sample Learning in Big Data Era
• Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
• Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
• A Joint Model for IT Operation Series Prediction and Anomaly Detection
• Artificial Intelligence in Glioma Imaging: Challenges and Advances
• Modeling Uncertainty with Hedged Instance Embedding
• Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
• Learning Likelihoods with Conditional Normalizing Flows
• Symbolic Pregression: Discovering Physical Laws from Distorted Video
• Do Deep Generative Models Know What They Don't Know?
• Bayesian leave-one-out cross-validation approximations for Gaussian latent variable models
• Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
• Adversarial-Residual-Coarse-Graining: Applying machine learning theory to systematic molecular coarse-graining
• Restricting the Flow: Information Bottlenecks for Attribution
• Lund jet images from generative and cycle-consistent adversarial networks
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• Simulations meet Machine Learning in Structural Biology
• Few-Shot Adaptation of Generative Adversarial Networks
• Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine
• A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Affinity and Diversity: Quantifying Mechanisms of Data Augmentation
• Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
• A topological encoding method for data-driven photonics inverse design
• ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
• CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network
• Exposure: A White-Box Photo Post-Processing Framework
• Generating Multi-Agent Trajectories using Programmatic Weak Supervision
• We Should at Least Be Able to Design Molecules That Dock Well
• Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
• Adaptive deep density approximation for Fokker-Planck equations
• Deferred Neural Rendering: Image Synthesis using Neural Textures
• Disentangling Disentanglement in Variational Autoencoders
• Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation
• Constrained Bayesian Optimization for Automatic Chemical Design
• A Novel Framework for Brain Tumor Detection Based on Convolutional Variational Generative Models
• Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
• Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation
• Variational inference with a quantum computer
• Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
• Unsupervised Heterogeneous Coupling Learning for Categorical Representation
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning
• PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
• Multi-Label Clinical Time-Series Generation via Conditional GAN
• Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
• The continuous Bernoulli: fixing a pervasive error in variational autoencoders
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• Inference Networks for Sequential Monte Carlo in Graphical Models
• Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
• Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
• Disentangling Factors of Variation Using Few Labels
• The Gaussian equivalence of generative models for learning with shallow neural networks
• Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
• ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder
• FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
• Importance nested sampling with normalising flows
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Presenting Unbinned Differential Cross Section Results
• Distribution Matching in Variational Inference
• ATISS: Autoregressive Transformers for Indoor Scene Synthesis
• Boosting Variational Inference
• StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
• Learning Beyond Human Expertise with Generative Models for Dental Restorations
• Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model
• IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
• Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• medigan: a Python library of pretrained generative models for medical image synthesis
• Generative Models of Visually Grounded Imagination
• Variational Sequential Monte Carlo
• Maximum Likelihood Training of Score-Based Diffusion Models
• DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup
• Fast Bayesian whole-brain fMRI analysis with spatial 3D priors
• An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
• Normalizing Flows on Riemannian Manifolds
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• 6GCVAE: Gated Convolutional Variational Autoencoder for IPv6 Target Generation
• Semi-Supervised Variational Reasoning for Medical Dialogue Generation
• Missing Data Imputation using Optimal Transport
• Practical Lossless Compression with Latent Variables using Bits Back Coding
• Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions
• DeepSketchHair: Deep Sketch-based 3D Hair Modeling
• A review of unsupervised learning in astronomy
• Gmail Smart Compose: Real-Time Assisted Writing
• Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
• Universally Quantized Neural Compression
• Generative 3D Part Assembly via Dynamic Graph Learning
• Causal Discovery in Physical Systems from Videos
• Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection
• Causality-based CTR Prediction using Graph Neural Networks
• Lung Segmentation from Chest X-rays using Variational Data Imputation
• Robust Compressed Sensing MRI with Deep Generative Priors
• Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework
• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• Adversarial Examples - A Complete Characterisation of the Phenomenon
• A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systems
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Speech enhancement with variational autoencoders and alpha-stable distributions
• Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network
• SSD: A Unified Framework for Self-Supervised Outlier Detection
• Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
• Disentangling the independently controllable factors of variation by interacting with the world
• Supervised and Semi-supervised Deep Probabilistic Models for Indoor Positioning Problems
• Label-Consistent Backdoor Attacks
• Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation
• InfoBot: Transfer and Exploration via the Information Bottleneck
• Hierarchical Generative Modeling for Controllable Speech Synthesis
• Probabilistic Binary Neural Networks
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• Learning protein conformational space by enforcing physics with convolutions and latent interpolations
• A Deep Learning Algorithm for High-Dimensional Exploratory Item Factor Analysis
• Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
• A Deep Generative Model for Fragment-Based Molecule Generation
• Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts
• VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation
• Generative Capacity of Probabilistic Protein Sequence Models
• Towards Precise and Accurate Calculations of Neutrinoless Double-Beta Decay: Project Scoping Workshop Report
• Diagnosing Concept Drift with Visual Analytics
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
• Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Progressive Pose Attention Transfer for Person Image Generation
• Tackling Over-pruning in Variational Autoencoders
• Invertible generative models for inverse problems: mitigating representation error and dataset bias
• On the Expressiveness of Approximate Inference in Bayesian Neural Networks
• Neural Adaptive Sequential Monte Carlo
• Data Generation as Sequential Decision Making
• Solving Mixed Integer Programs Using Neural Networks
• Generative Neural Machine Translation
• Recommending Accurate and Diverse Items Using Bilateral Branch Network
• A Universal Music Translation Network
• Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations
• SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
• Discrete Variational Autoencoders
• High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks
• Generative Models for Low-Rank Video Representation and Reconstruction
• Robust Training of Vector Quantized Bottleneck Models
• Generating Multivariate Load States Using a Conditional Variational Autoencoder
• From IC Layout to Die Photo: A CNN-Based Data-Driven Approach
• Creativity and Machine Learning: A Survey
• GANimation: Anatomically-aware Facial Animation from a Single Image
• On the Detection of Digital Face Manipulation
• Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures
• Accounting for Variance in Machine Learning Benchmarks
• Computer-Aided Design as Language
• MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization
• Model-Augmented Actor-Critic: Backpropagating through Paths
• Generative Temporal Models with Memory
• Deep Gaussian Processes for Multi-fidelity Modeling
• Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem
• A Variational Perspective on Diffusion-Based Generative Models and Score Matching
• Predictive Collective Variable Discovery with Deep Bayesian Models
• A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the Small Data regime
• Language as a Latent Variable: Discrete Generative Models for Sentence Compression
• Variational Information Bottleneck for Effective Low-Resource Fine-Tuning
• NODLINK: An Online System for Fine-Grained APT Attack Detection and Investigation
• Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAM
• Fixing a Broken ELBO
• Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
• AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
• Simple, Distributed, and Accelerated Probabilistic Programming
• Topology of Learning in Artificial Neural Networks
• A Benchmark of Medical Out of Distribution Detection
• Physics-aware Reduced-order Modeling of Transonic Flow via $\beta$-Variational Autoencoder
• Disentangled Representations for Short-Term and Long-Term Person Re-Identification
• Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
• Copula Flows for Synthetic Data Generation
• AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction
• Adversarially Regularized Autoencoders
• Deep Amortized Inference for Probabilistic Programs
• On Disentangled Representations Learned From Correlated Data
• End-to-end Learning of Driving Models from Large-scale Video Datasets
• A deep-learning search for technosignatures of 820 nearby stars
• Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties
• Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
• On the Importance of Gradients for Detecting Distributional Shifts in the Wild
• From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting
• Training Gaussian Boson Sampling Distributions
• LAFITE: Towards Language-Free Training for Text-to-Image Generation
• Conditional Gaussian Distribution Learning for Open Set Recognition
• Unsupervised Model Selection for Variational Disentangled Representation Learning
• Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring
• Stochastic Optimization of Sorting Networks via Continuous Relaxations
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
• Unifying Multimodal Transformer for Bi-directional Image and Text Generation
• Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets
• Adversarial Symmetric Variational Autoencoder
• Statistical Inference for Generative Models with Maximum Mean Discrepancy
• Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
• DDTCDR: Deep Dual Transfer Cross Domain Recommendation
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
• RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation
• Contrastive Learning with Stronger Augmentations
• Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
• Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging
• Simple and Effective VAE Training with Calibrated Decoders
• Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning
• Graphite: Iterative Generative Modeling of Graphs
• UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
• RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
• Quaternion Generative Adversarial Networks
• Stochastic Backpropagation through Mixture Density Distributions
• t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning
• Can multi-label classification networks know what they don't know?
• Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System
• Conditional Generative Moment-Matching Networks
• Boundless: Generative Adversarial Networks for Image Extension
• VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detection
• Predicting Deeper into the Future of Semantic Segmentation
• Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
• Generating Images Part by Part with Composite Generative Adversarial Networks
• Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
• Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras
• Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
• Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks
• Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges
• Cross-Modal Contrastive Learning for Text-to-Image Generation
• Canonical Correlation Analysis (CCA) Based Multi-View Learning: An Overview
• Deep Conversational Recommender in Travel
• Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
• Variational Neural Machine Translation
• Semi-Amortized Variational Autoencoders
• Deep Unfolding with Normalizing Flow Priors for Inverse Problems
• Adversarial Distributional Training for Robust Deep Learning
• CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
• Efficient inference in occlusion-aware generative models of images
• Generating Sentences by Editing Prototypes
• Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
• Semi-blind source separation with multichannel variational autoencoder
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Multi-fidelity physics constrained neural networks for dynamical systems
• Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
• From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
• Multi-view Generative Adversarial Networks
• A new interpretable unsupervised anomaly detection method based on residual explanation
• Challenges in Disentangling Independent Factors of Variation
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
• A Tutorial on Deep Latent Variable Models of Natural Language
• Entity Abstraction in Visual Model-Based Reinforcement Learning
• Revealing quantum chaos with machine learning
• Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
• Uncertainty-Aware Attention for Reliable Interpretation and Prediction
• Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
• LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
• Deep Music Analogy Via Latent Representation Disentanglement
• Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
• Safer Classification by Synthesis
• A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
• Attentive Semantic Exploring for Manipulated Face Detection
• On generative models as the basis for digital twins
• Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
• Design by adaptive sampling
• DALLE-URBAN: Capturing the urban design expertise of large text to image transformers
• Inductive Representation Learning on Temporal Graphs
• Exploring particle dynamics during self-organization processes via rotationally invariant latent representations
• Edge-based sequential graph generation with recurrent neural networks
• Adversarial Learning with Local Coordinate Coding
• On the Evaluation of Conditional GANs
• Differentially Private Data Generative Models
• A spectral surrogate model for stochastic simulators computed from trajectory samples
• Quantum device fine-tuning using unsupervised embedding learning
• Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
• Improving Variational Encoder-Decoders in Dialogue Generation
• Solving Bayesian Inverse Problems via Variational Autoencoders
• Graph Residual Flow for Molecular Graph Generation
• Data Augmentation for End-to-end Code-switching Speech Recognition
• A Theory of Usable Information Under Computational Constraints
• Robust Out-of-distribution Detection for Neural Networks
• Airline Passenger Name Record Generation using Generative Adversarial Networks
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• MuProp: Unbiased Backpropagation for Stochastic Neural Networks
• Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
• Probabilistic Autoencoder
• Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
• Unsupervised Pathology Detection: A Deep Dive Into the State of the Art
• Adversarial Autoencoders with Constant-Curvature Latent Manifolds
• Educating Text Autoencoders: Latent Representation Guidance via Denoising
• Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks
• Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables
• VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
• Overfitting for Fun and Profit: Instance-Adaptive Data Compression
• Active Learning: Problem Settings and Recent Developments
• DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
• Using latent space regression to analyze and leverage compositionality in GANs
• GraphDF: A Discrete Flow Model for Molecular Graph Generation
• Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
• Multivariate Time-series Anomaly Detection via Graph Attention Network
• Artemis: Articulated Neural Pets with Appearance and Motion synthesis
• Flash Photography for Data-Driven Hidden Scene Recovery
• GenNI: Human-AI Collaboration for Data-Backed Text Generation
• Information Maximization Clustering via Multi-View Self-Labelling
• Variational Bayesian Monte Carlo with Noisy Likelihoods
• Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition
• Convolutional Generation of Textured 3D Meshes
• State Space LSTM Models with Particle MCMC Inference
• Structured Attention for Unsupervised Dialogue Structure Induction
• An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
• Generating Comprehensive Lithium Battery Charging Data with Generative AI
• GP-VAE: Deep Probabilistic Time Series Imputation
• Deep Synthetic Minority Over-Sampling Technique
• SDM-NET: Deep Generative Network for Structured Deformable Mesh
• Thermal experiments for fractured rock characterization: theoretical analysis and inverse modeling
• FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis
• Mask-aware Photorealistic Face Attribute Manipulation
• Focal Frequency Loss for Image Reconstruction and Synthesis
• FitVid: Overfitting in Pixel-Level Video Prediction
• Lossless Image Compression through Super-Resolution
• Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
• Bayesian model and dimension reduction for uncertainty propagation: applications in random media
• Discrete and continuous representations and processing in deep learning: Looking forward
• Generative Modeling and Inverse Imaging of Cardiac Transmembrane Potential
• A Study of the Generalizability of Self-Supervised Representations
• Deep Semi-Supervised Anomaly Detection
• ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis
• Diffusion Variational Autoencoders
• Developing Bug-Free Machine Learning Systems With Formal Mathematics
• Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections
• Toward a Better Monitoring Statistic for Profile Monitoring via Variational Autoencoders
• Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows
• Amortized Variational Inference: A Systematic Review
• Towards Safe Machine Learning for CPS: Infer Uncertainty from Training Data
• The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
• Physics-informed GANs for Coastal Flood Visualization
• Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder
• Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
• Neural Spline Flows
• The Generalized Reparameterization Gradient
• Tighter Variational Bounds are Not Necessarily Better
• Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
• Semi-supervised source localization with deep generative modeling
• Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
• Reweighted Wake-Sleep
• Neural Canonical Transformation with Symplectic Flows
• Learning to Generate and Reconstruct 3D Meshes with only 2D Supervision
• Hamiltonian Generative Networks
• Reconstructing continuous distributions of 3D protein structure from cryo-EM images
• NeRF-VAE: A Geometry Aware 3D Scene Generative Model
• Representation, learning, and planning algorithms for geometric task and motion planning
• Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
• Attentive Neural Processes
• Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models
• Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
• Learning Image Representations by Completing Damaged Jigsaw Puzzles
• Neural Manifold Ordinary Differential Equations
• GAR: An efficient and scalable Graph-based Activity Regularization for semi-supervised learning
• Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis
• Face Image Quality Assessment: A Literature Survey
• EFTofLSS meets simulation-based inference: ${\sigma }_8$ from biased tracers
• Boosting Neural Image Compression for Machines Using Latent Space Masking
• Solving time dependent Fokker-Planck equations via temporal normalizing flow
• RWR-GAE: Random Walk Regularization for Graph Auto Encoders
• Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
• Mathematical Models of Overparameterized Neural Networks
• Scalable and Efficient Neural Speech Coding: A Hybrid Design
• Unsupervised State Representation Learning in Atari
• The Dynamic Embedded Topic Model
• Are Generative Classifiers More Robust to Adversarial Attacks?
• Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity
• Exposing Previously Undetectable Faults in Deep Neural Networks
• PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
• Modeling documents with Generative Adversarial Networks
• Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
• DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
• DP-BART for Privatized Text Rewriting under Local Differential Privacy
• Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
• Black-box Variational Inference for Stochastic Differential Equations
• Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
• Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming
• Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
• The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces
• Flowfield prediction of airfoil off-design conditions based on a modified variational autoencoder
• Operationally meaningful representations of physical systems in neural networks
• Focused Hierarchical RNNs for Conditional Sequence Processing
• Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Models
• McGan: Mean and Covariance Feature Matching GAN
• Nonlinear Invariant Risk Minimization: A Causal Approach
• Diverse Image Captioning with Context-Object Split Latent Spaces
• High-resolution Deep Convolutional Generative Adversarial Networks
• Robust Locally-Linear Controllable Embedding
• Hierarchical Quantized Autoencoders
• Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
• Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
• Black-box Adversarial Attacks with Bayesian Optimization
• 3DMolNet: A Generative Network for Molecular Structures
• Netboost: Boosting-supported network analysis improves high-dimensional omics prediction in acute myeloid leukemia and Huntington's disease
• Advances in Variational Inference
• Capturing Dynamics of Information Diffusion in SNS: A Survey of Methodology and Techniques
• Approximate Inference with Amortised MCMC
• Variational Bayesian Approximation of Inverse Problems using Sparse Precision Matrices
• Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
• Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
• Perfect density models cannot guarantee anomaly detection
• Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
• Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks
• Inverse Transport Networks
• Self-supervised visual learning in the low-data regime: a comparative evaluation
• Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model
• Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks
• DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning
• Hierarchical Autoregressive Image Models with Auxiliary Decoders
• Creativity in the era of artificial intelligence
• Improving black-box optimization in VAE latent space using decoder uncertainty
• Turbulence forecasting via Neural ODE
• A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
• Learning FRAME Models Using CNN Filters
• Learning to Fly via Deep Model-Based Reinforcement Learning
• Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
• Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
• Mastering Atari with Discrete World Models
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• IGNOR: Image-guided Neural Object Rendering
• Regularizing Deep Networks with Semantic Data Augmentation
• Generalizing Face Forgery Detection with High-frequency Features
• Decision-Making with Auto-Encoding Variational Bayes
• Independent Prototype Propagation for Zero-Shot Compositionality
• Bayesian policy selection using active inference
• Learning Implicit Priors for Motion Optimization
• Learning with hidden variables
• A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
• Fairness without the sensitive attribute via Causal Variational Autoencoder
• Fast mesh denoising with data driven normal filtering using deep variational autoencoders
• Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
• Automatic Differentiable Monte Carlo: Theory and Application
• Multi-Time Attention Networks for Irregularly Sampled Time Series
• Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
• Transport Analysis of Infinitely Deep Neural Network
• Information bottleneck through variational glasses
• Gradient Estimation with Stochastic Softmax Tricks
• Max-margin Deep Generative Models
• Efficient Learning of the Parameters of Non-Linear Models using Differentiable Resampling in Particle Filters
• Action Capsules: Human Skeleton Action Recognition
• Training Deep Learning Based Denoisers without Ground Truth Data
• Generative Slate Recommendation with Reinforcement Learning
• Iterative energy-based projection on a normal data manifold for anomaly localization
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• Generative Multi-Form Bayesian Optimization
• The Deep Kernelized Autoencoder
• MetaPix: Few-Shot Video Retargeting
• Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning
• All You Need is a Good Functional Prior for Bayesian Deep Learning
• Multi-class Gaussian Process Classification with Noisy Inputs
• Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• Controllable Level Blending between Games using Variational Autoencoders
• Transitive Invariance for Self-supervised Visual Representation Learning
• How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?
• Permutation Invariant Graph Generation via Score-Based Generative Modeling
• Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model
• Learning to Traverse Latent Spaces for Musical Score Inpainting
• Learning to Generate Chairs, Tables and Cars with Convolutional Networks
• Variational Template Machine for Data-to-Text Generation
• Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective
• Data Augmentation and Classification of Sea-Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN
• CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy
• Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
• Probing transfer learning with a model of synthetic correlated datasets
• Recent advances in deep learning theory
• Wavelet Transform-assisted Adaptive Generative Modeling for Colorization
• Block Neural Autoregressive Flow
• Focus on Impact: Indoor Exploration with Intrinsic Motivation
• Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck
• Relevance Factor VAE: Learning and Identifying Disentangled Factors
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• A practical tutorial on Variational Bayes
• Learning to Assist Drone Landings
• On Counterfactual Explanations under Predictive Multiplicity
• A Model to Search for Synthesizable Molecules
• not-MIWAE: Deep Generative Modelling with Missing not at Random Data
• A Comparative Study of Self-supervised Speech Representation Based Voice Conversion
• Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
• Statistical and Topological Properties of Sliced Probability Divergences
• A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation
• Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
• Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA
• Disentangled Person Image Generation
• Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
• Multiple Causal Inference with Latent Confounding
• Elucidating proximity magnetism through polarized neutron reflectometry and machine learning
• Causal datasheet: An approximate guide to practically assess Bayesian networks in the real world
• Esophageal virtual disease landscape using mechanics-informed machine learning
• Offline Reinforcement Learning with Reverse Model-based Imagination
• Visualising energy landscapes through manifold learning
• A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series
• AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models
• Locality and compositionality in zero-shot learning
• Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Hebbian Semi-Supervised Learning in a Sample Efficiency Setting
• Extendable and invertible manifold learning with geometry regularized autoencoders
• Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
• Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness
• Bandwidth Extension on Raw Audio via Generative Adversarial Networks
• Towards causal generative scene models via competition of experts
• Brain MRI Tumor Segmentation with Adversarial Networks
• A Memory System of a Robot Cognitive Architecture and its Implementation in ArmarX
• 3D Part Assembly Generation with Instance Encoded Transformer
• Single Episode Policy Transfer in Reinforcement Learning
• SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
• PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
• Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencoder
• A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
• Synthesizing Filamentary Structured Images with GANs
• Latent Convolutional Models
• Bayesian Renormalization
• A Less Biased Evaluation of Out-of-distribution Sample Detectors
• Learning latent state representation for speeding up exploration
• BOSS: Bayesian Optimization over String Spaces
• In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
• TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
• Functional PCA and Deep Neural Networks-based Bayesian Inverse Uncertainty Quantification with Transient Experimental Data
• Adversarial Attacks on Variational Autoencoders
• VFlow: More Expressive Generative Flows with Variational Data Augmentation
• Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
• TherML: Thermodynamics of Machine Learning
• Responsible Disclosure of Generative Models Using Scalable Fingerprinting
• Backdoor Attack through Frequency Domain
• Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model
• Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
• Weakly-Supervised Action Localization by Generative Attention Modeling
• Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion
• Style-transfer GANs for bridging the domain gap in synthetic pose estimator training
• Uncertainty Quantification with Generative Models
• Generative Learning of the Solution of Parametric Partial Differential Equations Using Guided Diffusion Models and Virtual Observations
• Expressive TTS Training with Frame and Style Reconstruction Loss
• Using machine learning to parametrize postmerger signals from binary neutron stars
• Learning Interpretable Representation for Controllable Polyphonic Music Generation
• An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
• Learning Wake-Sleep Recurrent Attention Models
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• Revealing Fundamental Physics from the Daya Bay Neutrino Experiment using Deep Neural Networks
• Extending Unsupervised Neural Image Compression With Supervised Multitask Learning
• Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis
• Audio query-based music source separation
• KATE: K-Competitive Autoencoder for Text
• Adversarial Variational Optimization of Non-Differentiable Simulators
• Score-Based Generative Models for PET Image Reconstruction
• View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
• Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces
• Wasserstein Dependency Measure for Representation Learning
• Anomaly Detection with Score Distribution Discrimination
• Bi-fidelity Variational Auto-encoder for Uncertainty Quantification
• Neural Autoregressive Distribution Estimation
• Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
• Perpetual Motion: Generating Unbounded Human Motion
• Learning Disentangled Representations with Reference-Based Variational Autoencoders
• Model Inversion Networks for Model-Based Optimization
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
• Variational Attention for Sequence-to-Sequence Models
• Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
• Deep Generative Video Compression
• Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks
• Towards Visually Explaining Variational Autoencoders
• A Deep Generative Model of Speech Complex Spectrograms
• Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients
• Deep Visual Foresight for Planning Robot Motion
• Fast Second-Order Stochastic Backpropagation for Variational Inference
• Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression
• A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
• See, Hear, Explore: Curiosity via Audio-Visual Association
• Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
• Learnable Explicit Density for Continuous Latent Space and Variational Inference
• Sparse Graphical Memory for Robust Planning
• Structured Object-Aware Physics Prediction for Video Modeling and Planning
• Deep reinforcement learning for smart calibration of radio telescopes
• Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
• A survey of machine learning-based physics event generation
• A generative model for molecule generation based on chemical reaction trees
• Deep Directed Generative Autoencoders
• Empirically Measuring Transfer Distance for System Design and Operation
• White Paper Machine Learning in Certified Systems
• Multi-resolution Multi-task Gaussian Processes
• Early Inference in Energy-Based Models Approximates Back-Propagation
• Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization
• A RAD approach to deep mixture models
• On the Latent Space of Wasserstein Auto-Encoders
• DONet: Dual Objective Networks for Skin Lesion Segmentation
• Learning a Deep ConvNet for Multi-label Classification with Partial Labels
• Dimensionality Reduction for Categorical Data
• Merlion: A Machine Learning Library for Time Series
• Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics
• Stroke-based sketched symbol reconstruction and segmentation
• Learning Global Pairwise Interactions with Bayesian Neural Networks
• First results of the glitching pulsars monitoring program at the Argentine Institute of Radioastronomy
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
• Deep Factors with Gaussian Processes for Forecasting
• Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective
• CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
• A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research
• RelationNet2: Deep Comparison Columns for Few-Shot Learning
• Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
• Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
• Continual State Representation Learning for Reinforcement Learning using Generative Replay
• Disentangling by Partitioning: A Representation Learning Framework for Multimodal Sensory Data
• Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems
• Hierarchical Variational Models
• Designing Perceptual Puzzles by Differentiating Probabilistic Programs
• Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
• Mixing autoencoder with classifier: conceptual data visualization
• Debiased Contrastive Learning
• Exploiting Persona Information for Diverse Generation of Conversational Responses
• Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
• Behavior Self-Organization Supports Task Inference for Continual Robot Learning
• Fundamental problems in statistical physics XIV: Lecture on Machine Learning
• Auto-Encoding Knockoff Generator for FDR Controlled Variable Selection
• Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect
• Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series
• Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0
• Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
• Phase Transitions for the Information Bottleneck in Representation Learning
• Deep Learning in Mining Biological Data
• Hierarchical Adversarially Learned Inference
• Causal Discovery from Incomplete Data: A Deep Learning Approach
• Style Generator Inversion for Image Enhancement and Animation
• Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
• Stochastic Normalizing Flows
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Symmetric Variational Autoencoder and Connections to Adversarial Learning
• Knowledge Cross-Distillation for Membership Privacy
• Minibatch optimal transport distances; analysis and applications
• Deeptime: a Python library for machine learning dynamical models from time series data
• Gaussian variational approximation for high-dimensional state space models
• Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss
• Reconstruction Student with Attention for Student-Teacher Pyramid Matching
• A Spectral Regularizer for Unsupervised Disentanglement
• Desiderata for Representation Learning: A Causal Perspective
• Defending Against Adversarial Examples with K-Nearest Neighbor
• Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
• Differential Anomaly Detection for Facial Images
• The Power Spherical distribution
• A Non-Parametric Test to Detect Data-Copying in Generative Models
• Disentangling User Interest and Conformity for Recommendation with Causal Embedding
• Neural Augmentation of Kalman Filter with Hypernetwork for Channel Tracking
• On the Effectiveness of Least Squares Generative Adversarial Networks
• Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data
• A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
• Patterns for Learning with Side Information
• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
• NAOMI: Non-Autoregressive Multiresolution Sequence Imputation
• Cramer-Wold AutoEncoder
• Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
• Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
• Towards meaningful physics from generative models
• Unsupervised Learning of Video Representations via Dense Trajectory Clustering
• Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition
• Learning a Structural Causal Model for Intuition Reasoning in Conversation
• A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
• From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
• Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
• CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis
• Disentangled Recurrent Wasserstein Autoencoder
• Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
• Tensorial Mixture Models
• Energy-based Models for Video Anomaly Detection
• Autofocused oracles for model-based design
• Graph Generation with Variational Recurrent Neural Network
• Modeling motor control in continuous-time Active Inference: a survey
• Deep Gaussian Process-Based Bayesian Inference for Contaminant Source Localization
• Estimating Gradients for Discrete Random Variables by Sampling without Replacement
• A case for new neural network smoothness constraints
• Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
• Learning Discrete Distributions by Dequantization
• Zero-shot Domain Adaptation without Domain Semantic Descriptors
• Scalable Gaussian Process Variational Autoencoders
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• Deep Predictive Policy Training using Reinforcement Learning
• Solving PDE-constrained Control Problems Using Operator Learning
• A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
• Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition
• Electra: Conditional Generative Model based Predicate-Aware Query Approximation
• The Six Fronts of the Generative Adversarial Networks
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
• Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)
• Probabilistic dose prediction using mixture density networks for automated radiation therapy treatment planning
• Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
• Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
• Semi-Supervised Domain Generalization with Stochastic StyleMatch
• Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms
• Variational Autoencoders with Normalizing Flow Decoders
• Bidirectional Helmholtz Machines
• Auto-Differentiating Linear Algebra
• Generative causal explanations of black-box classifiers
• Unsupervised Knowledge-Transfer for Learned Image Reconstruction
• Fast uncertainty quantification of reservoir simulation with variational U-Net
• A Tutorial on VAEs: From Bayes' Rule to Lossless Compression
• A Mathematical Introduction to Generative Adversarial Nets (GAN)
• Spatial Uncertainty Sampling for End-to-End Control
• Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
• Probabilistic feature extraction, dose statistic prediction and dose mimicking for automated radiation therapy treatment planning
• A Probabilistic Framework for Deep Learning
• A Semantic-based Medical Image Fusion Approach
• Autoencoding Variational Autoencoder
• Survival Function Matching for Calibrated Time-to-Event Predictions
• Deep Generative Models for Distribution-Preserving Lossy Compression
• Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing
• Risk-Averse Offline Reinforcement Learning
• Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent
• Image Generation From Small Datasets via Batch Statistics Adaptation
• AliGraph: A Comprehensive Graph Neural Network Platform
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
• Consistent Generative Query Networks
• S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
• Artificial Intelligence and Dimensionality Reduction: Tools for approaching future communications
• Online Deep Learning from Doubly-Streaming Data
• A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
• GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
• Contextual Imagined Goals for Self-Supervised Robotic Learning
• Information Dropout: Learning Optimal Representations Through Noisy Computation
• PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design
• D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection
• Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
• Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers
• iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling
• You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
• Calibrating Deep Convolutional Gaussian Processes
• A graph-based probabilistic geometric deep learning framework with online enforcement of physical constraints to predict the criticality of defects in porous materials
• Characterization and Generation of 3D Realistic Geological Particles with Metaball Descriptor based on X-Ray Computed Tomography
• Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser
• Accelerating Bayesian microseismic event location with deep learning
• Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
• When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes
• Learning to Generate with Memory
• Bridging the gap between paired and unpaired medical image translation
• DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networks
• Learning 3D Dense Correspondence via Canonical Point Autoencoder
• Graph Learning Network: A Structure Learning Algorithm
• ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models
• High-Precision Inversion of Dynamic Radiography Using Hydrodynamic Features
• Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
• RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior
• A Short Survey On Memory Based Reinforcement Learning
• Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
• Unsupervised Word Segmentation from Speech with Attention
• Perceptual Generative Autoencoders
• Exploring Bias in GAN-based Data Augmentation for Small Samples
• Analyzing drop coalescence in microfluidic device with a deep learning generative model
• Intent Disentanglement and Feature Self-supervision for Novel Recommendation
• Dialogue State Induction Using Neural Latent Variable Models
• Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
• Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
• Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties
• Deep learning based Meta-modeling for Multi-objective Technology Optimization of Electrical Machines
• Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
• Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
• Zero-Shot Recommender Systems
• LayoutVAE: Stochastic Scene Layout Generation From a Label Set
• Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems
• Stochastic Deep Koopman Model for Quality Propagation Analysis in Multistage Manufacturing Systems
• Contrastively Disentangled Sequential Variational Autoencoder
• Overdispersed Black-Box Variational Inference
• Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
• The stochastic digital human is now enrolling for in silico imaging trials -- Methods and tools for generating digital cohorts
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• Hidden Talents of the Variational Autoencoder
• Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search
• Adaptive sequential Monte Carlo for posterior inference and model selection among complex geological priors
• A likelihood approach to nonparametric estimation of a singular distribution using deep generative models
• Learning Mesh Representations via Binary Space Partitioning Tree Networks
• Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation
• Embedded out-of-distribution detection on an autonomous robot platform
• Deep-learning-based reduced-order modeling for subsurface flow simulation
• Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding
• Deep Amortized Clustering
• Generative Models as Distributions of Functions
• Smoothing Methods for Automatic Differentiation Across Conditional Branches
• Unsupervised anomaly localization using VAE and beta-VAE
• Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation
• TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
• Continual Learning in Recurrent Neural Networks
• Unified Adversarial Invariance
• Maximizing Mutual Information for Tacotron
• Active Image Synthesis for Efficient Labeling
• Generating unseen complex scenes: are we there yet?
• Categorical Normalizing Flows via Continuous Transformations
• Learning Pose-invariant 3D Object Reconstruction from Single-view Images
• Causal Reasoning in Software Quality Assurance: A Systematic Review
• Task Specific Adversarial Cost Function
• Exponential Family Estimation via Adversarial Dynamics Embedding
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications
• Novelty Detection Via Blurring
• A PCA-like Autoencoder
• f-Divergence Variational Inference
• Effect of The Latent Structure on Clustering with GANs
• PLAS: Latent Action Space for Offline Reinforcement Learning
• Preventing Posterior Collapse with delta-VAEs
• MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
• Reliable training and estimation of variance networks
• Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
• Energy-based models for atomic-resolution protein conformations
• A probabilistic deep learning model of inter-fraction anatomical variations in radiotherapy
• Interference Motion Removal for Doppler Radar Vital Sign Detection Using Variational Encoder-Decoder Neural Network
• Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19
• Towards Asteroid Detection in Microlensing Surveys with Deep Learning
• Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
• A Generative Node-attribute Network Model for Detecting Generalized Structure
• A Variational Bayes Approach to Adaptive Radio Tomography
• Distance-Based Learning from Errors for Confidence Calibration
• SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
• Treatment effect estimation with disentangled latent factors
• Markovian Score Climbing: Variational Inference with KL(p||q)
• A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
• Discriminative Transformation Learning for Fuzzy Sparse Subspace Clustering
• Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians
• FREE: Feature Refinement for Generalized Zero-Shot Learning
• The Variational Gaussian Process
• Invariant Representations from Adversarially Censored Autoencoders
• Generative Adversarial Zero-shot Learning via Knowledge Graphs
• Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble
• Jointly Deep Multi-View Learning for Clustering Analysis
• Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective
• Generating unrepresented proportions of geological facies using Generative Adversarial Networks
• Understanding Overparameterization in Generative Adversarial Networks
• Bounded Rational Decision-Making with Adaptive Neural Network Priors
• Variational Laplace Autoencoders
• Diverse Multimedia Layout Generation with Multi Choice Learning
• Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
• Geodesic Clustering in Deep Generative Models
• Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction
• FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity
• Dense Intrinsic Appearance Flow for Human Pose Transfer
• Generalization Properties of Optimal Transport GANs with Latent Distribution Learning
• Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems
• Treatment Learning Causal Transformer for Noisy Image Classification
• Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
• What Do We Mean by Generalization in Federated Learning?
• The Causal-Neural Connection: Expressiveness, Learnability, and Inference
• Score-based Generative Modeling in Latent Space
• Streaming Variational Monte Carlo
• X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
• Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior
• Learning-Aided Physical Layer Attacks Against Multicarrier Communications in IoT
• Big Learning with Bayesian Methods
• Truncated Variational Expectation Maximization
• Classification and reconstruction of optical quantum states with deep neural networks
• A Meta-Learning Framework for Generalized Zero-Shot Learning
• Hyperparameter Auto-tuning in Self-Supervised Robotic Learning
• An Identifiable Double VAE For Disentangled Representations
• SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation
• Low-rank Characteristic Tensor Density Estimation Part I: Foundations
• Clockwork Variational Autoencoders
• Grasping Field: Learning Implicit Representations for Human Grasps
• Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
• Class-Conditional VAE-GAN for Local-Ancestry Simulation
• Shapley explainability on the data manifold
• Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
• Gradients as Features for Deep Representation Learning
• Predictive Uncertainty Quantification with Compound Density Networks
• Feature Unlearning for Pre-trained GANs and VAEs
• Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks
• Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration
• Sparsely Activated Networks
• Identification of Gaussian Process State Space Models
• CompILE: Compositional Imitation Learning and Execution
• CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
• Behavior From the Void: Unsupervised Active Pre-Training
• Reweighted Expectation Maximization
• Learning document embeddings along with their uncertainties
• Leveraging exploration in off-policy algorithms via normalizing flows
• LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
• ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description
• Semi-Supervised Generation with Cluster-aware Generative Models
• Learning and controlling the source-filter representation of speech with a variational autoencoder
• Densely connected normalizing flows
• COIL: Constrained Optimization in Learned Latent Space: Learning Representations for Valid Solutions
• Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
• PuVAE: A Variational Autoencoder to Purify Adversarial Examples
• Early-Phase Performance-Driven Design using Generative Models
• Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
• Bayesian Neural Networks for Reversible Steganography
• Posterior inference unchained with EL_2O
• Dirichlet Graph Variational Autoencoder
• Using Visual Anomaly Detection for Task Execution Monitoring
• Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations
• From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends
• Hyperbolic Deep Neural Networks: A Survey
• Variational AutoEncoder For Regression: Application to Brain Aging Analysis
• Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics
• Modular Generative Adversarial Networks
• Variational Recurrent Neural Machine Translation
• Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
• Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling
• Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
• Explaining Visual Models by Causal Attribution
• Unsupervised Discovery of 3D Physical Objects from Video
• VaPar Synth -- A Variational Parametric Model for Audio Synthesis
• Unsupervised learning for concept detection in medical images: a comparative analysis
• Signal retrieval with measurement system knowledge using variational generative model
• Statistics of Deep Generated Images
• Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias
• Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement
• Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems
• Generative Graph Convolutional Network for Growing Graphs
• Learning Compositional Radiance Fields of Dynamic Human Heads
• Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
• Representation Transfer for Differentially Private Drug Sensitivity Prediction
• Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
• Minimum Width for Universal Approximation
• Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning
• A Physical Model for Microstructural Characterization and Segmentation of 3D Tomography Data
• Understanding Instance-based Interpretability of Variational Auto-Encoders
• LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
• Learning to Learn with Variational Information Bottleneck for Domain Generalization
• Data Consistent Deep Rigid MRI Motion Correction
• Primal-Dual Wasserstein GAN
• Deep learning insights into cosmological structure formation
• A Tutorial on Sparse Gaussian Processes and Variational Inference
• Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning
• Cascaded Text Generation with Markov Transformers
• Emulating Sunyaev-Zeldovich Images of Galaxy Clusters using Auto-Encoders
• Calibration of Model Uncertainty for Dropout Variational Inference
• Contextual Dropout: An Efficient Sample-Dependent Dropout Module
• PDE-Driven Spatiotemporal Disentanglement
• ITENE: Intrinsic Transfer Entropy Neural Estimator
• Scalable Bayesian Inverse Reinforcement Learning
• Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
• Sparsity in Variational Autoencoders
• The continuous categorical: a novel simplex-valued exponential family
• Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders
• High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
• Interactive Image Manipulation with Natural Language Instruction Commands
• Deep Active Inference for Autonomous Robot Navigation
• Stateful Detection of Model Extraction Attacks
• Reducing Magnetic Resonance Image Spacing by Learning Without Ground-Truth
• Neural Rendering and Reenactment of Human Actor Videos
• Improving Unsupervised Domain Adaptation with Variational Information Bottleneck
• Encoders and Ensembles for Task-Free Continual Learning
• Pose Guided Human Video Generation
• Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
• Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set
• Time Perception Machine: Temporal Point Processes for the When, Where and What of Activity Prediction
• Dense Uncertainty Estimation
• Learning Disentangled Representations via Mutual Information Estimation
• Semantics Disentangling for Generalized Zero-Shot Learning
• Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
• Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
• Flow-Grounded Spatial-Temporal Video Prediction from Still Images
• Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
• Counterfactual Reasoning for Fair Clinical Risk Prediction
• Variational Neural Discourse Relation Recognizer
• Learning to Synthesize Programs as Interpretable and Generalizable Policies
• Learning to Predict Explainable Plots for Neural Story Generation
• TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
• Guided Variational Autoencoder for Disentanglement Learning
• Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
• Leveraging the Exact Likelihood of Deep Latent Variable Models
• Smoothed Action Value Functions for Learning Gaussian Policies
• Causal Discovery with Cascade Nonlinear Additive Noise Models
• Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums
• StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
• Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks
• Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections
• Functional Generative Design: An Evolutionary Approach to 3D-Printing
• Vision-based Navigation of Unmanned Aerial Vehicles in Orchards: An Imitation Learning Approach
• Multi-Agent Reinforcement Learning with Multi-Step Generative Models
• Source Separation with Deep Generative Priors
• On the Transfer of Disentangled Representations in Realistic Settings
• Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
• Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systems
• Learning Post-Hoc Causal Explanations for Recommendation
• Unsupervised Anomaly Detection for X-Ray Images
• MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
• A Deep Generative Model for Reordering Adjacency Matrices
• Unconstrained Monotonic Neural Networks
• Integer Discrete Flows and Lossless Compression
• Emerging Directions in Geophysical Inversion
• TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
• Exchangeable Neural ODE for Set Modeling
• Variable-rate discrete representation learning
• Manifold Modeling in Embedded Space: A Perspective for Interpreting Deep Image Prior
• Isometric Autoencoders
• Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction
• Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
• 3D Human Motion Estimation via Motion Compression and Refinement
• VAEs in the Presence of Missing Data
• Stochastic Prototype Embeddings
• Robust Errant Beam Prognostics with Conditional Modeling for Particle Accelerators
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models
• How reparametrization trick broke differentially-private text representation learning
• Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement
• Neural Design Network: Graphic Layout Generation with Constraints
• Adversarial Approximate Inference for Speech to Electroglottograph Conversion
• High Fidelity Face Manipulation with Extreme Poses and Expressions
• Two Methods For Wild Variational Inference
• Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders
• Estimation with Low-Rank Time-Frequency Synthesis Models
• Learning Human Objectives by Evaluating Hypothetical Behavior
• Testing the robustness of simulation-based gravitational-wave population inference
• Evaluating representations by the complexity of learning low-loss predictors
• SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System
• Generative Neurosymbolic Machines
• The Neural Moving Average Model for Scalable Variational Inference of State Space Models
• Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)
• Regularized Autoencoders via Relaxed Injective Probability Flow
• Accurate Passive Radar via an Uncertainty-Aware Fusion of Wi-Fi Sensing Data
• HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models
• Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes
• Lower Bounds for Compressed Sensing with Generative Models
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Tractable Regularization of Probabilistic Circuits
• DwNet: Dense warp-based network for pose-guided human video generation
• VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
• SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
• Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
• README: REpresentation learning by fairness-Aware Disentangling MEthod
• Design, Benchmarking and Explainability Analysis of a Game-Theoretic Framework towards Energy Efficiency in Smart Infrastructure
• Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
• Inferring Multidimensional Rates of Aging from Cross-Sectional Data
• Data Uncertainty Learning in Face Recognition
• Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction
• InfoColorizer: Interactive Recommendation of Color Palettes for Infographics
• Latent Causal Invariant Model
• Invertible Generative Modeling using Linear Rational Splines
• A Generative Model for Molecular Distance Geometry
• Towards neural networks that provably know when they don't know
• On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks
• ChartPointFlow for Topology-Aware 3D Point Cloud Generation
• Generating Images with Sparse Representations
• Associative Adversarial Networks
• MA-VAE: Multi-head Attention-based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-series Applied to Automotive Endurance Powertrain Testing
• Validated Variational Inference via Practical Posterior Error Bounds
• Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasets
• Metropolis-Hastings view on variational inference and adversarial training
• Adaptive Parameterization for Neural Dialogue Generation
• Disentangled Variational Representation for Heterogeneous Face Recognition
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• Expected path length on random manifolds
• Variational Autoencoders with Riemannian Brownian Motion Priors
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
• Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
• PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference
• Representation Learning for Event-based Visuomotor Policies
• Symbolic Music Generation with Diffusion Models
• Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN
• Reparameterization Gradient for Non-differentiable Models
• Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction
• Information Maximizing Visual Question Generation
• Using RGB Image as Visual Input for Mapless Robot Navigation
• DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
• Improving Generative Imagination in Object-Centric World Models
• Neural Architecture Optimization with Graph VAE
• Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning
• Private-Shared Disentangled Multimodal VAE for Learning of Hybrid Latent Representations
• Structured Black Box Variational Inference for Latent Time Series Models
• Neural Baselines for Word Alignment
• Identification of Rare Cortical Folding Patterns using Unsupervised Deep Learning
• MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
• Identifying Invariant Texture Violation for Robust Deepfake Detection
• Rationalizing Predictions by Adversarial Information Calibration
• Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN
• Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative
• Demystifying Inter-Class Disentanglement
• Kamino: Constraint-Aware Differentially Private Data Synthesis
• Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning
• Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimation
• Zero-Shot Semantic Segmentation
• Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation
• ProBO: Versatile Bayesian Optimization Using Any Probabilistic Programming Language
• Separable Shape Tensors for Aerodynamic Design
• Generative Design of Physical Objects using Modular Framework
• Autoencoding sensory substitution
• Towards Information-Seeking Agents
• SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
• Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
• Transforming Gaussian Processes With Normalizing Flows
• Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow
• Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networks
• Nonparametric Inference for Auto-Encoding Variational Bayes
• On the Necessity and Effectiveness of Learning the Prior of Variational Auto-Encoder
• IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System
• In the Eye of the Beholder: Gaze and Actions in First Person Video
• Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
• Probabilistic Active Meta-Learning
• Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
• Dual Variational Generation for Low-Shot Heterogeneous Face Recognition
• Recurrent Latent Variable Networks for Session-Based Recommendation
• Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
• Context-aware learning for generative models
• Disentangling and Learning Robust Representations with Natural Clustering
• Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
• Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
• Non-saturating GAN training as divergence minimization
• Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance
• A Flexible Framework for Anomaly Detection via Dimensionality Reduction
• Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components
• ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning
• Model of rough surfaces with Gaussian processes
• A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
• Information Theoretic Co-Training
• Data-driven multifidelity topology design with multi-channel variational auto-encoder for concurrent optimization of multiple design variable fields
• Disentangled Representations from Non-Disentangled Models
• Differentiable Particle Filtering without Modifying the Forward Pass
• Generative Melody Composition with Human-in-the-Loop Bayesian Optimization
• Radial and Directional Posteriors for Bayesian Neural Networks
• A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks
• Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images
• Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
• Long-term Human Motion Prediction with Scene Context
• Reinforcement Learning Generalization with Surprise Minimization
• Data Augmentation For Medical MR Image Using Generative Adversarial Networks
• Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
• Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
• Disentangled Representation Learning with Wasserstein Total Correlation
• Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
• MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
• Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network
• A Simple Spectral Failure Mode for Graph Convolutional Networks
• Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators
• Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
• Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection
• SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
• OneFlow: One-class flow for anomaly detection based on a minimal volume region
• Unsupervised Machine Commenting with Neural Variational Topic Model
• Learning Deep Generative Models with Doubly Stochastic MCMC
• Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
• Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression Values
• Storchastic: A Framework for General Stochastic Automatic Differentiation
• flexgrid2vec: Learning Efficient Visual Representations Vectors
• CATE: Computation-aware Neural Architecture Encoding with Transformers
• MMGAN: Generative Adversarial Networks for Multi-Modal Distributions
• Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
• Neural Density Estimation and Likelihood-free Inference
• On the Fairness of Disentangled Representations
• A Neural-enhanced Factor Graph-based Algorithm for Robust Positioning in Obstructed LOS Situations
• PaintBot: A Reinforcement Learning Approach for Natural Media Painting
• Regularizing by the Variance of the Activations' Sample-Variances
• Training Generative Reversible Networks
• Adversarial Domain Adaptation with Domain Mixup
• Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation
• Goal-Oriented Gaze Estimation for Zero-Shot Learning
• BasisVAE: Translation-invariant feature-level clustering with Variational Autoencoders
• Scaling Down Deep Learning with MNIST-1D
• Accelerated Discovery of Sustainable Building Materials
• Reparameterization trick for discrete variables
• Conditional Image Generation with Score-Based Diffusion Models
• Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning
• Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET
• Knowledge-Based Regularization in Generative Modeling
• Gaussian Copula Variational Autoencoders for Mixed Data
• SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
• Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
• Concept-Oriented Deep Learning: Generative Concept Representations
• Unsupervised Incremental Learning with Dual Concept Drift Detection for Identifying Anomalous Sequences
• CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge
• Automatic Feature Engineering for Time Series Classification: Evaluation and Discussion
• A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features
• Prediction of the morphological evolution of a splashing drop using an encoder-decoder
• Neural Variational Hybrid Collaborative Filtering
• AI-generated art perceptions with GenFrame -- an image-generating picture frame
• Persuasive Faces: Generating Faces in Advertisements
• Bimanual Grasp Synthesis for Dexterous Robot Hands
• Modelling multivariate spatio-temporal data with identifiable variational autoencoders
• Handloom Design Generation Using Generative Networks
• Hierarchical VampPrior Variational Fair Auto-Encoder
• Learning Actionable Representations with Goal-Conditioned Policies
• Label-Noise Robust Generative Adversarial Networks
• Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders
• Predictive Modeling, Pattern Recognition, and Spatiotemporal Representations of Plant Growth in Simulated and Controlled Environments: A Comprehensive Review
• An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation
• Image Generation from Layout
• A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model
• Learning the Precise Feature for Cluster Assignment
• Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization
• Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes
• Gaussian mixture models with Wasserstein distance
• Deep Fake Detection: Survey of Facial Manipulation Detection Solutions
• Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server
• Instance-level Facial Attributes Transfer with Geometry-Aware Flow
• Generative Models for Anomaly Detection and Design-Space Dimensionality Reduction in Shape Optimization
• Inducing Interpretable Representations with Variational Autoencoders
• Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
• Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications
• Locally Masked Convolution for Autoregressive Models
• Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data
• Structured Bayesian Gaussian process latent variable model
• A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
• Generative networks as inverse problems with Scattering transforms
• Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning
• Generating Contextual Load Profiles Using a Conditional Variational Autoencoder
• Unsupervised Video Decomposition using Spatio-temporal Iterative Inference
• TracInAD: Measuring Influence for Anomaly Detection
• Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space
• Minimizing FLOPs to Learn Efficient Sparse Representations
• Improving Deep Image Clustering With Spatial Transformer Layers
• Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting
• Semantic-Aware Generation for Self-Supervised Visual Representation Learning
• Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
• Region Semantically Aligned Network for Zero-Shot Learning
• Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
• Detecting Anomalous Faces with 'No Peeking' Autoencoders
• Variational Inference for Computational Imaging Inverse Problems
• Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
• SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning
• Exploratory State Representation Learning
• Self-Supervised Out-of-Distribution Detection in Brain CT Scans
• Uncertainty Inspired RGB-D Saliency Detection
• Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
• Information Potential Auto-Encoders
• We are More than Our Joints: Predicting how 3D Bodies Move
• Compound Probabilistic Context-Free Grammars for Grammar Induction
• MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction
• Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models
• Improving Query Efficiency of Black-box Adversarial Attack
• How Bayesian Should Bayesian Optimisation Be?
• MineGAN: effective knowledge transfer from GANs to target domains with few images
• Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoders
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• Soft then Hard: Rethinking the Quantization in Neural Image Compression
• Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery
• Conditional Generative Models for Counterfactual Explanations
• DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
• Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance
• Prediction of head motion from speech waveforms with a canonical-correlation-constrained autoencoder
• CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels
• Perturbative Black Box Variational Inference
• Predictive Sampling with Forecasting Autoregressive Models
• GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
• Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations
• Neural Recursive Belief States in Multi-Agent Reinforcement Learning
• Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
• Deep Multi-Fidelity Active Learning of High-dimensional Outputs
• DeepGalaxy: Deducing the Properties of Galaxy Mergers from Images Using Deep Neural Networks
• Object-Centric Image Generation with Factored Depths, Locations, and Appearances
• Combinatorial 3D Shape Generation via Sequential Assembly
• Human-interpretable model explainability on high-dimensional data
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• No MCMC for me: Amortized sampling for fast and stable training of energy-based models
• Variational Bayesian Context-aware Representation for Grocery Recommendation
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Benchmarking Graph Neural Networks on Link Prediction
• Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods
• Marginalized State Distribution Entropy Regularization in Policy Optimization
• Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey
• Contrastive Variational Reinforcement Learning for Complex Observations
• EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
• Deep Involutive Generative Models for Neural MCMC
• Multi-View representation learning in Multi-Task Scene
• Stellar Cluster Detection using GMM with Deep Variational Autoencoder
• Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning
• Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation
• Inference over radiative transfer models using variational and expectation maximization methods
• Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation
• Learning Dynamic Generator Model by Alternating Back-Propagation Through Time
• Recursive Inference for Variational Autoencoders
• SocialInteractionGAN: Multi-person Interaction Sequence Generation
• LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
• Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
• Learning Disentangled Representations for Time Series
• Towards Empirical Sandwich Bounds on the Rate-Distortion Function
• Learning Deep Generative Models with Annealed Importance Sampling
• CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
• RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation
• Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
• DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
• Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
• Performing Co-Membership Attacks Against Deep Generative Models
• Generative Adversarial Networks for Scintillation Signal Simulation in EXO-200
• Learning Discrete State Abstractions With Deep Variational Inference
• Generative Class-conditional Autoencoders
• Human Trajectory Prediction via Counterfactual Analysis
• Information Theory in Density Destructors
• Training VAEs Under Structured Residuals
• Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression
• Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
• Adversarially Approximated Autoencoder for Image Generation and Manipulation
• Bayesian Conditional Generative Adverserial Networks
• Variational Generative Stochastic Networks with Collaborative Shaping
• Variational Bayesian Decision-making for Continuous Utilities
• Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective
• Latent Variables on Spheres for Autoencoders in High Dimensions
• Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
• High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection
• Visual Language Modeling on CNN Image Representations
• Unsupervised Phoneme and Word Discovery from Multiple Speakers using Double Articulation Analyzer and Neural Network with Parametric Bias
• Denoising Diffusion Gamma Models
• Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
• Variational Integrator Networks for Physically Structured Embeddings
• Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
• Towards Robust Metrics for Concept Representation Evaluation
• Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
• Multimodal Variational Autoencoders for Semi-Supervised Learning: In Defense of Product-of-Experts
• Structured Embedding Models for Grouped Data
• Reachability Embeddings: Scalable Self-Supervised Representation Learning from Mobility Trajectories for Multimodal Geospatial Computer Vision
• Topic Modelling Meets Deep Neural Networks: A Survey
• Learning Latent Space Energy-Based Prior Model for Molecule Generation
• Normalizing Flows Across Dimensions
• AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
• Posterior Estimation Using Deep Learning: A Simulation Study of Compartmental Modeling in Dynamic PET
• Discovering Dialog Structure Graph for Open-Domain Dialog Generation
• Reconstruction Bottlenecks in Object-Centric Generative Models
• Connect the Dots: In Situ 4D Seismic Monitoring of CO2 Storage with Spatio-temporal CNNs
• Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
• Learning Hierarchical Priors in VAEs
• Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
• Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
• Adaptive Monte Carlo augmented with normalizing flows
• Semantics Preserving Adversarial Learning
• Local Expectation Gradients for Doubly Stochastic Variational Inference
• Deep Variational Sufficient Dimensionality Reduction
• TSIT: A Simple and Versatile Framework for Image-to-Image Translation
• The Role of Information Complexity and Randomization in Representation Learning
• DeepOBS: A Deep Learning Optimizer Benchmark Suite
• Amortized Bethe Free Energy Minimization for Learning MRFs
• TwoStreamVAN: Improving Motion Modeling in Video Generation
• SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
• Incorporating Interpretable Output Constraints in Bayesian Neural Networks
• Bayesian Optimization for Cascade-type Multi-stage Processes
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
• Scalable Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Computer Vision
• Geometry-Aware Hamiltonian Variational Auto-Encoder
• Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations
• On Initial Pools for Deep Active Learning
• Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds
• Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Survey
• Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits
• PixelCNN Models with Auxiliary Variables for Natural Image Modeling
• Sparse Orthogonal Variational Inference for Gaussian Processes
• Variational Leakage: The Role of Information Complexity in Privacy Leakage
• Conditional Adversarial Generative Flow for Controllable Image Synthesis
• Style Transfer with Time Series: Generating Synthetic Financial Data
• Robust Ordinal VAE: Employing Noisy Pairwise Comparisons for Disentanglement
• Automatic Relevance Determination For Deep Generative Models
• Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
• Few-Shot Action Localization without Knowing Boundaries
• Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
• Anytime Sampling for Autoregressive Models via Ordered Autoencoding
• Investigation of Using VAE for i-Vector Speaker Verification
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Make a Face: Towards Arbitrary High Fidelity Face Manipulation
• MissDeepCausal: Causal Inference from Incomplete Data Using Deep Latent Variable Models
• Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI
• Cerberus: A Multi-headed Derenderer
• Continuous Mixtures of Tractable Probabilistic Models
• tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder
• Fast Black-box Variational Inference through Stochastic Trust-Region Optimization
• Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
• TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
• 3D Shape Reconstruction from Free-Hand Sketches
• Pose-Guided High-Resolution Appearance Transfer via Progressive Training
• Automatic Variational ABC
• How Does GAN-based Semi-supervised Learning Work?
• Explaining Predictions by Approximating the Local Decision Boundary
• Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
• Sample-Efficient Training of Robotic Guide Using Human Path Prediction Network
• Hand-Object Contact Consistency Reasoning for Human Grasps Generation
• Non-Adversarial Imitation Learning and its Connections to Adversarial Methods
• AutoCure: Automated Tabular Data Curation Technique for ML Pipelines
• Using Probabilistic Movement Primitives in Analyzing Human Motion Difference under Transcranial Current Stimulation
• Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)
• Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence
• Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models
• A COLD Approach to Generating Optimal Samples
• Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples
• highway2vec -- representing OpenStreetMap microregions with respect to their road network characteristics
• Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional
• Learning Proposals for Probabilistic Programs with Inference Combinators
• Capturing Label Characteristics in VAEs
• Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
• Measuring Dependence with Matrix-based Entropy Functional
• Particle Smoothing Variational Objectives
• Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes
• Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology
• Variational Deep Semantic Hashing for Text Documents
• Full Scaling Automation for Sustainable Development of Green Data Centers
• Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
• What Is Considered Complete for Visual Recognition?
• G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
• Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults
• Improving VAEs' Robustness to Adversarial Attack
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration
• Expected Information Maximization: Using the I-Projection for Mixture Density Estimation
• Bipartite Graph Embedding via Mutual Information Maximization
• Generating Smooth Pose Sequences for Diverse Human Motion Prediction
• PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
• Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarios
• A Cross-Level Information Transmission Network for Predicting Phenotype from New Genotype: Application to Cancer Precision Medicine
• Variational Autoencoders for Opponent Modeling in Multi-Agent Systems
• Data-efficient visuomotor policy training using reinforcement learning and generative models
• ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance
• Zero-shot generation of synthetic neurosurgical data with large language models
• Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communication
• BézierSketch: A generative model for scalable vector sketches
• Do sequence-to-sequence VAEs learn global features of sentences?
• Automatic Backward Filtering Forward Guiding for Markov processes and graphical models
• $\beta$-Variational Autoencoder as an Entanglement Classifier
• Intrinsic Motivation for Encouraging Synergistic Behavior
• Vector-Quantized Timbre Representation
• Suggestive Annotation of Brain Tumour Images with Gradient-guided Sampling
• Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
• Label Propagation Adaptive Resonance Theory for Semi-supervised Continuous Learning
• Automated Discovery of Anomalous Features in Ultra-Large Planetary Remote Sensing Datasets using Variational Autoencoders
• Addressing the Topological Defects of Disentanglement via Distributed Operators
• Multi-Facet Clustering Variational Autoencoders
• Outlier Detection through Null Space Analysis of Neural Networks
• RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
• Quantitative Evaluation of Time-Dependent Multidimensional Projection Techniques
• Robust Multi-Output Learning with Highly Incomplete Data via Restricted Boltzmann Machines
• Short-Term Traffic Flow Prediction Using Variational LSTM Networks
• Independent finite approximations for Bayesian nonparametric inference
• Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
• Anomaly Detection on Graph Time Series
• Information Theoretic Meta Learning with Gaussian Processes
• A Method to Model Conditional Distributions with Normalizing Flows
• Label-Free Segmentation of COVID-19 Lesions in Lung CT
• MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
• BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
• PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
• Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning
• Neural Topic Model via Optimal Transport
• A Technical Survey on Statistical Modelling and Design Methods for Crowdsourcing Quality Control
• Measuring the Biases and Effectiveness of Content-Style Disentanglement
• Unsupervised Recurrent Neural Network Grammars
• Generative Machine Learning for Multivariate Equity Returns
• A Closed-Loop Perception, Decision-Making and Reasoning Mechanism for Human-Like Navigation
• Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing
• Deep Residual Mixture Models
• VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
• Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
• A Two-Step Framework for Arbitrage-Free Prediction of the Implied Volatility Surface
• P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection
• Variational Inference with Continuously-Indexed Normalizing Flows
• Progressive and Aligned Pose Attention Transfer for Person Image Generation
• Deep Auto-encoder with Neural Response
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
• Adaptive Cross-Modal Few-Shot Learning
• Safe Autonomous Racing via Approximate Reachability on Ego-vision
• Learning Continuous Environment Fields via Implicit Functions
• Data-Driven Topology Optimization with Multiclass Microstructures using Latent Variable Gaussian Process
• Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
• Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
• Set-Conditional Set Generation for Particle Physics
• Clustering, factor discovery and optimal transport
• Image-based reconstruction for the impact problems by using DPNNs
• On Energy-Based Models with Overparametrized Shallow Neural Networks
• Probabilistic Video Generation using Holistic Attribute Control
• Factored Temporal Sigmoid Belief Networks for Sequence Learning
• MaCow: Masked Convolutional Generative Flow
• Simple Video Generation using Neural ODEs
• Multi-Task Variational Information Bottleneck
• Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling
• Emergent Graphical Conventions in a Visual Communication Game
• A Systematic Assessment of Deep Learning Models for Molecule Generation
• Learning Functions over Sets via Permutation Adversarial Networks
• Joint Intensity-Gradient Guided Generative Modeling for Colorization
• Learning an optimal PSF-pair for ultra-dense 3D localization microscopy
• ChemoVerse: Manifold traversal of latent spaces for novel molecule discovery
• Provable Smoothness Guarantees for Black-Box Variational Inference
• Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder
• Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
• Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks
• SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
• Anomaly Detection Based on Deep Learning Using Video for Prevention of Industrial Accidents
• REX: Revisiting Budgeted Training with an Improved Schedule
• UFO-BLO: Unbiased First-Order Bilevel Optimization
• Learning Disentangled Representations of Timbre and Pitch for Musical Instrument Sounds Using Gaussian Mixture Variational Autoencoders
• Device Image-IV Mapping using Variational Autoencoder for Inverse Design and Forward Prediction
• Manifolds for Unsupervised Visual Anomaly Detection
• Toxicity Detection in Drug Candidates using Simplified Molecular-Input Line-Entry System
• Cost-sensitive detection with variational autoencoders for environmental acoustic sensing
• Learning Neurosymbolic Generative Models via Program Synthesis
• Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
• Learning to Navigate in Turbulent Flows with Aerial Robot Swarms: A Cooperative Deep Reinforcement Learning Approach
• LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation
• A Brief Overview of Unsupervised Neural Speech Representation Learning
• Offline Reinforcement Learning with Pseudometric Learning
• Super-Resolution Perception for Industrial Sensor Data
• Attentive Action and Context Factorization
• A deep generative model for gene expression profiles from single-cell RNA sequencing
• Dual Adversarial Inference for Text-to-Image Synthesis
• Deep Reactive Planning in Dynamic Environments
• Semi-supervised Multimodal Representation Learning through a Global Workspace
• Bidirectional Generative Modeling Using Adversarial Gradient Estimation
• Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders
• A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Models
• A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
• Vela Pulsar: Single Pulses Analysis with Machine Learning Techniques
• A Bayes-Optimal View on Adversarial Examples
• mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation
• StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
• Adaptive Graph Auto-Encoder for General Data Clustering
• Half-body Portrait Relighting with Overcomplete Lighting Representation
• Re-parameterizing VAEs for stability
• Probabilistic Embeddings for Cross-Modal Retrieval
• Embarrassingly Simple Binary Representation Learning
• Max-Affine Spline Insights into Deep Generative Networks
• Improving Direct Physical Properties Prediction of Heterogeneous Materials from Imaging Data via Convolutional Neural Network and a Morphology-Aware Generative Model
• Trajectory Prediction with Latent Belief Energy-Based Model
• Independent Innovation Analysis for Nonlinear Vector Autoregressive Process
• toon2real: Translating Cartoon Images to Realistic Images
• Data-Dependent Randomized Smoothing
• Representation learning for improved interpretability and classification accuracy of clinical factors from EEG
• Generating Out of Distribution Adversarial Attack using Latent Space Poisoning
• Distributed Weight Consolidation: A Brain Segmentation Case Study
• Dense Pose Transfer
• Anomaly scores for generative models
• Deciphering quantum fingerprints in electric conductance
• Straight-Through Estimator as Projected Wasserstein Gradient Flow
• Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
• Latent Programmer: Discrete Latent Codes for Program Synthesis
• Augment and Reduce: Stochastic Inference for Large Categorical Distributions
• Compositional uncertainty in deep Gaussian processes
• A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU
• Ergodic Inference: Accelerate Convergence by Optimisation
• Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control
• DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis
• A survey on Variational Autoencoders from a GreenAI perspective
• Generative Design of Crystal Structures by Point Cloud Representations and Diffusion Model
• Towards Rapid and Robust Adversarial Training with One-Step Attacks
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
• Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANs
• Shared Generative Latent Representation Learning for Multi-view Clustering
• Function Norms and Regularization in Deep Networks
• Generalization and Robustness Implications in Object-Centric Learning
• Hybrid VAE: Improving Deep Generative Models using Partial Observations
• Visual Adversarial Imitation Learning using Variational Models
• Benchmarking Deep Sequential Models on Volatility Predictions for Financial Time Series
• BachGAN: High-Resolution Image Synthesis from Salient Object Layout
• Hamiltonian Variational Auto-Encoder
• Machine Learning Percolation Model
• Testing Outlier Detection Algorithms for Identifying Early-Stage Solute Clusters in Atom Probe Tomography
• Variational Autoencoder with Learned Latent Structure
• Energy Consumption of Deep Generative Audio Models
• Learning Latent Space Energy-Based Prior Model
• Variational online learning of neural dynamics
• Probabilistically-autoencoded horseshoe-disentangled multidomain item-response theory models
• Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance
• Posterior Meta-Replay for Continual Learning
• AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models
• Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization
• Semi-supervised Learning with Missing Values Imputation
• Variational Feature Disentangling for Fine-Grained Few-Shot Classification
• Active Decision Boundary Annotation with Deep Generative Models
• Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning
• Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
• Domain Generalization via Inference-time Label-Preserving Target Projections
• LumièreNet: Lecture Video Synthesis from Audio
• Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
• PSD Representations for Effective Probability Models
• Comparing directed networks via denoising graphlet distributions
• DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
• Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say "I don't know" for Ambiguous Cases
• Lossless compression with state space models using bits back coding
• Triggering Dark Showers with Conditional Dual Auto-Encoders
• Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning
• RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval
• Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking
• Wasserstein Measure Coresets
• Generative Interventions for Causal Learning
• Global-Local Item Embedding for Temporal Set Prediction
• Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition
• Information Theory Measures via Multidimensional Gaussianization
• Bayesian Paragraph Vectors
• A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
• Adaptive Pruning of Neural Language Models for Mobile Devices
• Target-Embedding Autoencoders for Supervised Representation Learning
• Deep Variational Semi-Supervised Novelty Detection
• SincVAE: A new semi-supervised approach to improve anomaly detection on EEG data using SincNet and variational autoencoder
• Learning to Score Behaviors for Guided Policy Optimization
• Robust Pollen Imagery Classification with Generative Modeling and Mixup Training
• Variational Capsules for Image Analysis and Synthesis
• HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE
• Semantically Multi-modal Image Synthesis
• Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
• Agent Modelling under Partial Observability for Deep Reinforcement Learning
• Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
• FFPDG: Fast, Fair and Private Data Generation
• Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
• Domain-Robust Visual Imitation Learning with Mutual Information Constraints
• Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism
• Annealed Flow Transport Monte Carlo
• Learning Image Representations for Content Based Image Retrieval of Radiotherapy Treatment Plans
• Learning Implicit Generative Models by Teaching Explicit Ones
• NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
• Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
• Adaptive Stress Testing for Autonomous Vehicles
• Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
• An Uncertain Future: Forecasting from Static Images using Variational Autoencoders
• Generative Ratio Matching Networks
• Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems
• Sparse Stochastic Zeroth-Order Optimization with an Application to Bandit Structured Prediction
• Deep Generative Learning via Schrödinger Bridge
• Beyond Low Earth Orbit: Biological Research, Artificial Intelligence, and Self-Driving Labs
• Visual Conceptual Blending with Large-scale Language and Vision Models
• Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders
• Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
• Benchmarking Unsupervised Object Representations for Video Sequences
• Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity
• Learning robust speech representation with an articulatory-regularized variational autoencoder
• Variational Information Bottleneck on Vector Quantized Autoencoders
• SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
• Reducing Positional Variance in Cross-sectional Abdominal CT Slices with Deep Conditional Generative Models
• Constructing a meta-learner for unsupervised anomaly detection
• Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning
• Detection of Deepfake Videos Using Long Distance Attention
• Generating 3D People in Scenes without People
• Exploring Dynamic Context for Multi-path Trajectory Prediction
• The Art of Food: Meal Image Synthesis from Ingredients
• TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts
• mmFall: Fall Detection using 4D MmWave Radar and a Hybrid Variational RNN AutoEncoder
• Classifying CMB time-ordered data through deep neural networks
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Improving Disentangled Representation Learning with the Beta Bernoulli Process
• GO Gradient for Expectation-Based Objectives
• Learning Flat Latent Manifolds with VAEs
• Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data
• Constructing the Matrix Multilayer Perceptron and its Application to the VAE
• Towards White-box Benchmarks for Algorithm Control
• Evidence Transfer for Improving Clustering Tasks Using External Categorical Evidence
• Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis
• Self-Constructing Graph Convolutional Networks for Semantic Labeling
• Variational Bayesian surrogate modelling with application to robust design optimisation
• Learning Continuous-Time Dynamics by Stochastic Differential Networks
• Disentangling Content and Style via Unsupervised Geometry Distillation
• Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming
• GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
• retina-VAE: Variationally Decoding the Spectrum of Macular Disease
• dMelodies: A Music Dataset for Disentanglement Learning
• A Novel Variational Autoencoder with Applications to Generative Modelling, Classification, and Ordinal Regression
• Log Message Anomaly Detection and Classification Using Auto-B/LSTM and Auto-GRU
• Learning from Noisy Web Data with Category-level Supervision
• Latent feature disentanglement for 3D meshes
• Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
• GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing
• Learning to Assimilate in Chaotic Dynamical Systems
• Unsupervised multi-modal Styled Content Generation
• Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding
• InfoFair: Information-Theoretic Intersectional Fairness
• BoA-PTA, A Bayesian Optimization Accelerated Error-Free SPICE Solver
• StackVAE-G: An efficient and interpretable model for time series anomaly detection
• AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization
• Measuring Fairness in Generative Models
• Deep Random Splines for Point Process Intensity Estimation of Neural Population Data
• Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin
• Generalized Energy Based Models
• Trust-Region Variational Inference with Gaussian Mixture Models
• Implicit Autoencoders
• TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions
• Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
• Dynamic Future Net: Diversified Human Motion Generation
• Indoor thermal comfort management: A Bayesian machine-learning approach to data denoising and dynamics prediction of HVAC systems
• Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
• Unsupervised object-centric video generation and decomposition in 3D
• Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks
• Deep Denerative Models for Drug Design and Response
• Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models
• On importance-weighted autoencoders
• Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
• Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
• Streaming Adaptive Nonparametric Variational Autoencoder
• A Dynamic Edge Exchangeable Model for Sparse Temporal Networks
• A Fine-Grained Analysis on Distribution Shift
• An Empirical Study: Extensive Deep Temporal Point Process
• Weakly Supervised Label Learning Flows
• Label Dependent Deep Variational Paraphrase Generation
• The Thermodynamic Variational Objective
• Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
• Flow Contrastive Estimation of Energy-Based Models
• Personalized Federated Learning of Driver Prediction Models for Autonomous Driving
• Data Augmentation for Enhancing EEG-based Emotion Recognition with Deep Generative Models
• A Simple Framework for Uncertainty in Contrastive Learning
• Walsh-Hadamard Variational Inference for Bayesian Deep Learning
• View-Invariant Probabilistic Embedding for Human Pose
• Unified Generator-Classifier for Efficient Zero-Shot Learning
• Critical initialisation in continuous approximations of binary neural networks
• DualDis: Dual-Branch Disentangling with Adversarial Learning
• Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
• Bridging Global Context Interactions for High-Fidelity Image Completion
• Improving Neural Topic Models with Wasserstein Knowledge Distillation
• Particle Filter Recurrent Neural Networks
• HumanGAN: A Generative Model of Humans Images
• Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
• Generative Hierarchical Features from Synthesizing Images
• Variational Auto-Encoder: not all failures are equal
• Learning Implicit Generative Models with Theoretical Guarantees
• Deterministic Decoding for Discrete Data in Variational Autoencoders
• SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
• Semantic Adversarial Network for Zero-Shot Sketch-Based Image Retrieval
• Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
• Learning to learn generative programs with Memoised Wake-Sleep
• Deep Generative Learning via Variational Gradient Flow
• Few Shot System Identification for Reinforcement Learning
• GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations
• Horseshoe Regularization for Machine Learning in Complex and Deep Models
• On Disentanglement in Gaussian Process Variational Autoencoders
• Sliced Iterative Normalizing Flows
• Meta Dropout: Learning to Perturb Features for Generalization
• Deep Tensor CCA for Multi-view Learning
• Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation
• The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design
• Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control
• Bayesian Structure Adaptation for Continual Learning
• Surfing: Iterative optimization over incrementally trained deep networks
• Index Tracking with Cardinality Constraints: A Stochastic Neural Networks Approach
• Longitudinal Variational Autoencoder
• Point Process Flows
• Causal Effect Variational Autoencoder with Uniform Treatment
• Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
• Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
• Three-body renormalization group limit cycles based on unsupervised feature learning
• Unsupervised Part Discovery from Contrastive Reconstruction
• WAD: A Deep Reinforcement Learning Agent for Urban Autonomous Driving
• Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
• Unsupervised Embedding of Hierarchical Structure in Euclidean Space
• Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
• Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
• SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
• F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
• Monotonic Gaussian Process Flow
• Heredity-aware Child Face Image Generation with Latent Space Disentanglement
• Sub-word Level Lip Reading With Visual Attention
• Unsupervised Object Keypoint Learning using Local Spatial Predictability
• Reinforcement Learning with Efficient Active Feature Acquisition
• Augmenting and Tuning Knowledge Graph Embeddings
• Bringing Old Photos Back to Life
• Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders
• An Exploration of Learnt Representations of W Jets
• HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation
• Unsupervised Classification of Street Architectures Based on InfoGAN
• A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling
• Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
• k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport
• Domain-Specific Mappings for Generative Adversarial Style Transfer
• Learning Task Decomposition with Ordered Memory Policy Network
• Vertical-Horizontal Structured Attention for Generating Music with Chords
• Dual Contradistinctive Generative Autoencoder
• Predicting Visual Memory Schemas with Variational Autoencoders
• On the Transformation of Latent Space in Autoencoders
• Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
• Capacity-Approaching Autoencoders for Communications
• Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation
• A Study on the Autoregressive and non-Autoregressive Multi-label Learning
• DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
• Learning Multimodal VAEs through Mutual Supervision
• Coupled Gradient Estimators for Discrete Latent Variables
• Planning from Pixels using Inverse Dynamics Models
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Variance Reduction for Evolution Strategies via Structured Control Variates
• Retinal Vessel Segmentation Based on Conditional Deep Convolutional Generative Adversarial Networks
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
• Novelty Detection via Robust Variational Autoencoding
• Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns
• Causal Inference with Deep Causal Graphs
• PD-GAN: Probabilistic Diverse GAN for Image Inpainting
• Latent Variable Modeling for Generative Concept Representations and Deep Generative Models
• The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction
• Contrastive Attraction and Contrastive Repulsion for Representation Learning
• Latent Dirichlet Allocation in Generative Adversarial Networks
• Learning Disentangled Representations with Latent Variation Predictability
• A Mathematical Framework for Learning Probability Distributions
• Uncertainty-guided Model Generalization to Unseen Domains
• Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture
• Sparse Uncertainty Representation in Deep Learning with Inducing Weights
• Bayesian Methods in Tensor Analysis
• Efficient Learning of Generative Models via Finite-Difference Score Matching
• Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
• Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction
• Landmarks Augmentation with Manifold-Barycentric Oversampling
• Location Anomalies Detection for Connected and Autonomous Vehicles
• Bigeminal Priors Variational auto-encoder
• Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
• Continuously tempered Hamiltonian Monte Carlo
• Attentive Representation Learning with Adversarial Training for Short Text Clustering
• Learning to Predict Navigational Patterns from Partial Observations
• Effect of latent space distribution on the segmentation of images with multiple annotations
• Unsupervised dynamic modeling of medical image transformation
• Variational Autoencoders with a Structural Similarity Loss in Time of Flight MRAs
• Robotic Motion Planning using Learned Critical Sources and Local Sampling
• Continuous Graph Flow
• CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
• Learning Neural Light Transport
• Multi-Task Time Series Forecasting With Shared Attention
• CODE-AE: A Coherent De-confounding Autoencoder for Predicting Patient-Specific Drug Response From Cell Line Transcriptomics
• CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
• Seq2seq Translation Model for Sequential Recommendation
• A prior-based approximate latent Riemannian metric
• Improving generalization of vocal tract feature reconstruction: from augmented acoustic inversion to articulatory feature reconstruction without articulatory data
• Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
• Adversarial Disentanglement with Grouped Observations
• Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
• Video Reenactment as Inductive Bias for Content-Motion Disentanglement
• Bayesian Neural Networks for Virtual Flow Metering: An Empirical Study
• Program Synthesis Guided Reinforcement Learning for Partially Observed Environments
• Uniform Interpolation Constrained Geodesic Learning on Data Manifold
• Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Data
• CSI Clustering with Variational Autoencoding
• AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
• Singing Voice Conversion with Disentangled Representations of Singer and Vocal Technique Using Variational Autoencoders
• Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation
• 3D Shape Reconstruction from a Single 2D Image via 2D-3D Self-Consistency
• High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve
• Generative Image Modeling using Style and Structure Adversarial Networks
• Animating Face using Disentangled Audio Representations
• Sensorimotor Visual Perception on Embodied System Using Free Energy Principle
• Generative Mixture of Networks
• Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval
• Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
• Evolutionary Variational Optimization of Generative Models
• Multi-View Variational Autoencoder for Missing Value Imputation in Untargeted Metabolomics
• Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
• Meta-SVDD: Probabilistic Meta-Learning for One-Class Classification in Cancer Histology Images
• Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
• Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
• Bayesian Reasoning with Trained Neural Networks
• MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs
• Deep Inverse Feature Learning: A Representation Learning of Error
• Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)
• Refining Deep Generative Models via Discriminator Gradient Flow
• Unpaired Image-to-Image Translation via Latent Energy Transport
• Definition-independent Formalization of Soundscapes: Towards a Formal Methodology
• Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
• An Information-Geometric Distance on the Space of Tasks
• Interpretable Partitioned Embedding for Customized Fashion Outfit Composition
• Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction
• Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach
• Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
• Customizing Sequence Generation with Multi-Task Dynamical Systems
• Regularizing Model-Based Planning with Energy-Based Models
• Combining Spiking Neural Network and Artificial Neural Network for Enhanced Image Classification
• Coloring the Black Box: Visualizing neural network behavior with a self-introspective model
• Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
• Auto-Encoding Variational Bayes for Inferring Topics and Visualization
• Task-adaptive Neural Process for User Cold-Start Recommendation
• Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesis
• UVA: A Universal Variational Framework for Continuous Age Analysis
• Probabilistic Circuits for Variational Inference in Discrete Graphical Models
• A Variational Time Series Feature Extractor for Action Prediction
• Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
• CUDA: Contradistinguisher for Unsupervised Domain Adaptation
• TopoResNet: A hybrid deep learning architecture and its application to skin lesion classification
• Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
• Variational Autoencoding of PDE Inverse Problems
• Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning
• Target-Focused Feature Selection Using a Bayesian Approach
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models
• Class-Distinct and Class-Mutual Image Generation with GANs
• Task-Generic Hierarchical Human Motion Prior using VAEs
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
• Classify and Generate: Using Classification Latent Space Representations for Image Generations
• Bayesian Transformer Language Models for Speech Recognition
• Linear Algebra and Duality of Neural Networks
• Online reinforcement learning with sparse rewards through an active inference capsule
• White Noise Analysis of Neural Networks
• On the Difficulty of Unbiased Alpha Divergence Minimization
• Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
• Weight-Covariance Alignment for Adversarially Robust Neural Networks
• PRI-VAE: Principle-of-Relevant-Information Variational Autoencoders
• Variational Approximation of Factor Stochastic Volatility Models
• Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks
• Unsupervised Machine Learning Discovery of Chemical and Physical Transformation Pathways from Imaging Data
• My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• VAE-KRnet and its applications to variational Bayes
• Importance Weighted Hierarchical Variational Inference
• Review of Text Style Transfer Based on Deep Learning
• Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions
• Learning Global and Local Features of Normal Brain Anatomy for Unsupervised Abnormality Detection
• Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
• Embodied Self-supervised Learning by Coordinated Sampling and Training
• Including Physics in Deep Learning -- An example from 4D seismic pressure saturation inversion
• Semi-Supervised Variational Autoencoder for Survival Prediction
• The Convolution Exponential and Generalized Sylvester Flows
• Improved BiGAN training with marginal likelihood equalization
• Learning Latent State Spaces for Planning through Reward Prediction
• Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET
• Joint Learning of Generative Translator and Classifier for Visually Similar Classes
• TRADI: Tracking deep neural network weight distributions for uncertainty estimation
• An Attribute-Aligned Strategy for Learning Speech Representation
• Consensus Message Passing for Layered Graphical Models
• Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
• Federated Estimation of Causal Effects from Observational Data
• Predicting with High Correlation Features
• Invertible Zero-Shot Recognition Flows
• Future Urban Scenes Generation Through Vehicles Synthesis
• A unified survey of treatment effect heterogeneity modeling and uplift modeling
• Low Distortion Block-Resampling with Spatially Stochastic Networks
• AMENet: Attentive Maps Encoder Network for Trajectory Prediction
• On the Discrepancy between Density Estimation and Sequence Generation
• Crossmodal Voice Conversion
• Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices
• Self-Supervised Ultrasound to MRI Fetal Brain Image Synthesis
• Event-Based Modeling with High-Dimensional Imaging Biomarkers for Estimating Spatial Progression of Dementia
• Continual Learning of New Sound Classes using Generative Replay
• Variational Rejection Sampling
• BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning
• Group Anomaly Detection using Deep Generative Models
• Truncated Gaussian-Mixture Variational AutoEncoder
• Joint Variational Autoencoders for Recommendation with Implicit Feedback
• Edge-Enhanced Global Disentangled Graph Neural Network for Sequential Recommendation
• Reviewing continual learning from the perspective of human-level intelligence
• Contrastive Unpaired Translation using Focal Loss for Patch Classification
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• Representation Learning and Recovery in the ReLU Model
• Variational Inference with Holder Bounds
• The Variational Predictive Natural Gradient
• WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data
• Training Deep Spiking Auto-encoders without Bursting or Dying Neurons through Regularization
• Reconstruction and Membership Inference Attacks against Generative Models
• Learning to Model the Grasp Space of an Underactuated Robot Gripper Using Variational Autoencoder
• Multi-modal data generation with a deep metric variational autoencoder
• Physics-constrained, data-driven discovery of coarse-grained dynamics
• Learning Robust Feature Representations for Scene Text Detection
• Simple, Scalable, and Stable Variational Deep Clustering
• Pitchtron: Towards audiobook generation from ordinary people's voices
• Community Detection Clustering via Gumbel Softmax
• Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks
• An information-based metric for observing strategy optimization, demonstrated in the context of photometric redshifts with applications to cosmology
• Learning to Manipulate Individual Objects in an Image
• DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images
• Collision-Aware Target-Driven Object Grasping in Constrained Environments
• A Combined Deep Learning based End-to-End Video Coding Architecture for YUV Color Space
• Attention Map-guided Two-stage Anomaly Detection using Hard Augmentation
• Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
• Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval
• Future Frame Prediction for Robot-assisted Surgery
• Deepfake Videos in the Wild: Analysis and Detection
• Hierarchical Bayesian Model for the Transfer of Knowledge on Spatial Concepts based on Multimodal Information
• Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
• Unsupervised Learning of Lidar Features for Use in a Probabilistic Trajectory Estimator
• Group Equivariant Conditional Neural Processes
• Research and development of MolAICal for drug design via deep learning and classical programming
• Universal Neural Vocoding with Parallel WaveNet
• Neural Network architectures to classify emotions in Indian Classical Music
• Generating a Doppelganger Graph: Resembling but Distinct
• Learning based signal detection for MIMO systems with unknown noise statistics
• Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests
• Physics-aware, probabilistic model order reduction with guaranteed stability
• Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
• Generative Learning With Euler Particle Transport
• Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
• Generating private data with user customization
• Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization
• Unsupervised Anomaly Detection From Semantic Similarity Scores
• Iterative VAE as a predictive brain model for out-of-distribution generalization
• Representing and Denoising Wearable ECG Recordings
• ColdGAN: Resolving Cold Start User Recommendation by using Generative Adversarial Networks
• Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
• Diverse Plausible Shape Completions from Ambiguous Depth Images
• Dynamic allocation of limited memory resources in reinforcement learning
• Diffusion models for Handwriting Generation
• On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision
• Bayesian Variational Optimization for Combinatorial Spaces
• MAD-VAE: Manifold Awareness Defense Variational Autoencoder
• Measure Transport with Kernel Stein Discrepancy
• MisConv: Convolutional Neural Networks for Missing Data
• RoMA: Robust Model Adaptation for Offline Model-based Optimization
• On the Latent Holes of VAEs for Text Generation
• Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
• Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)
• Inferential Wasserstein Generative Adversarial Networks
• Few Shot Activity Recognition Using Variational Inference
• High-dimensional Assisted Generative Model for Color Image Restoration
• Fractional Transfer Learning for Deep Model-Based Reinforcement Learning
• DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs
• Transporting Causal Mechanisms for Unsupervised Domain Adaptation
• Towards the Unseen: Iterative Text Recognition by Distilling from Errors
• Anomaly Detection via Self-organizing Map
• Harmonization with Flow-based Causal Inference
• Variational Information Bottleneck for Effective Low-resource Audio Classification
• Diverse Video Generation using a Gaussian Process Trigger
• MCMC Variational Inference via Uncorrected Hamiltonian Annealing
• Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning
• GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes
• Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View
• Machine learning in the social and health sciences
• From Discourse to Narrative: Knowledge Projection for Event Relation Extraction
• Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
• NWT: Towards natural audio-to-video generation with representation learning
• Rectangular Flows for Manifold Learning
• Monte Carlo Filtering Objectives: A New Family of Variational Objectives to Learn Generative Model and Neural Adaptive Proposal for Time Series
• On the use of Nonlinear Normal Modes for Nonlinear Reduced Order Modelling
• It Is Likely That Your Loss Should be a Likelihood
• All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
• Model-agnostic out-of-distribution detection using combined statistical tests
• A Binded VAE for Inorganic Material Generation
• GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
• MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
• On Masked Pre-training and the Marginal Likelihood
• CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
• Deep Feature Response Discriminative Calibration
• Semantics-Aware Human Motion Generation from Audio Instructions
• Path and Bone-Contour Regularized Unpaired MRI-to-CT Translation
• Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
• Differentiable Particle Filtering using Optimal Placement Resampling
• Fast gradient-free activation maximization for neurons in spiking neural networks
• Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective
• T-Rep: Representation Learning for Time Series using Time-Embeddings
• Patch-wise Auto-Encoder for Visual Anomaly Detection
• Application-driven Validation of Posteriors in Inverse Problems
• Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
• Controllable Image Synthesis via SegVAE
• Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
• Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
• Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling
• A Commentary on the Unsupervised Learning of Disentangled Representations
• Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Images
• Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
• Geometrically Enriched Latent Spaces
• A Variational Autoencoder for Heterogeneous Temporal and Longitudinal Data
• Deep Learning Enables Robust and Precise Light Focusing on Treatment Needs
• Theoretical Connection between Locally Linear Embedding, Factor Analysis, and Probabilistic PCA
• OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
• Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey
• Instance-Aware Graph Convolutional Network for Multi-Label Classification
• Assessing Deep Neural Networks as Probability Estimators
• Inference and De-Noising of Non-Gaussian Particle Distribution Functions: A Generative Modeling Approach
• A Variational Approach to Unsupervised Sentiment Analysis
• On Learning the Transformer Kernel
• WeLa-VAE: Learning Alternative Disentangled Representations Using Weak Labels
• EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
• MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining
• Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
• Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
• Scarce Data Driven Deep Learning of Drones via Generalized Data Distribution Space
• Variational Marginal Particle Filters
• Variational Mixture of Normalizing Flows
• Learning to discover: expressive Gaussian mixture models for multi-dimensional simulation and parameter inference in the physical sciences
• Parameterization of Forced Isotropic Turbulent Flow using Autoencoders and Generative Adversarial Networks
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
• Gradient Importance Learning for Incomplete Observations
• Fair Normalizing Flows
• How Tight Can PAC-Bayes be in the Small Data Regime?
• Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder
• The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC
• Cross-Modal Generative Augmentation for Visual Question Answering
• Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images
• Text Generation with Deep Variational GAN
• Scalable Microservice Forensics and Stability Assessment Using Variational Autoencoders
• Autonomous Vehicles Drive into Shared Spaces: eHMI Design Concept Focusing on Vulnerable Road Users
• "Best-of-Many-Samples" Distribution Matching
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform
• On the Existence of Optimal Transport Gradient for Learning Generative Models
• Structured Dropout Variational Inference for Bayesian Neural Networks
• Energy-Inspired Models: Learning with Sampler-Induced Distributions
• Predictive coding feedback results in perceived illusory contours in a recurrent neural network
• Scaling Up Bayesian Uncertainty Quantification for Inverse Problems using Deep Neural Networks
• MIM: Mutual Information Machine
• Variational Encoders and Autoencoders : Information-theoretic Inference and Closed-form Solutions
• Reconstruction of Pairwise Interactions using Energy-Based Models
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
• A similarity-based Bayesian mixture-of-experts model
• Multi-type Disentanglement without Adversarial Training
• Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables
• Modular Action Concept Grounding in Semantic Video Prediction
• On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
• not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution
• Autoregressive Score Matching
• Deep Generative Modeling in Network Science with Applications to Public Policy Research
• Flexible mean field variational inference using mixtures of non-overlapping exponential families
• A Variational Auto-Encoder Approach for Image Transmission in Wireless Channel
• The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies
• Bayesian Meta-reinforcement Learning for Traffic Signal Control
• Random Polytope Descriptors
• Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning
• Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
• Zero-shot Synthesis with Group-Supervised Learning
• A Practical Layer-Parallel Training Algorithm for Residual Networks
• Linear Disentangled Representations and Unsupervised Action Estimation
• REMAX: Relational Representation for Multi-Agent Exploration
• Homotopic Gradients of Generative Density Priors for MR Image Reconstruction
• Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
• Accelerated WGAN update strategy with loss change rate balancing
• Nonparallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks
• Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
• Artificial Neural Networks Jamming on the Beat
• Gradient Origin Networks
• Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means
• Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
• Exploration by Maximizing Rényi Entropy for Reward-Free RL Framework
• Generating Semantically Valid Adversarial Questions for TableQA
• Hidden Markov Neural Networks
• Learning Controllable Disentangled Representations with Decorrelation Regularization
• MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing
• A lower bound for the ELBO of the Bernoulli Variational Autoencoder
• Disentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders
• Blur, Noise, and Compression Robust Generative Adversarial Networks
• SentenceMIM: A Latent Variable Language Model
• Single-View 3D Object Reconstruction from Shape Priors in Memory
• Hierarchical Kinematic Human Mesh Recovery
• Automatic Differentiation Variational Inference with Mixtures
• Relational State-Space Model for Stochastic Multi-Object Systems
• Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
• On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods
• Deep Learning Based Unsupervised and Semi-supervised Classification for Keratoconus
• On Positive-Unlabeled Classification in GAN
• MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
• Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
• Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation
• Rate-Regularization and Generalization in VAEs
• Amortized Population Gibbs Samplers with Neural Sufficient Statistics
• GSNs : Generative Stochastic Networks
• Understanding and Improving Virtual Adversarial Training
• Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement
• To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics
• Likelihood Contribution based Multi-scale Architecture for Generative Flows
• Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering
• Hierarchically Clustered Representation Learning
• Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift
• Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes
• DPPNet: Approximating Determinantal Point Processes with Deep Networks
• Generalization to Novel Objects using Prior Relational Knowledge
• Curriculum Learning for Deep Generative Models with Clustering
• Modeling the Biological Pathology Continuum with HSIC-regularized Wasserstein Auto-encoders
• Learning to compress and search visual data in large-scale systems
• Precision-Recall Curves Using Information Divergence Frontiers
• Probabilistic Discriminative Learning with Layered Graphical Models
• Variational inference for neural network matrix factorization and its application to stochastic blockmodeling
• Semi-Implicit Generative Model
• Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
• Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing
• Latent Variable Session-Based Recommendation
• Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
• PAC-Bayes Analysis of Sentence Representation
• An Alarm System For Segmentation Algorithm Based On Shape Model
• Accelerating Training of Deep Neural Networks with a Standardization Loss
• New Tricks for Estimating Gradients of Expectations
• Solving inverse problems via auto-encoders
• Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
• Attribute-Guided Sketch Generation
• StyleRemix: An Interpretable Representation for Neural Image Style Transfer
• On The Chain Rule Optimal Transport Distance
• State representation learning with recurrent capsule networks
• Black-Box Autoregressive Density Estimation for State-Space Models
• Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
• Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
• The Many Moods of Emotion
• Pairwise Augmented GANs with Adversarial Reconstruction Loss
• Generalized Latent Variable Recovery for Generative Adversarial Networks
• An ETF view of Dropout regularization
• Neural Allocentric Intuitive Physics Prediction from Real Videos
• Latent Space Optimal Transport for Generative Models
• Torchbearer: A Model Fitting Library for PyTorch
• Random Projection in Neural Episodic Control
• Structural Consistency and Controllability for Diverse Colorization
• Interactive user interface based on Convolutional Auto-encoders for annotating CT-scans
• Investigation of F0 conditioning and Fully Convolutional Networks in Variational Autoencoder based Voice Conversion
• Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects
• How good is my GAN?
• Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
• Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
• Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval
• Discrete flow posteriors for variational inference in discrete dynamical systems
• Distribution Aware Active Learning
• Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres
• BreGMN: scaled-Bregman Generative Modeling Networks
• Joint Learning of Neural Networks via Iterative Reweighted Least Squares
• Scenario Forecasting of Residential Load Profiles
• Exploring Deep Anomaly Detection Methods Based on Capsule Net
• Quantum query complexity of entropy estimation
• Importance Sampled Stochastic Optimization for Variational Inference
• Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples
• Structured Variational Inference for Coupled Gaussian Processes
• Computationally Efficient Bayesian Estimation of High Dimensional Copulas with Discrete and Mixed Margins
• Texture Synthesis with Recurrent Variational Auto-Encoder
• DISCO Nets: DISsimilarity COefficient Networks
• High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models
• Max-Margin Deep Generative Models for (Semi-)Supervised Learning
• Cascading Denoising Auto-Encoder as a Deep Directed Generative Model
• Symmetries and control in generative neural nets
• Semantics, Representations and Grammars for Deep Learning
• Towards universal neural nets: Gibbs machines and ACE
• An Empirical Study of Stochastic Variational Algorithms for the Beta Bernoulli Process
• Optimal Transport Based Generative Autoencoders
• Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning
• Double Control Variates for Gradient Estimation in Discrete Latent Variable Models
• Hierarchical Context enabled Recurrent Neural Network for Recommendation
• Quasi-Newton Quasi-Monte Carlo for variational Bayes
• UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning
• Variational Auto Encoder Gradient Clustering
• On Contrastive Representations of Stochastic Processes
• Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example
• Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features
• Variational Auto-Decoder: A Method for Neural Generative Modeling from Incomplete Data
• Sampling Using Neural Networks for colorizing the grayscale images
• Particle Filter Bridge Interpolation
• LyricJam: A system for generating lyrics for live instrumental music
• Uncertainty estimation for classification and risk prediction on medical tabular data
• Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
• Causality in Neural Networks -- An Extended Abstract
• Imitation Learning of Factored Multi-agent Reactive Models
• Learning Augmentation Distributions using Transformed Risk Minimization
• Adversarial sampling of unknown and high-dimensional conditional distributions
• Computer-Assisted Analysis of Biomedical Images
• Generative Model without Prior Distribution Matching
• Semantic Editing On Segmentation Map Via Multi-Expansion Loss
• Auto-Encoding for Shared Cross Domain Feature Representation and Image-to-Image Translation
• End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks
• Learning Signal-Agnostic Manifolds of Neural Fields
• Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes
• Ensemble Kalman Variational Objectives: Nonlinear Latent Trajectory Inference with A Hybrid of Variational Inference and Ensemble Kalman Filter
• Improving Text to Image Generation using Mode-seeking Function
• Deep Bayesian Unsupervised Lifelong Learning
• Untangling urban data signatures: unsupervised machine learning methods for the detection of urban archetypes at the pedestrian scale
• A Variational View on Bootstrap Ensembles as Bayesian Inference
• Kernel Mean Matching for Content Addressability of GANs
• Recursive Least Squares Based Refinement Network for the Rollout Trajectory Prediction Methods
• Deep Vocoder: Low Bit Rate Compression of Speech with Deep Autoencoder
• Unsupervised Disentanglement of Linear-Encoded Facial Semantics
• You Never Cluster Alone
• Using Sensory Time-cue to enable Unsupervised Multimodal Meta-learning
• Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
• Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales
• Digital phase-only holography using deep conditional generative models
• A Temporal Kernel Approach for Deep Learning with Continuous-time Information
• Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition
• I-nteract 2.0: A Cyber-Physical System to Design 3D Models using Mixed Reality Technologies and Deep Learning for Additive Manufacturing
• Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model
• Factorized Neural Processes for Neural Processes: $K$-Shot Prediction of Neural Responses
• Exploring Versatile Prior for Human Motion via Motion Frequency Guidance
• Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
• Learning Perceptual Manifold of Fonts
• Learning Conditional Invariance through Cycle Consistency
• Augmented KRnet for density estimation and approximation
• MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning
• Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification
• Improving latent variable descriptiveness with AutoGen
• Symmetric Wasserstein Autoencoders
• Towards a Mathematical Theory of Abstraction
• An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE
• Holographic Neural Architectures
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
• Learning Scalable ${\ell }_{\infty }$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
• Random Sum-Product Forests with Residual Links
• Semi-supervised multiple testing
• SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
• IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse
• Deep Switching State Space Model (DS${}^3$M) for Nonlinear Time Series Forecasting with Regime Switching
• Excavate Condition-invariant Space by Intrinsic Encoder
• Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
• ANFIC: Image Compression Using Augmented Normalizing Flows
• Pathwise Derivatives for Multivariate Distributions
• Metric Learning for Anti-Compression Facial Forgery Detection
• Unsupervised Learning of Neurosymbolic Encoders
• Memory and attention in deep learning
• Learning Calibratable Policies using Programmatic Style-Consistency
• LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
• Variational Learning for Unsupervised Knowledge Grounded Dialogs
• SVP-CF: Selection via Proxy for Collaborative Filtering Data
• Probabilistic Approach for Road-Users Detection
• Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations
• Structure-Aware Human-Action Generation
• Re-examination of the Role of Latent Variables in Sequence Modeling
• A Deep Generative Artificial Intelligence system to decipher species coexistence patterns
• Copula-Based Normalizing Flows
• Input Dependent Sparse Gaussian Processes
• Invertible Neural BRDF for Object Inverse Rendering
• Domain Private and Agnostic Feature for Modality Adaptive Face Recognition
• Assisting Scene Graph Generation with Self-Supervision
• $\beta$-Annealed Variational Autoencoder for glitches
• Mixture factorized auto-encoder for unsupervised hierarchical deep factorization of speech signal
• Generative Creativity: Adversarial Learning for Bionic Design
• Matching Embeddings for Domain Adaptation
• Neural Crossbreed: Neural Based Image Metamorphosis
• Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?
• Self-supervised SAR-optical Data Fusion and Land-cover Mapping using Sentinel-1/-2 Images
• Invariance-based Multi-Clustering of Latent Space Embeddings for Equivariant Learning
• Gaussian variational approximation with a factor covariance structure
• Discrete Action On-Policy Learning with Action-Value Critic
• Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning
• Disentanglement Analysis with Partial Information Decomposition
• Image Augmentation Using a Task Guided Generative Adversarial Network for Age Estimation on Brain MRI
• Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
• Regularized Sequential Latent Variable Models with Adversarial Neural Networks
• Harnessing value from data science in business: ensuring explainability and fairness of solutions
• Amortized backward variational inference in nonlinear state-space models
• Parameter estimation in FACS-seq enables high-throughput characterization of phenotypic heterogeneity
• Quasi-symplectic Langevin Variational Autoencoder
• M-estimation with the Trimmed l1 Penalty
• Policy Optimization with Second-Order Advantage Information
• A fast asynchronous MCMC sampler for sparse Bayesian inference
• Spherical Sliced-Wasserstein
• Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
• Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks
• Recent Developments in Program Synthesis with Evolutionary Algorithms
• Towards to Robust and Generalized Medical Image Segmentation Framework
• Intrinsically motivated option learning: a comparative study of recent methods
• GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization
• Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
• Deep Markov Random Field for Image Modeling
• f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
• Variational Pedestrian Detection
• Towards robustness under occlusion for face recognition
• Discrete Word Embedding for Logical Natural Language Understanding
• Unsupervised Learning of Sequence Representations by Autoencoders
• TOMA: Topological Map Abstraction for Reinforcement Learning
• Person-in-Context Synthesiswith Compositional Structural Space
• D3p -- A Python Package for Differentially-Private Probabilistic Programming
• Separate In Latent Space: Unsupervised Single Image Layer Separation
• Generative Locally Linear Embedding
• Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning
• Efficient and Robust Machine Learning for Real-World Systems
• Latent Network Embedding via Adversarial Auto-encoders
• Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion
• Model Order Selection with Variational Autoencoding
• Artistic Style in Robotic Painting; a Machine Learning Approach to Learning Brushstroke from Human Artists
• PRRS Outbreak Prediction via Deep Switching Auto-Regressive Factorization Modeling
• High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
• GAN-based Pose-aware Regulation for Video-based Person Re-identification
• Generative networks as inverse problems with fractional wavelet scattering networks
• ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects
• Conditioned Query Generation for Task-Oriented Dialogue Systems
• Learning Markov Random Fields for Combinatorial Structures via Sampling through Lovász Local Lemma
• An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
• Acoustic feature learning using cross-domain articulatory measurements
• Learning the Solution Manifold in Optimization and Its Application in Motion Planning
• Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
• Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder
• Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
• Neural View-Interpolation for Sparse Light Field Video
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• Discrete Point Flow Networks for Efficient Point Cloud Generation
• Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
• Prediction of liquid fuel properties using machine learning models with Gaussian processes and probabilistic conditional generative learning
• Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
• Neural Articulated Radiance Field
• Clustered Reinforcement Learning
• Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
• Signature-Graph Networks
• Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation
• Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
• An Overview on Generative AI at Scale with Edge-Cloud Computing
• Instance-Dependent Partial Label Learning
• Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial Nets
• CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator
• Controllable Data Augmentation Through Deep Relighting
• DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing
• Preventing posterior collapse in variational autoencoders for text generation via decoder regularization
• Learning Invariances for Interpretability using Supervised VAE
• Spatially-weighted Anomaly Detection with Regression Model
• Disentanglement Learning via Topology
• OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression
• Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks
• 3D Organ Shape Reconstruction from Topogram Images
• Dynamic Routing Networks
• General Characterization of Agents by States they Visit
• The equivalence between Stein variational gradient descent and black-box variational inference
• Explainability-aided Domain Generalization for Image Classification
• Representation Learning for Words and Entities
• My House, My Rules: Learning Tidying Preferences with Graph Neural Networks
• Learning to Rectify for Robust Learning with Noisy Labels
• Wasserstein Adversarially Regularized Graph Autoencoder
• Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
• torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP
• Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems
• Verification of ML Systems via Reparameterization
• Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness
• Solving deep-learning density functional theory via variational autoencoders
• Fighting Copycat Agents in Behavioral Cloning from Observation Histories
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference
• Cellular State Transformations using Generative Adversarial Networks
• Lifting 2D StyleGAN for 3D-Aware Face Generation
• Cooperative image captioning
• Fast Hyperparameter Optimization of Deep Neural Networks via Ensembling Multiple Surrogates
• MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
• Bilevel Continual Learning
• Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
• CookGAN: Meal Image Synthesis from Ingredients
• Challenges in Vessel Behavior and Anomaly Detection: From Classical Machine Learning to Deep Learning
• Uncovering Obscured Phonon Dynamics from Powder Inelastic Neutron Scattering using Machine Learning
• Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
• Gaussian Embedding of Temporal Networks
• Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking
• Vision-driven UAV River Following: Benchmarking with Safe Reinforcement Learning
• Phase Collaborative Network for Two-Phase Medical Image Segmentation
• Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrast
• The Bayesian Committee Approach for Computational Physics Problems
• Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
• Modeling Autonomous Shifts Between Focus State and Mind-Wandering Using a Predictive-Coding-Inspired Variational RNN Model
• ATM:Adversarial-neural Topic Model
• Generative Feature Replay with Orthogonal Weight Modification for Continual Learning
• An Iterative Closest Points Approach to Neural Generative Models
• LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning
• Pose2RGBD. Generating Depth and RGB images from absolute positions
• Synthesising Activity Participations and Scheduling with Deep Generative Machine Learning
• Latent Regression Bayesian Network for Data Representation
• Out-of-Sample Testing for GANs
• Synthetic Data Augmentation for Enhancing Harmful Algal Bloom Detection with Machine Learning
• Use of Student's t-Distribution for the Latent Layer in a Coupled Variational Autoencoder
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• Resolution and Relevance Trade-offs in Deep Learning
• Variational Monocular Depth Estimation for Reliability Prediction
• Conditional Generative Modeling via Learning the Latent Space
• Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech
• A Metric for Linear Symmetry-Based Disentanglement
• Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Sampling
• Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
• Learning geometry-image representation for 3D point cloud generation
• Sim2Real for Self-Supervised Monocular Depth and Segmentation
• Top-N: Equivariant set and graph generation without exchangeability
• Learning Compositional Sparse Gaussian Processes with a Shrinkage Prior
• Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network
• DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and $L_0$ Regularization
• Flow-based Generative Models for Learning Manifold to Manifold Mappings
• A New Distribution on the Simplex with Auto-Encoding Applications
• Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods
• Learning Portrait Style Representations
• Density Deconvolution with Normalizing Flows
• Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery
• NP-ODE: Neural Process Aided Ordinary Differential Equations for Uncertainty Quantification of Finite Element Analysis
• Graph-Based Method for Anomaly Prediction in Brain Network
• Local Competition and Uncertainty for Adversarial Robustness in Deep Learning
• C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling
• Fitting Skeletal Models via Graph-based Learning
• Accelerated Parallel Non-conjugate Sampling for Bayesian Non-parametric Models
• CoPE: Conditional image generation using Polynomial Expansions
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
• Self-Supervised Sketch-to-Image Synthesis
• Correspondence Learning for Controllable Person Image Generation
• Predictive Uncertainty through Quantization
• Local Competition and Stochasticity for Adversarial Robustness in Deep Learning
• Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models
• StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations
• Improving Generalization of Sequence Encoder-Decoder Networks for Inverse Imaging of Cardiac Transmembrane Potential
• Variational Determinant Estimation with Spherical Normalizing Flows
• Normalizing Flows with Multi-Scale Autoregressive Priors
• Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation
• Reinforcement Evolutionary Learning Method for self-learning
• Neural Contractive Dynamical Systems
• Learning the Compositional Spaces for Generalized Zero-shot Learning
• Improved Training of Sparse Coding Variational Autoencoder via Weight Normalization
• A Chain Graph Interpretation of Real-World Neural Networks
• Low-count Time Series Anomaly Detection
• Beyond traditional assumptions in fair machine learning
• Region-based Energy Neural Network for Approximate Inference
• Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation
• Geometric Enclosing Networks
• Online Variational Filtering and Parameter Learning
• Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE
• Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
• A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
• End-to-end Generative Zero-shot Learning via Few-shot Learning
• Assembling Semantically-Disentangled Representations for Predictive-Generative Models via Adaptation from Synthetic Domain
• Privacy-Preserving Self-Taught Federated Learning for Heterogeneous Data
• Learning Audio-Visual Correlations from Variational Cross-Modal Generation
• Sequential Matrix Completion
• Learning Robust Variational Information Bottleneck with Reference
• Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Latent Chord Labels and Features
• HUGE2: a Highly Untangled Generative-model Engine for Edge-computing
• Encapsulating models and approximate inference programs in probabilistic modules
• Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
• MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
• Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
• Detection of Alzheimer's Disease Using Graph-Regularized Convolutional Neural Network Based on Structural Similarity Learning of Brain Magnetic Resonance Images
• Generator Surgery for Compressed Sensing
• The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders
• The Pitfall of More Powerful Autoencoders in Lidar-Based Navigation
• Unsupervised Object Learning via Common Fate
• Generative Transition Mechanism to Image-to-Image Translation via Encoded Transformation
• Russian Natural Language Generation: Creation of a Language Modelling Dataset and Evaluation with Modern Neural Architectures
• Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech
• Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI
• Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms
• Conditional Graph Neural Processes: A Functional Autoencoder Approach
• Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
• Variational Knowledge Distillation for Disease Classification in Chest X-Rays
• A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models
• Variational Inference over Non-differentiable Cardiac Simulators using Bayesian Optimization
• ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision
• Information Theoretic Lower Bounds on Negative Log Likelihood
• Open-Ended Content-Style Recombination Via Leakage Filtering
• Variational Bayesian Quantization
• Learning Bijective Feature Maps for Linear ICA
• Leveraging Cross Feedback of User and Item Embeddings with Attention for Variational Autoencoder based Collaborative Filtering
• StyleDEM: a Versatile Model for Authoring Terrains
• Learning GPLVM with arbitrary kernels using the unscented transformation
• Masking schemes for universal marginalisers
• Neuro-Symbolic Generative Art: A Preliminary Study
• Electrocardio Panorama: Synthesizing New ECG Views with Self-supervision
• Stochastic Variational Bayesian Inference for a Nonlinear Forward Model
• Amortised Learning by Wake-Sleep
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
• Dynamic Narrowing of VAE Bottlenecks Using GECO and L0 Regularization
• Approximate Inference for Spectral Mixture Kernel
• Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection
• Fast and Efficient Scene Categorization for Autonomous Driving using VAEs
• Intrinsic motivations and open-ended learning
• Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model
• A simulator-based autoencoder for focal plane wavefront sensing
• Scalable Approximate Inference and Some Applications
• Transferable Task Execution from Pixels through Deep Planning Domain Learning
• Amortized variance reduction for doubly stochastic objectives
• Networked Time Series Prediction with Incomplete Data via Generative Adversarial Network
• SSN: Soft Shadow Network for Image Compositing
• Database development and exploration of microstructure versus process relationships using variational autoencoders
• Variational Autoencoders: A Harmonic Perspective
• Anomaly Detection in Video Data Based on Probabilistic Latent Space Models
• Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
• Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
• Provably robust deep generative models
• Knowledge-Guided Object Discovery with Acquired Deep Impressions
• Long-Term Human Video Generation of Multiple Futures Using Poses
• Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
• A Factorial Mixture Prior for Compositional Deep Generative Models
• Text Modeling with Syntax-Aware Variational Autoencoders
• Ordering Dimensions with Nested Dropout Normalizing Flows
• Variance Constrained Autoencoding
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck
• Decoupling Global and Local Representations via Invertible Generative Flows
• Residual-Recursion Autoencoder for Shape Illustration Images
• Mixture Representation Learning with Coupled Autoencoders
• Continuous Histogram Loss: Beyond Neural Similarity
• Tessellated Wasserstein Auto-Encoders
• Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization
• A Class of Algorithms for General Instrumental Variable Models
• Joints in Random Forests
• Learning undirected models via query training
• Linear, or Non-Linear, That is the Question!
• Stochastic Variational Inference via Upper Bound
• Autoencoding Under Normalization Constraints
• An Empirical Study of Generative Models with Encoders
• Equivariant Deep Dynamical Model for Motion Prediction
• Copula-like Variational Inference
• No Representation without Transformation
• Exploring Autoencoder-based Error-bounded Compression for Scientific Data
• Graph Embedding VAE: A Permutation Invariant Model of Graph Structure
• LAMP-HQ: A Large-Scale Multi-Pose High-Quality Database and Benchmark for NIR-VIS Face Recognition
• Off-Policy Policy Gradient Algorithms by Constraining the State Distribution Shift
• Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation
• Dynamic Relational Inference in Multi-Agent Trajectories
• Synthesising Multi-Modal Minority Samples for Tabular Data
• Scalable Modeling of Spatiotemporal Data using the Variational Autoencoder: an Application in Glaucoma
• Dependent Multi-Task Learning with Causal Intervention for Image Captioning
• Bandit algorithms for real-time data capture on large social medias
• Noise Attention based Spectrum Anomaly Detection Method for Unauthorized Bands
• To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs
• KernelNet: A Data-Dependent Kernel Parameterization for Deep Generative Modeling
• L-Verse: Bidirectional Generation Between Image and Text
• CRL: Class Representative Learning for Image Classification
• Learning Generative Prior with Latent Space Sparsity Constraints
• Generalized Doubly Reparameterized Gradient Estimators
• EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision
• Text-to-image Synthesis via Symmetrical Distillation Networks
• MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents
• Controllable Gradient Item Retrieval
• Relaxed-Responsibility Hierarchical Discrete VAEs
• Hybrid system identification using switching density networks
• Automatically Generating Macro Research Reports from a Piece of News
• Coarse Grained Exponential Variational Autoencoders
• DSBERT:Unsupervised Dialogue Structure learning with BERT
• Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation
• Robust Disentanglement of a Few Factors at a Time
• Latent Multi-Criteria Ratings for Recommendations
• Low-Variance Policy Gradient Estimation with World Models
• Interpreting Graph Drawing with Multi-Agent Reinforcement Learning
• Semi-supervised Autoencoding Projective Dependency Parsing
• Amortized Variational Deep Q Network
• Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems
• Statistical Guarantees for Transformation Based Models with Applications to Implicit Variational Inference
• Quantized Variational Inference
• Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis
• Learning to Organize Knowledge and Answer Questions with N-Gram Machines
• Testing for Typicality with Respect to an Ensemble of Learned Distributions
• Discriminative, Generative and Self-Supervised Approaches for Target-Agnostic Learning
• VCE: Variational Convertor-Encoder for One-Shot Generalization
• Controllable Emotion Transfer For End-to-End Speech Synthesis
• Asymmetric Variational Autoencoders
• End-To-End Dilated Variational Autoencoder with Bottleneck Discriminative Loss for Sound Morphing -- A Preliminary Study
• Lightweight Data Fusion with Conjugate Mappings
• Learning Informative Representations of Biomedical Relations with Latent Variable Models
• Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition
• Stochastic Talking Face Generation Using Latent Distribution Matching
• Node Attribute Generation on Graphs
• Autonomous learning of multiple, context-dependent tasks
• Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach
• Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
• Joint Estimation of Image Representations and their Lie Invariants
• Learning Consistent Deep Generative Models from Sparse Data via Prediction Constraints
• NeuralQAAD: An Efficient Differentiable Framework for High Resolution Point Cloud Compression
• LiveMap: Real-Time Dynamic Map in Automotive Edge Computing
• Cross-Domain Latent Modulation for Variational Transfer Learning
• OffCon${}^3$: What is state of the art anyway?
• A Tutorial on the Mathematical Model of Single Cell Variational Inference
• Formalising Concepts as Grounded Abstractions
• Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation
• Adversarial Machine Learning in Text Analysis and Generation
• Efficient Semi-Implicit Variational Inference
• NEMR: Network Embedding on Metric of Relation
• Accelerating Continuous Normalizing Flow with Trajectory Polynomial Regularization
• Automatic design of novel potential 3CL${}^{\text{pro}}$ and PL${}^{\text{pro}}$ inhibitors
• Neural representation and generation for RNA secondary structures
• Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extraction
• GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer
• HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception
• Improving Uncertainty Calibration via Prior Augmented Data
• Automatic Feature Extraction for Heartbeat Anomaly Detection
• Learning to Shift Attention for Motion Generation
• Domain Adaptation for Learning Generator from Paired Few-Shot Data
• Deep Goal-Oriented Clustering
• Continual Density Ratio Estimation in an Online Setting
• Analyzing the Hidden Activations of Deep Policy Networks: Why Representation Matters
• Non-Asymptotic Performance Guarantees for Neural Estimation of $\mathsf{f}$-Divergences
• GO Hessian for Expectation-Based Objectives
• Planning from Images with Deep Latent Gaussian Process Dynamics
• DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning
• Gradient Boosted Normalizing Flows
• Lipschitz standardization for multivariate learning
• NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps
• Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models
• Generating Object Stamps
• Roof Age Determination for the Automated Site-Selection of Rooftop Solar
• Bayesian Sparsification Methods for Deep Complex-valued Networks
• Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
• Bayesian task embedding for few-shot Bayesian optimization
• Deep Variational Luenberger-type Observer for Stochastic Video Prediction
• From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
• Unsupervised Program Synthesis for Images By Sampling Without Replacement
• MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
• Hierarchical Models: Intrinsic Separability in High Dimensions
• A Generative Learning Approach for Spatio-temporal Modeling in Connected Vehicular Network
• A Block-based Generative Model for Attributed Networks Embedding
• Defense Through Diverse Directions
• Towards GANs' Approximation Ability
• Neighbor Embedding Variational Autoencoder
• Out-of-Distribution Detection of Melanoma using Normalizing Flows
• Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
• Controlling for sparsity in sparse factor analysis models: adaptive latent feature sharing for piecewise linear dimensionality reduction
• Exploration-Exploitation Motivated Variational Auto-Encoder for Recommender Systems
• Learning to infer in recurrent biological networks
• Longitudinal Self-Supervised Learning
• A Generalised Linear Model Framework for $\beta$-Variational Autoencoders based on Exponential Dispersion Families
• Recurrent Flow Networks: A Recurrent Latent Variable Model for Density Modelling of Urban Mobility
• Efficient Approximate Inference with Walsh-Hadamard Variational Inference
• Approximation Based Variance Reduction for Reparameterization Gradients
• Deep Automodulators
• Fisher Auto-Encoders
• Automated Dependence Plots
• Compressed Sensing via Measurement-Conditional Generative Models
• Covariate Distribution Aware Meta-learning
• Representation Learning: A Statistical Perspective
• Sparsely Activated Networks: A new method for decomposing and compressing data
• Transformations between deep neural networks
• From Persistent Homology to Reinforcement Learning with Applications for Retail Banking
• Auto-encoding brain networks with applications to analyzing large-scale brain imaging datasets
• GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction
• Meta-Learning with Variational Bayes
• Learning mappings onto regularized latent spaces for biometric authentication
• SimVAE: Simulator-Assisted Training forInterpretable Generative Models
• Noise Robust Generative Adversarial Networks
• Neural Topic Models with Survival Supervision: Jointly Predicting Time-to-Event Outcomes and Learning How Clinical Features Relate
• Towards Better Understanding of Disentangled Representations via Mutual Information
• Deep Clustering of Compressed Variational Embeddings
• Supervised Encoding for Discrete Representation Learning
• Language coverage and generalization in RNN-based continuous sentence embeddings for interacting agents
• On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
• From the Expectation Maximisation Algorithm to Autoencoded Variational Bayes
• Zero-Shot Recognition via Optimal Transport
• TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction
• Invertible Manifold Learning for Dimension Reduction
• Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations
• Sampling possible reconstructions of undersampled acquisitions in MR imaging
• Bridging the Gap Between $f$-GANs and Wasserstein GANs
• MCMC-Interactive Variational Inference
• LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial Network
• Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
• Uncertainty in Neural Processes
• Modeling continuous-time stochastic processes using $\mathcal{N}$-Curve mixtures
• Contextualisation of eCommerce Users
• Decoupling feature propagation from the design of graph auto-encoders
• Anomaly Detection with Inexact Labels
• Data-driven Regularized Inference Privacy
• Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection
• Learning Priors for Adversarial Autoencoders
• Spectral Synthesis for Satellite-to-Satellite Translation
• Label-Conditioned Next-Frame Video Generation with Neural Flows
• Learning to Reconstruct and Segment 3D Objects
• How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
• Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
• NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps
• Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring
• Bayesian Neural Decoding Using A Diversity-Encouraging Latent Representation Learning Method
• Multilevel Monte Carlo estimation of log marginal likelihood
• Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
• Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment
• Quantifying and Learning Linear Symmetry-Based Disentanglement
• Using Neural Networks for Programming by Demonstration
• Regularization with Latent Space Virtual Adversarial Training
• Irregular Convolutional Auto-Encoder on Point Clouds
• Spatiotemporal Pattern Mining for Nowcasting Extreme Earthquakes in Southern California
• Stacked Wasserstein Autoencoder
• High Mutual Information in Representation Learning with Symmetric Variational Inference
• Reconsidering Analytical Variational Bounds for Output Layers of Deep Networks
• VAE-based Domain Adaptation for Speaker Verification
• Learning Graph-Based Priors for Generalized Zero-Shot Learning
• The backpropagation-based recollection hypothesis: Backpropagated action potentials mediate recall, imagination, language understanding and naming
• Compositional Video Prediction
• DGST : Discriminator Guided Scene Text detector
• ErrorNet: Learning error representations from limited data to improve vascular segmentation
• Bayesian Quadrature on Riemannian Data Manifolds
• Transductive Zero-Shot Learning by Decoupled Feature Generation
• Joint Wasserstein Distribution Matching
• The Angel is in the Priors: Improving GAN based Image and Sequence Inpainting with Better Noise and Structural Priors
• How Sequence-to-Sequence Models Perceive Language Styles?
• DEFT: Distilling Entangled Factors by Preventing Information Diffusion
• Probabilistic Trust Intervals for Out of Distribution Detection
• Inverse Design of Quantum Holograms in Three-Dimensional Nonlinear Photonic Crystals
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• PAUL: Procrustean Autoencoder for Unsupervised Lifting
• Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation
• Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction
• Medical data wrangling with sequential variational autoencoders
• Visual-Relation Conscious Image Generation from Structured-Text
• Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
• Semi-supervised voice conversion with amortized variational inference
• Model-free Policy Learning with Reward Gradients
• Continuous normalizing flows on manifolds
• Improve variational autoEncoder with auxiliary softmax multiclassifier
• Channel Decomposition into Painting Actions
• Intelligent image synthesis to attack a segmentation CNN using adversarial learning
• A Robust Speaker Clustering Method Based on Discrete Tied Variational Autoencoder
• Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings
• Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error
• A Linear Systems Theory of Normalizing Flows
• Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
• Eccentric Regularization: Minimizing Hyperspherical Energy without explicit projection
• Type I Attack for Generative Models
• MFPC-Net: Multi-fidelity Physics-Constrained Neural Process
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• WakaVT: A Sequential Variational Transformer for Waka Generation
• A comparison of classical and variational autoencoders for anomaly detection
• Data Augmentation with Variational Autoencoders and Manifold Sampling
• Learning What To Do by Simulating the Past
• Towards Verified Stochastic Variational Inference for Probabilistic Programs
• Joint Mapping and Calibration via Differentiable Sensor Fusion
• SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment
• Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning
• Generative latent neural models for automatic word alignment
• Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL
• A Practical & Unified Notation for Information-Theoretic Quantities in ML
• A Multi-Implicit Neural Representation for Fonts
• Interactive Optimization of Generative Image Modeling using Sequential Subspace Search and Content-based Guidance
• Enhanced Variational Inference with Dyadic Transformation
• Evidential Turing Processes
• TD-GEN: Graph Generation With Tree Decomposition
• Learning and Generalization in Overparameterized Normalizing Flows
• Probabilistic task modelling for meta-learning
• ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models
• Pulling back information geometry
• Learning Correlated Latent Representations with Adaptive Priors
• EMFlow: Data Imputation in Latent Space via EM and Deep Flow Models
• Stochastic Function Norm Regularization of Deep Networks
• Learning Identity-Preserving Transformations on Data Manifolds
• Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
• Cascade Decoders-Based Autoencoders for Image Reconstruction
• Towards Representation Learning with Tractable Probabilistic Models
• Computational Analysis of Deformable Manifolds: from Geometric Modelling to Deep Learning
• MLMOD: Machine Learning Methods for Data-Driven Modeling in LAMMPS
• Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
• Supervised Topological Maps
• P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening
• Variational Deep Image Denoising
• A Modified Convolutional Network for Auto-encoding based on Pattern Theory Growth Function
• Neural Scene Decoration from a Single Photograph
• Missingness Augmentation: A General Approach for Improving Generative Imputation Models
• Information Bottleneck Approach to Spatial Attention Learning
• Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation
• Implicit Generative Copulas
• Entropic Issues in Likelihood-Based OOD Detection
• New Perspective on Progressive GANs Distillation for One-class Novelty Detection
• Be More Active! Understanding the Differences between Mean and Sampled Representations of Variational Autoencoders
• Capturing Evolution Genes for Time Series Data
• Contrastive String Representation Learning using Synthetic Data
• Mixture-of-Variational-Experts for Continual Learning
• Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
• Information Theoretic Structured Generative Modeling
• When Can Neural Networks Learn Connected Decision Regions?
• Quantization-Based Regularization for Autoencoders
• On the Limitations of Multimodal VAEs
• Multi-View Image-to-Image Translation Supervised by 3D Pose
• Neural Estimation of Statistical Divergences
• DiverseNet: When One Right Answer is not Enough
• Towards Stable Imbalanced Data Classification via Virtual Big Data Projection
• Learning disentangled representation for classical models
• Investigating the Effect of Intraclass Variability in Temporal Ensembling
• Barlow Graph Auto-Encoder for Unsupervised Network Embedding
• Relay Variational Inference: A Method for Accelerated Encoderless VI
• TzK: Flow-Based Conditional Generative Model
• Contrastive Active Inference
• Visualization of AE's Training on Credit Card Transactions with Persistent Homology
• Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
• Causal Discovery from Conditionally Stationary Time Series
• Normalized Diversification
• $\beta$-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap
• Physics-Informed Deep Learning Characterizes Morphodynamics of Asian Soybean Rust Disease
• Learning to Learn Graph Topologies
• Planning with Expectation Models for Control
• Generating synthetic transactional profiles
• Diverse Exploration via Conjugate Policies for Policy Gradient Methods
• Differentiable TAN Structure Learning for Bayesian Network Classifiers
• Lossless Compression with Probabilistic Circuits
• Perturbative estimation of stochastic gradients
• Modeling Graph Node Correlations with Neighbor Mixture Models
• Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
• Point-to-Point Video Generation
• IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay
• Intuitive Shape Editing in Latent Space
• Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features
• Layered Controllable Video Generation
• A General Divergence Modeling Strategy for Salient Object Detection
• Discovering Latent Representations of Relations for Interacting Systems
• Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation
• Variational Auto-Encoder Architectures that Excel at Causal Inference
• Disentangling Physical Parameters for Anomalous Sound Detection Under Domain Shifts
• Symbolic Music Loop Generation with VQ-VAE
• Neural Motion Planning for Autonomous Parking
• Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation
• Video Content Swapping Using GAN
• Lossless Compression with Latent Variable Models
• Fast Non-Parametric Tests of Relative Dependency and Similarity
• Jointly Dynamic Topic Model for Recognition of Lead-lag Relationship in Two Text Corpora
• Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
• Differential Similarity in Higher Dimensional Spaces: Theory and Applications
• Multilevel Monte Carlo Variational Inference
• Manifold Optimization Assisted Gaussian Variational Approximation
• Generation Drawing/Grinding Trajectoy Based on Hierarchical CVAE
• Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks
• Improving Generalization of Deep Networks for Inverse Reconstruction of Image Sequences
• Encoding Causal Macrovariables
• Based on Graph-VAE Model to Predict Student's Score
• Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies
• Stochastic Contrastive Learning
• Self-supervised similarity search for large scientific datasets
• On the Practical Consistency of Meta-Reinforcement Learning Algorithms
• Deep Measurement Updates for Bayes Filters
• Forward Operator Estimation in Generative Models with Kernel Transfer Operators
• 3D-Aware Semantic-Guided Generative Model for Human Synthesis
• Anomalous sound detection based on interpolation deep neural network
• Towards Learning to Imitate from a Single Video Demonstration
• Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy
• Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical Systems
• WiSE-ALE: Wide Sample Estimator for Approximate Latent Embedding
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
• M${}^2$VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood
• What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations
• Automatic Quantification of Volumes and Biventricular Function in Cardiac Resonance. Validation of a New Artificial Intelligence Approach
• A Neural-Symbolic Framework for Mental Simulation
• The pursuit of beauty: Converting image labels to meaningful vectors
• On-Demand Video Dispatch Networks: A Scalable End-to-End Learning Approach
• OPAL-Net: A Generative Model for Part-based Object Layout Generation
• Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages
• Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
• Improving Generative Adversarial Networks with Local Coordinate Coding
• Domain Mismatch Robust Acoustic Scene Classification using Channel Information Conversion
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
• Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations
• The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
• Toroidal AutoEncoder
• High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling
• Approximate Inference via Fibrations of Statistical Games
• Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
• A New Perspective on Learning Context-Specific Independence
• Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
• Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
• Sequential Variational Autoencoders for Collaborative Filtering
• SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generation
• Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
• PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network
• Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization
• Training End-to-end Single Image Generators without GANs
• Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods
• Deep Koopman-based Control of Quality Variation in Multistage Manufacturing Systems
• Large-Angle Convergent-Beam Electron Diffraction Patterns via Conditional Generative Adversarial Networks
• Image-Based Reconstruction for a 3D-PFHS Heat Transfer Problem by ReConNN
• Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent Modeling
• Unsupposable Test-data Generation for Machine-learned Software
• Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
• Investigating Semi-Supervised Learning Algorithms in Text Datasets
• CNN in CT Image Segmentation: Beyound Loss Function for Expoliting Ground Truth Images
• MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
• Towards Robust Classification with Deep Generative Forests
• Generating new pictures in complex datasets with a simple neural network
• Self-Reflective Variational Autoencoder
• A Variational Auto-Encoder Model for Stochastic Point Processes
• The FMRIB Variational Bayesian Inference Tutorial II: Stochastic Variational Bayes
• Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning
• Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
• On Inductive Biases for Machine Learning in Data Constrained Settings
• Learning Sparsity of Representations with Discrete Latent Variables
• Variational Bayesian Framework for Advanced Image Generation with Domain-Related Variables
• EvoVGM: a Deep Variational Generative Model for Evolutionary Parameter Estimation
• AriEL: volume coding for sentence generation
• Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit
• Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems
• Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes
• Bi-Discriminator Class-Conditional Tabular GAN
• Unsupervised Representation Learning via Neural Activation Coding
• Action2video: Generating Videos of Human 3D Actions
• Processsing Simple Geometric Attributes with Autoencoders
• Decoder-free Robustness Disentanglement without (Additional) Supervision
• Group-based Learning of Disentangled Representations with Generalizability for Novel Contents
• Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
• Stay Positive: Non-Negative Image Synthesis for Augmented Reality
• Synthesizing Photorealistic Images with Deep Generative Learning
• Learning in Sparse Rewards settings through Quality-Diversity algorithms
• Disentangled Variational Information Bottleneck for Multiview Representation Learning
• Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization
• GAN pretraining for deep convolutional autoencoders applied to Software-based Fingerprint Presentation Attack Detection
• Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models
• Convolutional Normalizing Flows for Deep Gaussian Processes
• Measuring global properties of neural generative model outputs via generating mathematical objects
• MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
• Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees
• Graph Convolutional Memory using Topological Priors
• Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks
• Unsupervised Feature Learning for Online Voltage Stability Evaluation and Monitoring Based on Variational Autoencoder
• Multi-Decoder RNN Autoencoder Based on Variational Bayes Method
• Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization
• A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion
• On the Generative Utility of Cyclic Conditionals
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• Realistic molecule optimization on a learned graph manifold
• Domain Adaptation for Deviating Acquisition Protocols in CNN-based Lesion Classification on Diffusion-Weighted MR Images
• Probabilistic Re-aggregation Algorithm [First Draft]
• Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
• DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction
• Boosting Generative Models by Leveraging Cascaded Meta-Models
• Efficient training for future video generation based on hierarchical disentangled representation of latent variables
• Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates
• Debiasing a First-order Heuristic for Approximate Bi-level Optimization
• Unsupervised Neural Hidden Markov Models with a Continuous latent state space
• Atlas Based Representation and Metric Learning on Manifolds
• A Self-Supervised Framework for Function Learning and Extrapolation
• A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
• Efficient Deep Gaussian Process Models for Variable-Sized Input
• Bayesian Subspace HMM for the Zerospeech 2020 Challenge
• Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
• Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
• Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation
• Discrete Auto-regressive Variational Attention Models for Text Modeling
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
• Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation
• Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure
• Generating Data Augmentation samples for Semantic Segmentation of Salt Bodies in a Synthetic Seismic Image Dataset
• Towards bio-inspired unsupervised representation learning for indoor aerial navigation
• Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
• Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
• Efficient State-space Exploration in Massively Parallel Simulation Based Inference
• A Mechanism for Producing Aligned Latent Spaces with Autoencoders
• Generating the Graph Gestalt: Kernel-Regularized Graph Representation Learning
• Leveraging Hidden Structure in Self-Supervised Learning
• Dual Adversarial Variational Embedding for Robust Recommendation
• Reparameterized Sampling for Generative Adversarial Networks
• X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering
• Semi-supervised Learning with Contrastive Predicative Coding
• Learning by stochastic serializations
• Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
• Semantic and Geometric Unfolding of StyleGAN Latent Space
• Lifelong Twin Generative Adversarial Networks
• A Closer Look at the Adversarial Robustness of Information Bottleneck Models
• Understanding the Behaviour of the Empirical Cross-Entropy Beyond the Training Distribution
• Learning Aesthetic Layouts via Visual Guidance
• Modeling Grasp Motor Imagery through Deep Conditional Generative Models
• Minority Class Oversampling for Tabular Data with Deep Generative Models
• Unsupervised Skill-Discovery and Skill-Learning in Minecraft
• A Survey on Role-Oriented Network Embedding
• Network Learning with Local Propagation
• Introducing: DeepHead, Wide-band Electromagnetic Imaging Paradigm
• Replicating Active Appearance Model by Generator Network
• Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective
• What Remains of Visual Semantic Embeddings
• Analysis of ODE2VAE with Examples
• Applying the Information Bottleneck Principle to Prosodic Representation Learning
• Flow-based SVDD for anomaly detection
• Enhancing audio quality for expressive Neural Text-to-Speech
• Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
• Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation
• Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
• Exploiting Uncertainty of Loss Landscape for Stochastic Optimization
• Lattice Representation Learning
• ConRPG: Paraphrase Generation using Contexts as Regularizer
• Representation Learning for Efficient and Effective Similarity Search and Recommendation
• Neural network based order parameter for phase transitions and its applications in high-entropy alloys
• One-element Batch Training by Moving Window
• 3-Dimensional Deep Learning with Spatial Erasing for Unsupervised Anomaly Segmentation in Brain MRI
• Explainability Requires Interactivity
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Attribute-controlled face photo synthesis from simple line drawing
• Multi-way Clustering and Discordance Analysis through Deep Collective Matrix Tri-Factorization
• DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
• Efficient Model Identification for Tensegrity Locomotion
• Variational Composite Autoencoders
• Efficient Modelling Across Time of Human Actions and Interactions
• Video Autoencoder: self-supervised disentanglement of static 3D structure and motion
• Collaging Class-specific GANs for Semantic Image Synthesis
• Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
• CoRGi: Content-Rich Graph Neural Networks with Attention
• Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent
• Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes
• Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning
• DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
• Multiple Style Transfer via Variational AutoEncoder
• Diffusion Normalizing Flow
• The Neglected Sibling: Isotropic Gaussian Posterior for VAE
• Dynamic Variational Autoencoders for Visual Process Modeling
• GaussED: A Probabilistic Programming Language for Sequential Experimental Design
• MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
• PixelPyramids: Exact Inference Models from Lossless Image Pyramids
• Sufficient Dimension Reduction for High-Dimensional Regression and Low-Dimensional Embedding: Tutorial and Survey
• Class-Conditional Compression and Disentanglement: Bridging the Gap between Neural Networks and Naive Bayes Classifiers
• Group-disentangled Representation Learning with Weakly-Supervised Regularization
• Conditional Deep Gaussian Processes: empirical Bayes hyperdata learning
• Fine-Grained Control of Artistic Styles in Image Generation
• VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
• PatchGame: Learning to Signal Mid-level Patches in Referential Games
• Coulomb Autoencoders
• The Implicit Metropolis-Hastings Algorithm
• Coupled Variational Recurrent Collaborative Filtering
• Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
• Survival-oriented embeddings for improving accessibility to complex data structures
• GILBO: One Metric to Measure Them All
• Incremental Learning from Scratch for Task-Oriented Dialogue Systems
• Variational Inference with Numerical Derivatives: variance reduction through coupling