Auto-Encoding Variational Bayes
arXiv:1312.6114
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.
arXiv commentFixes a typo in the abstract, no other changes
References in corpus (3)
Cited by in corpus (3565)
- 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
- Artificial neural networks for neuroscientists: A primer
- Model-Based Reinforcement Learning for Atari
- 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
- GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
- Deep Appearance Models for Face Rendering
- 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
- Character Controllers Using Motion VAEs
- Guided Image Generation with Conditional Invertible Neural Networks
- Unsupervised Generative Modeling Using Matrix Product States
- Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
- Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
- Lossy Image Compression with Compressive Autoencoders
- 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
- Learning by Playing - Solving Sparse Reward Tasks from Scratch
- Neural Image Compression for Gigapixel Histopathology Image Analysis
- 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
- Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
- Soft Actor-Critic for Discrete Action Settings
- Stochastic Adversarial Video Prediction
- Adversarial Text-to-Image Synthesis: A Review
- A Deep Reinforcement Learning Chatbot
- Masked Autoregressive Flow for Density Estimation
- 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
- Keeping it Simple: Language Models can learn Complex Molecular Distributions
- SPICE: Semantic Pseudo-labeling for Image Clustering
- Neural Variational Inference and Learning in Belief Networks
- 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
- GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
- Molecular graph generation with Graph Neural 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
- Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks
- MR image reconstruction using deep density priors
- 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
- Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
- Causal Contextual Prediction for Learned Image Compression
- DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
- Dynamic Word Embeddings
- Gravitational-wave parameter estimation with autoregressive neural network flows
- Learning Model-Agnostic Counterfactual Explanations for Tabular Data
- Quantum generative adversarial network for generating discrete distribution
- 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
- Nonlinear Information Bottleneck
- Latent ODEs for Irregularly-Sampled Time Series
- Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
- 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
- WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
- Learning Sparse Neural Networks through Regularization
- Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
- High-throughput discovery of novel cubic crystal materials using deep generative neural networks
- Differentially Private Synthetic Medical Data Generation using Convolutional GANs
- 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
- Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
- Towards a Neural Statistician
- Deep Learning for Procedural Content Generation
- 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
- Deep Learning for Computational Cytology: A Survey
- Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
- GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
- Deep Learning in Mobile and Wireless Networking: A Survey
- Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
- Learning Representation for Clustering via Prototype Scattering and Positive Sampling
- Emotion Intensity and its Control for Emotional Voice Conversion
- Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
- A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- Tree Tensor Networks for Generative Modeling
- Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
- Do GANs actually learn the distribution? An empirical study
- Learning on Attribute-Missing Graphs
- 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
- 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
- Explaining by Removing: A Unified Framework for Model Explanation
- Compressing Neural Networks using the Variational Information Bottleneck
- Early Visual Concept Learning with Unsupervised Deep Learning
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Graph Convolutional Networks for Graphs Containing Missing Features
- Random Feature Attention
- Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
- Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder
- DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
- Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition
- Generative Visual Manipulation on the Natural Image Manifold
- MLIC: Multi-Reference Entropy Model for Learned Image Compression
- How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
- Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities
- Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
- Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
- Adapting Mask-RCNN for Automatic Nucleus Segmentation
- OmiEmbed: a unified multi-task deep learning framework for multi-omics data
- Sampling using gauge equivariant flows
- Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters
- LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving
- A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
- Are Disentangled Representations Helpful for Abstract Visual Reasoning?
- Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
- Grammar Variational Autoencoder
- Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
- Deep Knockoffs
- Deep learning algorithm for data-driven simulation of noisy dynamical system
- Generating and designing DNA with deep generative models
- RPC: A Large-Scale Retail Product Checkout Dataset
- TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
- Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
- Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification
- Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
- Lifelong Generative Modeling
- Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
- Learning to Decompose and Disentangle Representations for Video Prediction
- Diffusion Models, Image Super-Resolution And Everything: A Survey
- STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
- Review: Deep Learning in Electron Microscopy
- Jukebox: A Generative Model for Music
- Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
- Crystal Diffusion Variational Autoencoder for Periodic Material Generation
- Generating Diverse High-Fidelity Images with VQ-VAE-2
- The Consciousness Prior
- Stochastic Gradient Descent as Approximate Bayesian Inference
- Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder
- From Variational to Deterministic Autoencoders
- Coupled Generative Adversarial Networks
- Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
- Machine learning non-Markovian quantum dynamics
- IoT Malware Network Traffic Classification using Visual Representation and Deep Learning
- Conditional Variational Image Deraining
- A Deep Generative Model for Molecule Optimization via One Fragment Modification
- Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
- Diffusion Model-Based Image Editing: A Survey
- Roundtrip: A Deep Generative Neural Density Estimator
- Learning Disentangled Representations in the Imaging Domain
- The Conditional Entropy Bottleneck
- Machine learning with neural networks
- 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
- Deep learning of thermodynamics-aware reduced-order models from data
- Unsupervised Learning of 3D Structure from Images
- Deep Active Inference
- Hierarchical Implicit Models and Likelihood-Free Variational Inference
- Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space
- 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
- Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
- Information Constraints on Auto-Encoding Variational Bayes
- Attribute2Image: Conditional Image Generation from Visual Attributes
- Population-Based Black-Box Optimization for Biological Sequence Design
- Neural Predictor based Quantum Architecture Search
- Vector-quantized Image Modeling with Improved VQGAN
- Reversing the Irreversible: A Survey on Inverse Biometrics
- Adversarial Attacks Against Deep Generative Models on Data: A Survey
- Loss is its own Reward: Self-Supervision for Reinforcement Learning
- Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
- Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
- Learning to design from humans: Imitating human designers through deep learning
- Image Synthesis with a Single (Robust) Classifier
- Diagnosing and Enhancing VAE Models
- Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
- TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
- Deep Structural Causal Models for Tractable Counterfactual Inference
- DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal
- DIVA: Domain Invariant Variational Autoencoders
- Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
- Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification
- MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
- On the Quantum versus Classical Learnability of Discrete Distributions
- Deep Learning for Genomics: A Concise Overview
- PathVQA: 30000+ Questions for Medical Visual Question Answering
- Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
- Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset
- HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
- Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
- Low-Resource Knowledge-Grounded Dialogue Generation
- In Search of Lost Domain Generalization
- Random Feature Expansions for Deep Gaussian Processes
- An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era
- Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
- SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
- Learning Robust Representations via Multi-View Information Bottleneck
- Emotional Speech-Driven Animation with Content-Emotion Disentanglement
- Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
- Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
- How to Train Your Energy-Based Models
- Generalisation error in learning with random features and the hidden manifold model
- Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
- Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
- Unsupervised machine learning of topological phase transitions from experimental data
- Monte Carlo Gradient Estimation in Machine Learning
- Bayesian Bits: Unifying Quantization and Pruning
- HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
- Strategic Attentive Writer for Learning Macro-Actions
- Inference Suboptimality in Variational Autoencoders
- ChatPainter: Improving Text to Image Generation using Dialogue
- Overlearning Reveals Sensitive Attributes
- Copyright in Generative Deep Learning
- Machine Learning for Spatiotemporal Sequence Forecasting: A Survey
- Supervised Compression for Resource-Constrained Edge Computing Systems
- Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
- Learning Conditional Deformable Templates with Convolutional Networks
- Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
- Deep Survival Analysis
- T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography
- Bayesian Layers: A Module for Neural Network Uncertainty
- Machine learning-assisted design of material properties
- FSNet: An Identity-Aware Generative Model for Image-based Face Swapping
- Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
- Concrete Autoencoders for Differentiable Feature Selection and Reconstruction
- 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
- PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
- Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification
- A Graph to Graphs Framework for Retrosynthesis Prediction
- Optimizing Molecules using Efficient Queries from Property Evaluations
- Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
- 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
- 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
- Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
- Associative Learning Mechanism for Drug-Target Interaction Prediction
- Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization
- Structured Pruning of a BERT-based Question Answering Model
- Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
- Stochastic Variational Video Prediction
- Generating Images from Captions with Attention
- 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
- What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
- Factorizable Graph Convolutional Networks
- A Survey on Deep Learning for Skeleton-Based Human Animation
- A causal view of compositional zero-shot recognition
- Measuring and modeling the motor system with machine learning
- Variational Inference using Implicit Distributions
- Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
- Semantic Facial Expression Editing using Autoencoded Flow
- CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
- Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder
- Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
- A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
- Adversarial Network Embedding
- SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions
- Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and Privacy
- Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
- Adversarial Robustness as a Prior for Learned Representations
- Unrestricted Adversarial Examples via Semantic Manipulation
- Variational Deep Image Restoration
- A Deep Generative Model for Graph Layout
- Open Domain Event Extraction Using Neural Latent Variable Models
- Unsupervised Deep Learning for IoT Time Series
- Sliced Score Matching: A Scalable Approach to Density and Score Estimation
- Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
- Contracting Arbitrary Tensor Networks: General Approximate Algorithm and Applications in Graphical Models and Quantum Circuit Simulations
- Hypernetwork functional image representation
- PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
- Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space
- Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
- Fast differentiable DNA and protein sequence optimization for molecular design
- CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech
- A Framework for Interdomain and Multioutput Gaussian Processes
- VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
- Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
- DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data
- A review of radar-based nowcasting of precipitation and applicable machine learning techniques
- NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
- DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
- Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
- Stabilizing Generative Adversarial Networks: A Survey
- Machine Learning for Anomaly Detection in Particle Physics
- Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
- Implicit Weight Uncertainty in Neural Networks
- Content and Style Aware Generation of Text-line Images for Handwriting Recognition
- Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
- Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
- Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors
- Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
- Lifelong Teacher-Student Network Learning
- Deep Diffusion Models for Seismic Processing
- A Probabilistic Formulation of Unsupervised Text Style Transfer
- Variational Autoencoder with Arbitrary Conditioning
- On denoising autoencoders trained to minimise binary cross-entropy
- Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
- Variational Temporal Deep Generative Model for Radar HRRP Target Recognition
- Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data
- Intriguing Properties of Contrastive Losses
- Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
- Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
- ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
- Maximum Entropy Generators for Energy-Based Models
- Deep Temporal Sigmoid Belief Networks for Sequence Modeling
- A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods
- Adversarial Images for Variational Autoencoders
- NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
- Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
- PoNA: Pose-guided Non-local Attention for Human Pose Transfer
- FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchonized GANs
- Improving Outfit Recommendation with Co-supervision of Fashion Generation
- Classification Aware Neural Topic Model and its Application on a New COVID-19 Disinformation Corpus
- von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
- PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
- Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
- Controllable Invariance through Adversarial Feature Learning
- Pathwise Derivatives Beyond the Reparameterization Trick
- CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
- Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction
- FIGR: Few-shot Image Generation with Reptile
- Learning Implicit Fields for Generative Shape Modeling
- Dual Adversarial Auto-Encoders for Clustering
- Generalized Variational Inference: Three arguments for deriving new Posteriors
- Variational Bayes with Synthetic Likelihood
- Deep Factors for Forecasting
- Multi-modal Deep Analysis for Multimedia
- Conditional Flow Variational Autoencoders for Structured Sequence Prediction
- A joint model of unpaired data from scRNA-seq and spatial transcriptomics for imputing missing gene expression measurements
- Improving Generalization in Meta Reinforcement Learning using Learned Objectives
- Towards Zero-shot Sign Language Recognition
- Cardiac MRI Segmentation with Strong Anatomical Guarantees
- StructureNet: Hierarchical Graph Networks for 3D Shape Generation
- Reinforcement Learning through Active Inference
- Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm
- Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
- Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control
- Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priors
- Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
- LMQFormer: A Laplace-Prior-Guided Mask Query Transformer for Lightweight Snow Removal
- End-to-End Pixel-Based Deep Active Inference for Body Perception and Action
- A Perspective on Deep Learning for Molecular Modeling and Simulations
- Operator Variational Inference
- 6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning
- Small Sample Learning in Big Data Era
- A Joint Model for IT Operation Series Prediction and Anomaly Detection
- Artificial Intelligence in Glioma Imaging: Challenges and Advances
- Learning to Perform Physics Experiments via Deep Reinforcement Learning
- Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders
- Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
- Do Deep Generative Models Know What They Don't Know?
- Modeling Uncertainty with Hedged Instance Embedding
- Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
- Symbolic Pregression: Discovering Physical Laws from Distorted Video
- Learning Likelihoods with Conditional Normalizing Flows
- Lund jet images from generative and cycle-consistent adversarial networks
- Restricting the Flow: Information Bottlenecks for Attribution
- Adversarial-Residual-Coarse-Graining: Applying machine learning theory to systematic molecular coarse-graining
- 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
- Simulations meet Machine Learning in Structural Biology
- Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
- A topological encoding method for data-driven photonics inverse design
- Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
- Few-Shot Adaptation of Generative Adversarial Networks
- Affinity and Diversity: Quantifying Mechanisms of Data Augmentation
- Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
- A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning
- Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine
- 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
- Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation
- Constrained Bayesian Optimization for Automatic Chemical Design
- Disentangling Disentanglement in Variational Autoencoders
- Deferred Neural Rendering: Image Synthesis using Neural Textures
- Adaptive deep density approximation for Fokker-Planck equations
- Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
- Variational inference with a quantum computer
- Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation
- 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
- Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
- Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
- A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning
- Multi-Label Clinical Time-Series Generation via Conditional GAN
- PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
- The continuous Bernoulli: fixing a pervasive error in variational autoencoders
- Unsupervised Heterogeneous Coupling Learning for Categorical Representation
- A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
- The Gaussian equivalence of generative models for learning with shallow neural networks
- Structured Prediction of 3D Human Pose with Deep Neural Networks
- ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder
- Inference Networks for Sequential Monte Carlo in Graphical Models
- Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
- Online-compatible Unsupervised Non-resonant Anomaly Detection
- Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
- Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
- Disentangling Factors of Variation Using Few Labels
- Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
- FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
- L2LFlows: Generating High-Fidelity 3D Calorimeter Images
- Presenting Unbinned Differential Cross Section Results
- medigan: a Python library of pretrained generative models for medical image synthesis
- Robust in Practice: Adversarial Attacks on Quantum Machine Learning
- Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
- StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
- Distribution Matching in Variational Inference
- Generative Models of Visually Grounded Imagination
- Variational Sequential Monte Carlo
- IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
- ATISS: Autoregressive Transformers for Indoor Scene Synthesis
- Learning Beyond Human Expertise with Generative Models for Dental Restorations
- Learning Causal Semantic Representation for Out-of-Distribution Prediction
- Importance nested sampling with normalising flows
- Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model
- Boosting Variational Inference
- Maximum Likelihood Training of Score-Based Diffusion Models
- An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
- Fast Bayesian whole-brain fMRI analysis with spatial 3D priors
- The Free Energy Principle for Perception and Action: A Deep Learning Perspective
- DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup
- Semi-Supervised Variational Reasoning for Medical Dialogue Generation
- Normalizing Flows on Riemannian Manifolds
- 6GCVAE: Gated Convolutional Variational Autoencoder for IPv6 Target Generation
- A review of unsupervised learning in astronomy
- Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions
- Causality-based CTR Prediction using Graph Neural Networks
- Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection
- Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
- Generative 3D Part Assembly via Dynamic Graph Learning
- Practical Lossless Compression with Latent Variables using Bits Back Coding
- DeepSketchHair: Deep Sketch-based 3D Hair Modeling
- Causal Discovery in Physical Systems from Videos
- Lung Segmentation from Chest X-rays using Variational Data Imputation
- Gmail Smart Compose: Real-Time Assisted Writing
- Missing Data Imputation using Optimal Transport
- Robust Compressed Sensing MRI with Deep Generative Priors
- Universally Quantized Neural Compression
- Detection of Gravitational Waves Using Bayesian Neural Networks
- Adversarial Examples - A Complete Characterisation of the Phenomenon
- Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis
- SSD: A Unified Framework for Self-Supervised Outlier Detection
- Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework
- Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network
- Disentangling the independently controllable factors of variation by interacting with the world
- Speech enhancement with variational autoencoders and alpha-stable distributions
- A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systems
- Learning to Simulate High Energy Particle Collisions from Unlabeled Data
- Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
- Supervised and Semi-supervised Deep Probabilistic Models for Indoor Positioning Problems
- Probabilistic Binary Neural Networks
- Label-Consistent Backdoor Attacks
- Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation
- Learning protein conformational space by enforcing physics with convolutions and latent interpolations
- InfoBot: Transfer and Exploration via the Information Bottleneck
- A Deep Generative Model for Fragment-Based Molecule Generation
- A Deep Learning Algorithm for High-Dimensional Exploratory Item Factor Analysis
- Hierarchical Generative Modeling for Controllable Speech Synthesis
- Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
- Towards Precise and Accurate Calculations of Neutrinoless Double-Beta Decay: Project Scoping Workshop Report
- Generative Capacity of Probabilistic Protein Sequence Models
- The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
- Progressive Pose Attention Transfer for Person Image Generation
- E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
- Invertible generative models for inverse problems: mitigating representation error and dataset bias
- Solving Mixed Integer Programs Using Neural Networks
- Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts
- Diagnosing Concept Drift with Visual Analytics
- Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
- Data Generation as Sequential Decision Making
- Neural Adaptive Sequential Monte Carlo
- VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation
- Tackling Over-pruning in Variational Autoencoders
- On the Expressiveness of Approximate Inference in Bayesian Neural Networks
- Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
- Generative Neural Machine Translation
- Creativity and Machine Learning: A Survey
- GANimation: Anatomically-aware Facial Animation from a Single Image
- Generating Multivariate Load States Using a Conditional Variational Autoencoder
- Recommending Accurate and Diverse Items Using Bilateral Branch Network
- Generative Models for Low-Rank Video Representation and Reconstruction
- Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations
- Discrete Variational Autoencoders
- Robust Training of Vector Quantized Bottleneck Models
- On the Detection of Digital Face Manipulation
- SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
- High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks
- A Universal Music Translation Network
- From IC Layout to Die Photo: A CNN-Based Data-Driven Approach
- Language as a Latent Variable: Discrete Generative Models for Sentence Compression
- Predictive Collective Variable Discovery with Deep Bayesian Models
- Accounting for Variance in Machine Learning Benchmarks
- Computer-Aided Design as Language
- Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures
- MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization
- Generative Temporal Models with Memory
- Deep Gaussian Processes for Multi-fidelity Modeling
- A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the Small Data regime
- A Variational Perspective on Diffusion-Based Generative Models and Score Matching
- Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem
- Model-Augmented Actor-Critic: Backpropagating through Paths
- Topology of Learning in Artificial Neural Networks
- Physics-aware Reduced-order Modeling of Transonic Flow via -Variational Autoencoder
- NODLINK: An Online System for Fine-Grained APT Attack Detection and Investigation
- Variational Information Bottleneck for Effective Low-Resource Fine-Tuning
- Disentangled Representations for Short-Term and Long-Term Person Re-Identification
- Simple, Distributed, and Accelerated Probabilistic Programming
- Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
- Fixing a Broken ELBO
- Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAM
- AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
- A Benchmark of Medical Out of Distribution Detection
- Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties
- Adversarially Regularized Autoencoders
- Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
- DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
- Deep Amortized Inference for Probabilistic Programs
- End-to-end Learning of Driving Models from Large-scale Video Datasets
- AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild
- Copula Flows for Synthetic Data Generation
- On Disentangled Representations Learned From Correlated Data
- A deep-learning search for technosignatures of 820 nearby stars
- Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network
- From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting
- Unsupervised Model Selection for Variational Disentangled Representation Learning
- Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
- Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring
- LAFITE: Towards Language-Free Training for Text-to-Image Generation
- Unifying Multimodal Transformer for Bi-directional Image and Text Generation
- Conditional Gaussian Distribution Learning for Open Set Recognition
- Stochastic Optimization of Sorting Networks via Continuous Relaxations
- SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
- Training Gaussian Boson Sampling Distributions
- Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
- Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
- DDTCDR: Deep Dual Transfer Cross Domain Recommendation
- Adversarial Symmetric Variational Autoencoder
- Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets
- Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging
- Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
- Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
- RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation
- Statistical Inference for Generative Models with Maximum Mean Discrepancy
- CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
- Contrastive Learning with Stronger Augmentations
- Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
- Stochastic Backpropagation through Mixture Density Distributions
- UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
- t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning
- Graphite: Iterative Generative Modeling of Graphs
- Conditional Generative Moment-Matching Networks
- Simple and Effective VAE Training with Calibrated Decoders
- Can multi-label classification networks know what they don't know?
- Quaternion Generative Adversarial Networks
- Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning
- RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
- Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System
- Deep Semantic-Visual Alignment for Zero-Shot Remote Sensing Image Scene Classification
- Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras
- Generating Images Part by Part with Composite Generative Adversarial Networks
- Cross-Modal Contrastive Learning for Text-to-Image Generation
- Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges
- Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
- Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
- VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detection
- Boundless: Generative Adversarial Networks for Image Extension
- Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks
- Predicting Deeper into the Future of Semantic Segmentation
- Efficient inference in occlusion-aware generative models of images
- Deep Conversational Recommender in Travel
- CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
- Multi-view Generative Adversarial Networks
- Semi-blind source separation with multichannel variational autoencoder
- Generating Sentences by Editing Prototypes
- Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
- Adversarial Distributional Training for Robust Deep Learning
- Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
- Variational Neural Machine Translation
- Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
- Multi-fidelity physics constrained neural networks for dynamical systems
- Semi-Amortized Variational Autoencoders
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- A new interpretable unsupervised anomaly detection method based on residual explanation
- Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
- Canonical Correlation Analysis (CCA) Based Multi-View Learning: An Overview
- From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
- Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
- Deep Unfolding with Normalizing Flow Priors for Inverse Problems
- On generative models as the basis for digital twins
- Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
- A Tutorial on Deep Latent Variable Models of Natural Language
- Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
- A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
- Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
- Entity Abstraction in Visual Model-Based Reinforcement Learning
- Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
- Design by adaptive sampling
- DALLE-URBAN: Capturing the urban design expertise of large text to image transformers
- Inductive Representation Learning on Temporal Graphs
- Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
- LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
- Challenges in Disentangling Independent Factors of Variation
- Uncertainty-Aware Attention for Reliable Interpretation and Prediction
- Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
- Safer Classification by Synthesis
- Revealing quantum chaos with machine learning
- Attentive Semantic Exploring for Manipulated Face Detection
- Deep Music Analogy Via Latent Representation Disentanglement
- Exploring particle dynamics during self-organization processes via rotationally invariant latent representations
- Quantum device fine-tuning using unsupervised embedding learning
- Data Augmentation for End-to-end Code-switching Speech Recognition
- Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
- Graph Residual Flow for Molecular Graph Generation
- Solving Bayesian Inverse Problems via Variational Autoencoders
- Adversarial Learning with Local Coordinate Coding
- Airline Passenger Name Record Generation using Generative Adversarial Networks
- Conditional Generation of Medical Images via Disentangled Adversarial Inference
- On the Evaluation of Conditional GANs
- Edge-based sequential graph generation with recurrent neural networks
- A spectral surrogate model for stochastic simulators computed from trajectory samples
- Robust Out-of-distribution Detection for Neural Networks
- Differentially Private Data Generative Models
- A Theory of Usable Information Under Computational Constraints
- Improving Variational Encoder-Decoders in Dialogue Generation
- Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
- Overfitting for Fun and Profit: Instance-Adaptive Data Compression
- Using latent space regression to analyze and leverage compositionality in GANs
- MuProp: Unbiased Backpropagation for Stochastic Neural Networks
- Multivariate Time-series Anomaly Detection via Graph Attention Network
- DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
- GraphDF: A Discrete Flow Model for Molecular Graph Generation
- VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
- Educating Text Autoencoders: Latent Representation Guidance via Denoising
- Active Learning: Problem Settings and Recent Developments
- Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
- Adversarial Autoencoders with Constant-Curvature Latent Manifolds
- Unsupervised Pathology Detection: A Deep Dive Into the State of the Art
- Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
- Probabilistic Autoencoder
- Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables
- Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks
- Information Maximization Clustering via Multi-View Self-Labelling
- GP-VAE: Deep Probabilistic Time Series Imputation
- FitVid: Overfitting in Pixel-Level Video Prediction
- Focal Frequency Loss for Image Reconstruction and Synthesis
- An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
- Variational Bayesian Monte Carlo with Noisy Likelihoods
- ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis
- Discrete and continuous representations and processing in deep learning: Looking forward
- Generating Comprehensive Lithium Battery Charging Data with Generative AI
- Lossless Image Compression through Super-Resolution
- Deep Semi-Supervised Anomaly Detection
- Structured Attention for Unsupervised Dialogue Structure Induction
- A Study of the Generalizability of Self-Supervised Representations
- SDM-NET: Deep Generative Network for Structured Deformable Mesh
- Artemis: Articulated Neural Pets with Appearance and Motion synthesis
- Thermal experiments for fractured rock characterization: theoretical analysis and inverse modeling
- Flash Photography for Data-Driven Hidden Scene Recovery
- Convolutional Generation of Textured 3D Meshes
- Generative Modeling and Inverse Imaging of Cardiac Transmembrane Potential
- Deep Synthetic Minority Over-Sampling Technique
- Diffusion Variational Autoencoders
- GenNI: Human-AI Collaboration for Data-Backed Text Generation
- Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
- State Space LSTM Models with Particle MCMC Inference
- FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis
- Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition
- Mask-aware Photorealistic Face Attribute Manipulation
- Bayesian model and dimension reduction for uncertainty propagation: applications in random media
- Amortized Variational Inference: A Systematic Review
- Towards Safe Machine Learning for CPS: Infer Uncertainty from Training Data
- Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections
- Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder
- Physics-informed GANs for Coastal Flood Visualization
- Toward a Better Monitoring Statistic for Profile Monitoring via Variational Autoencoders
- The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
- Model-Based Policy Search Using Monte Carlo Gradient Estimation with Real Systems Application
- Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows
- Developing Bug-Free Machine Learning Systems With Formal Mathematics
- Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
- Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
- Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
- Representation, learning, and planning algorithms for geometric task and motion planning
- 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
- Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
- Semi-supervised source localization with deep generative modeling
- Chainer: A Deep Learning Framework for Accelerating the Research Cycle
- Attentive Neural Processes
- The Generalized Reparameterization Gradient
- Reweighted Wake-Sleep
- Neural Spline Flows
- A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
- Tighter Variational Bounds are Not Necessarily Better
- Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions
- Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation
- Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models
- RWR-GAE: Random Walk Regularization for Graph Auto Encoders
- GAR: An efficient and scalable Graph-based Activity Regularization for semi-supervised learning
- Modeling documents with Generative Adversarial Networks
- Deep Reinforcement Learning amidst Lifelong Non-Stationarity
- DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
- Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
- Face Image Quality Assessment: A Literature Survey
- Are Generative Classifiers More Robust to Adversarial Attacks?
- Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective
- EFTofLSS meets simulation-based inference: from biased tracers
- Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
- The Dynamic Embedded Topic Model
- Unsupervised State Representation Learning in Atari
- Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
- Neural Manifold Ordinary Differential Equations
- Mathematical Models of Overparameterized Neural Networks
- Boosting Neural Image Compression for Machines Using Latent Space Masking
- Solving time dependent Fokker-Planck equations via temporal normalizing flow
- Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis
- PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
- Learning Image Representations by Completing Damaged Jigsaw Puzzles
- Exposing Previously Undetectable Faults in Deep Neural Networks
- Scalable and Efficient Neural Speech Coding: A Hybrid Design
- Approximate Inference with Amortised MCMC
- Capturing Dynamics of Information Diffusion in SNS: A Survey of Methodology and Techniques
- Flowfield prediction of airfoil off-design conditions based on a modified variational autoencoder
- Diverse Image Captioning with Context-Object Split Latent Spaces
- McGan: Mean and Covariance Feature Matching GAN
- Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming
- DP-BART for Privatized Text Rewriting under Local Differential Privacy
- Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
- Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Models
- The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces
- Black-box Adversarial Attacks with Bayesian Optimization
- Focused Hierarchical RNNs for Conditional Sequence Processing
- Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
- Advances in Variational Inference
- 3DMolNet: A Generative Network for Molecular Structures
- Black-box Variational Inference for Stochastic Differential Equations
- Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
- Robust Locally-Linear Controllable Embedding
- Nonlinear Invariant Risk Minimization: A Causal Approach
- Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
- Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
- Hierarchical Quantized Autoencoders
- Netboost: Boosting-supported network analysis improves high-dimensional omics prediction in acute myeloid leukemia and Huntington's disease
- High-resolution Deep Convolutional Generative Adversarial Networks
- Operationally meaningful representations of physical systems in neural networks
- Self-supervised visual learning in the low-data regime: a comparative evaluation
- Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model
- Turbulence forecasting via Neural ODE
- Inverse Transport Networks
- Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
- Learning FRAME Models Using CNN Filters
- Perfect density models cannot guarantee anomaly detection
- Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
- Variational Bayesian Approximation of Inverse Problems using Sparse Precision Matrices
- Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
- Hierarchical Autoregressive Image Models with Auxiliary Decoders
- A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
- Learning to Fly via Deep Model-Based Reinforcement Learning
- Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks
- Creativity in the era of artificial intelligence
- Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
- Improving black-box optimization in VAE latent space using decoder uncertainty
- Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks
- DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning
- Gradient Estimation with Stochastic Softmax Tricks
- Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
- Mastering Atari with Discrete World Models
- Transport Analysis of Infinitely Deep Neural Network
- Fairness without the sensitive attribute via Causal Variational Autoencoder
- Generalizing Face Forgery Detection with High-frequency Features
- Regularizing Deep Networks with Semantic Data Augmentation
- Automatic Differentiable Monte Carlo: Theory and Application
- IGNOR: Image-guided Neural Object Rendering
- Learning with hidden variables
- Information bottleneck through variational glasses
- Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm
- Fast mesh denoising with data driven normal filtering using deep variational autoencoders
- A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
- Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
- Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
- Multi-Time Attention Networks for Irregularly Sampled Time Series
- Decision-Making with Auto-Encoding Variational Bayes
- Learning Implicit Priors for Motion Optimization
- Bayesian policy selection using active inference
- Max-margin Deep Generative Models
- Independent Prototype Propagation for Zero-Shot Compositionality
- A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
- Data Augmentation and Classification of Sea-Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN
- Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
- Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
- Learning to Traverse Latent Spaces for Musical Score Inpainting
- MetaPix: Few-Shot Video Retargeting
- The Deep Kernelized Autoencoder
- Iterative energy-based projection on a normal data manifold for anomaly localization
- Variational Template Machine for Data-to-Text Generation
- Multi-class Gaussian Process Classification with Noisy Inputs
- Controllable Level Blending between Games using Variational Autoencoders
- Permutation Invariant Graph Generation via Score-Based Generative Modeling
- Training Deep Learning Based Denoisers without Ground Truth Data
- Relevance Factor VAE: Learning and Identifying Disentangled Factors
- Learning to Generate Chairs, Tables and Cars with Convolutional Networks
- SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
- Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning
- How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?
- All You Need is a Good Functional Prior for Bayesian Deep Learning
- Block Neural Autoregressive Flow
- Recent advances in deep learning theory
- Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model
- Probing transfer learning with a model of synthetic correlated datasets
- Wavelet Transform-assisted Adaptive Generative Modeling for Colorization
- Focus on Impact: Indoor Exploration with Intrinsic Motivation
- Efficient Learning of the Parameters of Non-Linear Models using Differentiable Resampling in Particle Filters
- Transitive Invariance for Self-supervised Visual Representation Learning
- Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck
- CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy
- Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective
- Generative Multi-Form Bayesian Optimization
- Generative Slate Recommendation with Reinforcement Learning
- Action Capsules: Human Skeleton Action Recognition
- INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
- Brain MRI Tumor Segmentation with Adversarial Networks
- Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness
- A Memory System of a Robot Cognitive Architecture and its Implementation in ArmarX
- A Model to Search for Synthesizable Molecules
- Causal datasheet: An approximate guide to practically assess Bayesian networks in the real world
- A practical tutorial on Variational Bayes
- Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA
- Learning to Assist Drone Landings
- Extendable and invertible manifold learning with geometry regularized autoencoders
- PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
- Hebbian Semi-Supervised Learning in a Sample Efficiency Setting
- Elucidating proximity magnetism through polarized neutron reflectometry and machine learning
- Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders
- A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series
- Offline Reinforcement Learning with Reverse Model-based Imagination
- Visualising energy landscapes through manifold learning
- Bandwidth Extension on Raw Audio via Generative Adversarial Networks
- Esophageal virtual disease landscape using mechanics-informed machine learning
- 3D Part Assembly Generation with Instance Encoded Transformer
- Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
- Locality and compositionality in zero-shot learning
- Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
- Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
- Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
- On Counterfactual Explanations under Predictive Multiplicity
- AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models
- Multiple Causal Inference with Latent Confounding
- Towards causal generative scene models via competition of experts
- SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
- A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation
- not-MIWAE: Deep Generative Modelling with Missing not at Random Data
- A Comparative Study of Self-supervised Speech Representation Based Voice Conversion
- Single Episode Policy Transfer in Reinforcement Learning
- Statistical and Topological Properties of Sliced Probability Divergences
- Disentangled Person Image Generation
- Image Clustering using an Augmented Generative Adversarial Network and Information Maximization
- TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
- Synthesizing Filamentary Structured Images with GANs
- TherML: Thermodynamics of Machine Learning
- In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains
- Using machine learning to parametrize postmerger signals from binary neutron stars
- A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
- Functional PCA and Deep Neural Networks-based Bayesian Inverse Uncertainty Quantification with Transient Experimental Data
- Backdoor Attack through Frequency Domain
- A Less Biased Evaluation of Out-of-distribution Sample Detectors
- Learning latent state representation for speeding up exploration
- Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion
- Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model
- Expressive TTS Training with Frame and Style Reconstruction Loss
- Learning Interpretable Representation for Controllable Polyphonic Music Generation
- BOSS: Bayesian Optimization over String Spaces
- An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
- Generative Learning of the Solution of Parametric Partial Differential Equations Using Guided Diffusion Models and Virtual Observations
- Bayesian Renormalization
- Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
- Uncertainty Quantification with Generative Models
- Learning Wake-Sleep Recurrent Attention Models
- Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencoder
- Responsible Disclosure of Generative Models Using Scalable Fingerprinting
- VFlow: More Expressive Generative Flows with Variational Data Augmentation
- Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
- Latent Convolutional Models
- Style-transfer GANs for bridging the domain gap in synthetic pose estimator training
- Weakly-Supervised Action Localization by Generative Attention Modeling
- Adversarial Attacks on Variational Autoencoders
- KATE: K-Competitive Autoencoder for Text
- Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
- Perpetual Motion: Generating Unbounded Human Motion
- Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces
- Anomaly Detection with Score Distribution Discrimination
- Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks
- Variational Attention for Sequence-to-Sequence Models
- Model Inversion Networks for Model-Based Optimization
- Audio query-based music source separation
- Adversarial Variational Optimization of Non-Differentiable Simulators
- Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
- A Deep Generative Model of Speech Complex Spectrograms
- Towards Visually Explaining Variational Autoencoders
- Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients
- Revealing Fundamental Physics from the Daya Bay Neutrino Experiment using Deep Neural Networks
- Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis
- Score-Based Generative Models for PET Image Reconstruction
- Deep Visual Foresight for Planning Robot Motion
- Fast Second-Order Stochastic Backpropagation for Variational Inference
- Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
- Bi-fidelity Variational Auto-encoder for Uncertainty Quantification
- View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
- Deep Generative Video Compression
- Neural Autoregressive Distribution Estimation
- Extending Unsupervised Neural Image Compression With Supervised Multitask Learning
- Learning Disentangled Representations with Reference-Based Variational Autoencoders
- Wasserstein Dependency Measure for Representation Learning
- Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
- Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
- Multi-resolution Multi-task Gaussian Processes
- Stroke-based sketched symbol reconstruction and segmentation
- CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
- On the Latent Space of Wasserstein Auto-Encoders
- See, Hear, Explore: Curiosity via Audio-Visual Association
- Merlion: A Machine Learning Library for Time Series
- A survey of machine learning-based physics event generation
- A RAD approach to deep mixture models
- Early Inference in Energy-Based Models Approximates Back-Propagation
- Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics
- A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research
- Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective
- A generative model for molecule generation based on chemical reaction trees
- Sparse Graphical Memory for Robust Planning
- Learning a Deep ConvNet for Multi-label Classification with Partial Labels
- Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
- Deep Factors with Gaussian Processes for Forecasting
- Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression
- Deep reinforcement learning for smart calibration of radio telescopes
- Structured Object-Aware Physics Prediction for Video Modeling and Planning
- First results of the glitching pulsars monitoring program at the Argentine Institute of Radioastronomy
- Empirically Measuring Transfer Distance for System Design and Operation
- Deep Directed Generative Autoencoders
- Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
- White Paper Machine Learning in Certified Systems
- Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization
- A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
- Learnable Explicit Density for Continuous Latent Space and Variational Inference
- A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
- Dimensionality Reduction for Categorical Data
- RelationNet2: Deep Comparison Columns for Few-Shot Learning
- DONet: Dual Objective Networks for Skin Lesion Segmentation
- Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
- Learning Global Pairwise Interactions with Bayesian Neural Networks
- Continual State Representation Learning for Reinforcement Learning using Generative Replay
- Hierarchical Variational Models
- Auto-Encoding Knockoff Generator for FDR Controlled Variable Selection
- Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series
- Designing Perceptual Puzzles by Differentiating Probabilistic Programs
- Hierarchical Adversarially Learned Inference
- Exploiting Persona Information for Diverse Generation of Conversational Responses
- Style Generator Inversion for Image Enhancement and Animation
- Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adversarial Triplet Loss
- Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems
- Debiased Contrastive Learning
- Defending Against Adversarial Examples with K-Nearest Neighbor
- Gaussian variational approximation for high-dimensional state space models
- Behavior Self-Organization Supports Task Inference for Continual Robot Learning
- Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
- Minibatch optimal transport distances; analysis and applications
- Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
- Desiderata for Representation Learning: A Causal Perspective
- Disentangling by Partitioning: A Representation Learning Framework for Multimodal Sensory Data
- Deeptime: a Python library for machine learning dynamical models from time series data
- Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0
- Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
- Reconstruction Student with Attention for Student-Teacher Pyramid Matching
- Knowledge Cross-Distillation for Membership Privacy
- A Spectral Regularizer for Unsupervised Disentanglement
- Deep Learning in Mining Biological Data
- Bayesian neural networks for weak solution of PDEs with uncertainty quantification
- Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect
- Stochastic Normalizing Flows
- Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
- Fundamental problems in statistical physics XIV: Lecture on Machine Learning
- Symmetric Variational Autoencoder and Connections to Adversarial Learning
- Causal Discovery from Incomplete Data: A Deep Learning Approach
- Phase Transitions for the Information Bottleneck in Representation Learning
- Mixing autoencoder with classifier: conceptual data visualization
- A Non-Parametric Test to Detect Data-Copying in Generative Models
- Deep Gaussian Process-Based Bayesian Inference for Contaminant Source Localization
- Solving PDE-constrained Control Problems Using Operator Learning
- Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
- Disentangled Recurrent Wasserstein Autoencoder
- A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
- Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
- Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data
- Differential Anomaly Detection for Facial Images
- Energy-based Models for Video Anomaly Detection
- Neural Augmentation of Kalman Filter with Hypernetwork for Channel Tracking
- Towards meaningful physics from generative models
- Modeling motor control in continuous-time Active Inference: a survey
- Cramer-Wold AutoEncoder
- Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
- A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
- Disentangling User Interest and Conformity for Recommendation with Causal Embedding
- Learning a Structural Causal Model for Intuition Reasoning in Conversation
- Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
- Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
- Autofocused oracles for model-based design
- Tensorial Mixture Models
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement
- On the Effectiveness of Least Squares Generative Adversarial Networks
- Learning Discrete Distributions by Dequantization
- Zero-shot Domain Adaptation without Domain Semantic Descriptors
- NAOMI: Non-Autoregressive Multiresolution Sequence Imputation
- A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
- Deep Predictive Policy Training using Reinforcement Learning
- Unsupervised Learning of Video Representations via Dense Trajectory Clustering
- Patterns for Learning with Side Information
- Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition
- Graph Generation with Variational Recurrent Neural Network
- A case for new neural network smoothness constraints
- Scalable Gaussian Process Variational Autoencoders
- Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
- The Power Spherical distribution
- 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
- 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
- S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
- Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
- GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
- Probabilistic dose prediction using mixture density networks for automated radiation therapy treatment planning
- AliGraph: A Comprehensive Graph Neural Network Platform
- Risk-Averse Offline Reinforcement Learning
- Semi-Supervised Domain Generalization with Stochastic StyleMatch
- Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms
- Deep Generative Models for Distribution-Preserving Lossy Compression
- Fast uncertainty quantification of reservoir simulation with variational U-Net
- Image Generation From Small Datasets via Batch Statistics Adaptation
- Unsupervised Knowledge-Transfer for Learned Image Reconstruction
- Generative causal explanations of black-box classifiers
- Spatial Uncertainty Sampling for End-to-End Control
- Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)
- Incomplete Graph Representation and Learning via Partial Graph Neural Networks
- AnchorGAE: General Data Clustering via Bipartite Graph Convolution
- Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
- Variational Autoencoders with Normalizing Flow Decoders
- Artificial Intelligence and Dimensionality Reduction: Tools for approaching future communications
- Electra: Conditional Generative Model based Predicate-Aware Query Approximation
- Consistent Generative Query Networks
- Online Deep Learning from Doubly-Streaming Data
- A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
- Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition
- A Tutorial on VAEs: From Bayes' Rule to Lossless Compression
- Bidirectional Helmholtz Machines
- Information Dropout: Learning Optimal Representations Through Noisy Computation
- The Six Fronts of the Generative Adversarial Networks
- Contextual Imagined Goals for Self-Supervised Robotic Learning
- A Probabilistic Framework for Deep Learning
- A Semantic-based Medical Image Fusion Approach
- PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design
- D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection
- Survival Function Matching for Calibrated Time-to-Event Predictions
- Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing
- Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent
- A Mathematical Introduction to Generative Adversarial Nets (GAN)
- Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
- Autoencoding Variational Autoencoder
- Auto-Differentiating Linear Algebra
- Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
- Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
- When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes
- LayoutVAE: Stochastic Scene Layout Generation From a Label Set
- A graph-based probabilistic geometric deep learning framework with online enforcement of physical constraints to predict the criticality of defects in porous materials
- ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models
- Learning to Generate with Memory
- Online Continual Learning via the Knowledge Invariant and Spread-out Properties
- High-Precision Inversion of Dynamic Radiography Using Hydrodynamic Features
- Unsupervised Word Segmentation from Speech with Attention
- Overdispersed Black-Box Variational Inference
- Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
- Stochastic Deep Koopman Model for Quality Propagation Analysis in Multistage Manufacturing Systems
- Bridging the gap between paired and unpaired medical image translation
- Calibrating Deep Convolutional Gaussian Processes
- Contrastively Disentangled Sequential Variational Autoencoder
- Intent Disentanglement and Feature Self-supervision for Novel Recommendation
- Perceptual Generative Autoencoders
- Analyzing drop coalescence in microfluidic device with a deep learning generative model
- Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
- A Short Survey On Memory Based Reinforcement Learning
- Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers
- Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
- Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser
- Dialogue State Induction Using Neural Latent Variable Models
- Graph Learning Network: A Structure Learning Algorithm
- Deep learning based Meta-modeling for Multi-objective Technology Optimization of Electrical Machines
- Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
- Zero-Shot Recommender Systems
- Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems
- DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networks
- Accelerating Bayesian microseismic event location with deep learning
- Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
- Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
- Exploring Bias in GAN-based Data Augmentation for Small Samples
- RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior
- iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling
- You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
- Characterization and Generation of 3D Realistic Geological Particles with Metaball Descriptor based on X-Ray Computed Tomography
- Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
- Learning 3D Dense Correspondence via Canonical Point Autoencoder
- TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
- Hidden Talents of the Variational Autoencoder
- Learning Mesh Representations via Binary Space Partitioning Tree Networks
- Reliable training and estimation of variance networks
- Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search
- Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
- Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
- Adaptive sequential Monte Carlo for posterior inference and model selection among complex geological priors
- Deep-learning-based reduced-order modeling for subsurface flow simulation
- A likelihood approach to nonparametric estimation of a singular distribution using deep generative models
- Unsupervised anomaly localization using VAE and beta-VAE
- Effect of The Latent Structure on Clustering with GANs
- Novelty Detection Via Blurring
- Deep Amortized Clustering
- Exponential Family Estimation via Adversarial Dynamics Embedding
- Energy-based models for atomic-resolution protein conformations
- Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation
- Interference Motion Removal for Doppler Radar Vital Sign Detection Using Variational Encoder-Decoder Neural Network
- PLAS: Latent Action Space for Offline Reinforcement Learning
- A PCA-like Autoencoder
- Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation
- Maximizing Mutual Information for Tacotron
- Embedded out-of-distribution detection on an autonomous robot platform
- Latent Translation: Crossing Modalities by Bridging Generative Models
- Learning Pose-invariant 3D Object Reconstruction from Single-view Images
- Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications
- Task Specific Adversarial Cost Function
- Smoothing Methods for Automatic Differentiation Across Conditional Branches
- Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
- Generative Models as Distributions of Functions
- Active Image Synthesis for Efficient Labeling
- f-Divergence Variational Inference
- Generating unseen complex scenes: are we there yet?
- Categorical Normalizing Flows via Continuous Transformations
- MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
- Continual Learning in Recurrent Neural Networks
- Preventing Posterior Collapse with delta-VAEs
- The stochastic digital human is now enrolling for in silico imaging trials -- Methods and tools for generating digital cohorts
- A probabilistic deep learning model of inter-fraction anatomical variations in radiotherapy
- Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19
- A Generative Node-attribute Network Model for Detecting Generalized Structure
- Causal Reasoning in Software Quality Assurance: A Systematic Review
- Towards Asteroid Detection in Microlensing Surveys with Deep Learning
- Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
- Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding
- Unified Adversarial Invariance
- Geodesic Clustering in Deep Generative Models
- Discriminative Transformation Learning for Fuzzy Sparse Subspace Clustering
- Dense Intrinsic Appearance Flow for Human Pose Transfer
- Distance-Based Learning from Errors for Confidence Calibration
- Class-Conditional VAE-GAN for Local-Ancestry Simulation
- X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
- Generalization Properties of Optimal Transport GANs with Latent Distribution Learning
- Generative Adversarial Zero-shot Learning via Knowledge Graphs
- Understanding Overparameterization in Generative Adversarial Networks
- Clockwork Variational Autoencoders
- Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians
- FREE: Feature Refinement for Generalized Zero-Shot Learning
- Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble
- Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective
- Generating unrepresented proportions of geological facies using Generative Adversarial Networks
- Variational Laplace Autoencoders
- Diverse Multimedia Layout Generation with Multi Choice Learning
- Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
- 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
- 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
- Classification and reconstruction of optical quantum states with deep neural networks
- 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
- Grasping Field: Learning Implicit Representations for Human Grasps
- Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
- Shapley explainability on the data manifold
- Markovian Score Climbing: Variational Inference with KL(p||q)
- A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
- Treatment effect estimation with disentangled latent factors
- SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
- A Meta-Learning Framework for Generalized Zero-Shot Learning
- A Variational Bayes Approach to Adaptive Radio Tomography
- Learning-Aided Physical Layer Attacks Against Multicarrier Communications in IoT
- Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior
- Streaming Variational Monte Carlo
- Bounded Rational Decision-Making with Adaptive Neural Network Priors
- Jointly Deep Multi-View Learning for Clustering Analysis
- Invariant Representations from Adversarially Censored Autoencoders
- Truncated Variational Expectation Maximization
- The Variational Gaussian Process
- Big Learning with Bayesian Methods
- Modular Generative Adversarial Networks
- Interactive Image Manipulation with Natural Language Instruction Commands
- Dirichlet Graph Variational Autoencoder
- Scalable Bayesian Inverse Reinforcement Learning
- Behavior From the Void: Unsupervised Active Pre-Training
- PDE-Driven Spatiotemporal Disentanglement
- Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
- Minimum Width for Universal Approximation
- Explaining Visual Models by Causal Attribution
- Calibration of Model Uncertainty for Dropout Variational Inference
- Understanding Instance-based Interpretability of Variational Auto-Encoders
- Signal retrieval with measurement system knowledge using variational generative model
- Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks
- Learning Compositional Radiance Fields of Dynamic Human Heads
- Learning document embeddings along with their uncertainties
- High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
- Sparsely Activated Networks
- Learning to Learn with Variational Information Bottleneck for Domain Generalization
- Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
- Latent Representation in Human-Robot Interaction with Explicit Consideration of Periodic Dynamics
- Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling
- Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
- Contextual Dropout: An Efficient Sample-Dependent Dropout Module
- Unsupervised Discovery of 3D Physical Objects from Video
- Using Visual Anomaly Detection for Task Execution Monitoring
- A Physical Model for Microstructural Characterization and Segmentation of 3D Tomography Data
- Early-Phase Performance-Driven Design using Generative Models
- ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description
- Reweighted Expectation Maximization
- CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
- Deep learning insights into cosmological structure formation
- Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration
- Leveraging exploration in off-policy algorithms via normalizing flows
- Emulating Sunyaev-Zeldovich Images of Galaxy Clusters using Auto-Encoders
- Predictive Uncertainty Quantification with Compound Density Networks
- Representation Transfer for Differentially Private Drug Sensitivity Prediction
- Posterior inference unchained with EL_2O
- CompILE: Compositional Imitation Learning and Execution
- Sparsity in Variational Autoencoders
- ITENE: Intrinsic Transfer Entropy Neural Estimator
- Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
- Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders
- Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias
- LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
- Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
- Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning
- Bayesian Neural Networks for Reversible Steganography
- Normalizing flows as an enhanced sampling method for atomistic supercooled liquids
- Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems
- COIL: Constrained Optimization in Learned Latent Space: Learning Representations for Valid Solutions
- Variational Recurrent Neural Machine Translation
- Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning
- Learning and controlling the source-filter representation of speech with a variational autoencoder
- Primal-Dual Wasserstein GAN
- Unsupervised learning for concept detection in medical images: a comparative analysis
- Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations
- Semi-Supervised Generation with Cluster-aware Generative Models
- Identification of Gaussian Process State Space Models
- Cascaded Text Generation with Markov Transformers
- Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement
- Data Consistent Deep Rigid MRI Motion Correction
- 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
- Generative Graph Convolutional Network for Growing Graphs
- Feature Unlearning for Pre-trained GANs and VAEs
- LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
- A Tutorial on Sparse Gaussian Processes and Variational Inference
- Statistics of Deep Generated Images
- Variational AutoEncoder For Regression: Application to Brain Aging Analysis
- From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends
- VaPar Synth -- A Variational Parametric Model for Audio Synthesis
- Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
- Hyperbolic Deep Neural Networks: A Survey
- Densely connected normalizing flows
- Gradients as Features for Deep Representation Learning
- The continuous categorical: a novel simplex-valued exponential family
- Smoothed Action Value Functions for Learning Gaussian Policies
- On the Transfer of Disentangled Representations in Realistic Settings
- Robust Errant Beam Prognostics with Conditional Modeling for Particle Accelerators
- Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
- Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systems
- Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
- VAEs in the Presence of Missing Data
- Learning Post-Hoc Causal Explanations for Recommendation
- Leveraging the Exact Likelihood of Deep Latent Variable Models
- 3D Human Motion Estimation via Motion Compression and Refinement
- On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
- Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks
- StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
- TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
- Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction
- Variable-rate discrete representation learning
- Guided Variational Autoencoder for Disentanglement Learning
- Semantics Disentangling for Generalized Zero-Shot Learning
- Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set
- Improving Unsupervised Domain Adaptation with Variational Information Bottleneck
- Exchangeable Neural ODE for Set Modeling
- Deep Active Inference for Autonomous Robot Navigation
- Reducing Magnetic Resonance Image Spacing by Learning Without Ground-Truth
- Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
- Learning to Predict Explainable Plots for Neural Story Generation
- Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
- Learning Disentangled Representations via Mutual Information Estimation
- Source Separation with Deep Generative Priors
- Learning to Synthesize Programs as Interpretable and Generalizable Policies
- Neural Rendering and Reenactment of Human Actor Videos
- TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
- Flow-Grounded Spatial-Temporal Video Prediction from Still Images
- Unsupervised Anomaly Detection for X-Ray Images
- Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
- Integer Discrete Flows and Lossless Compression
- Isometric Autoencoders
- Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums
- Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections
- Time Perception Machine: Temporal Point Processes for the When, Where and What of Activity Prediction
- Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models
- Encoders and Ensembles for Task-Free Continual Learning
- Functional Generative Design: An Evolutionary Approach to 3D-Printing
- Dense Uncertainty Estimation
- Pose Guided Human Video Generation
- Stochastic Prototype Embeddings
- MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
- Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
- A Deep Generative Model for Reordering Adjacency Matrices
- Unconstrained Monotonic Neural Networks
- Vision-based Navigation of Unmanned Aerial Vehicles in Orchards: An Imitation Learning Approach
- Causal Discovery with Cascade Nonlinear Additive Noise Models
- Stateful Detection of Model Extraction Attacks
- Manifold Modeling in Embedded Space: A Perspective for Interpreting Deep Image Prior
- Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
- Emerging Directions in Geophysical Inversion
- Counterfactual Reasoning for Fair Clinical Risk Prediction
- Multi-Agent Reinforcement Learning with Multi-Step Generative Models
- Variational Neural Discourse Relation Recognizer
- Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement
- Tractable Regularization of Probabilistic Circuits
- Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction
- VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
- A Contrastive Learning Approach for Training Variational Autoencoder Priors
- Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning
- Generative Neurosymbolic Machines
- Associative Adversarial Networks
- InfoColorizer: Interactive Recommendation of Color Palettes for Infographics
- Evaluating representations by the complexity of learning low-loss predictors
- SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System
- Autoencoding sensory substitution
- Two Methods For Wild Variational Inference
- Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction
- On the Necessity and Effectiveness of Learning the Prior of Variational Auto-Encoder
- Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative
- MA-VAE: Multi-head Attention-based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-series Applied to Automotive Endurance Powertrain Testing
- Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasets
- Using RGB Image as Visual Input for Mapless Robot Navigation
- Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
- Information Maximizing Visual Question Generation
- SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
- Identification of Rare Cortical Folding Patterns using Unsupervised Deep Learning
- Estimation with Low-Rank Time-Frequency Synthesis Models
- Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN
- Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow
- Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders
- ProBO: Versatile Bayesian Optimization Using Any Probabilistic Programming Language
- Separable Shape Tensors for Aerodynamic Design
- Generative Design of Physical Objects using Modular Framework
- Reparameterization Gradient for Non-differentiable Models
- PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference
- Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
- How reparametrization trick broke differentially-private text representation learning
- Lower Bounds for Compressed Sensing with Generative Models
- Regularized Autoencoders via Relaxed Injective Probability Flow
- Inferring Multidimensional Rates of Aging from Cross-Sectional Data
- Testing the robustness of simulation-based gravitational-wave population inference
- IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System
- Adaptive Parameterization for Neural Dialogue Generation
- HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models
- Metropolis-Hastings view on variational inference and adversarial training
- Rationalizing Predictions by Adversarial Information Calibration
- DwNet: Dense warp-based network for pose-guided human video generation
- Design, Benchmarking and Explainability Analysis of a Game-Theoretic Framework towards Energy Efficiency in Smart Infrastructure
- Validated Variational Inference via Practical Posterior Error Bounds
- Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN
- Improving Generative Imagination in Object-Centric World Models
- High Fidelity Face Manipulation with Extreme Poses and Expressions
- Adversarial Approximate Inference for Speech to Electroglottograph Conversion
- Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values
- Neural Baselines for Word Alignment
- Zero-Shot Semantic Segmentation
- Demystifying Inter-Class Disentanglement
- Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation
- Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimation
- Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
- Expected path length on random manifolds
- README: REpresentation learning by fairness-Aware Disentangling MEthod
- Transforming Gaussian Processes With Normalizing Flows
- MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
- Towards neural networks that provably know when they don't know
- A Generative Model for Molecular Distance Geometry
- Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning
- Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
- Neural Architecture Optimization with Graph VAE
- The Neural Moving Average Model for Scalable Variational Inference of State Space Models
- Neural Design Network: Graphic Layout Generation with Constraints
- Learning Human Objectives by Evaluating Hypothetical Behavior
- Invertible Generative Modeling using Linear Rational Splines
- Symbolic Music Generation with Diffusion Models
- Representation Learning for Event-based Visuomotor Policies
- Variational Autoencoders with Riemannian Brownian Motion Priors
- Towards Information-Seeking Agents
- Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
- On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks
- Data Uncertainty Learning in Face Recognition
- Disentangled Variational Representation for Heterogeneous Face Recognition
- SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
- Kamino: Constraint-Aware Differentially Private Data Synthesis
- Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)
- Nonparametric Inference for Auto-Encoding Variational Bayes
- DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
- ChartPointFlow for Topology-Aware 3D Point Cloud Generation
- Accurate Passive Radar via an Uncertainty-Aware Fusion of Wi-Fi Sensing Data
- Structured Black Box Variational Inference for Latent Time Series Models
- Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes
- Identifying Invariant Texture Violation for Robust Deepfake Detection
- Private-Shared Disentangled Multimodal VAE for Learning of Hybrid Latent Representations
- Latent Causal Invariant Model
- Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networks
- Generating Images with Sparse Representations
- Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET
- Regularizing by the Variance of the Activations' Sample-Variances
- Concept-Oriented Deep Learning: Generative Concept Representations
- Scaling Down Deep Learning with MNIST-1D
- Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection
- MMGAN: Generative Adversarial Networks for Multi-Modal Distributions
- Non-saturating GAN training as divergence minimization
- A Simple Spectral Failure Mode for Graph Convolutional Networks
- Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
- Generative Melody Composition with Human-in-the-Loop Bayesian Optimization
- Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
- Data-driven multifidelity topology design with multi-channel variational auto-encoder for concurrent optimization of multiple design variable fields
- A Flexible Framework for Anomaly Detection via Dimensionality Reduction
- Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
- Automatic Feature Engineering for Time Series Classification: Evaluation and Discussion
- Goal-Oriented Gaze Estimation for Zero-Shot Learning
- Adversarial Domain Adaptation with Domain Mixup
- Recurrent Latent Variable Networks for Session-Based Recommendation
- In the Eye of the Beholder: Gaze and Actions in First Person Video
- Unsupervised Machine Commenting with Neural Variational Topic Model
- Disentangled Representation Learning with Wasserstein Total Correlation
- Conditional Image Generation with Score-Based Diffusion Models
- SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
- Learning Deep Generative Models with Doubly Stochastic MCMC
- Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
- Unsupervised Incremental Learning with Dual Concept Drift Detection for Identifying Anomalous Sequences
- A Neural-enhanced Factor Graph-based Algorithm for Robust Positioning in Obstructed LOS Situations
- Data Augmentation For Medical MR Image Using Generative Adversarial Networks
- BasisVAE: Translation-invariant feature-level clustering with Variational Autoencoders
- Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression Values
- A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks
- SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
- A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
- Probabilistic Active Meta-Learning
- Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
- Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
- Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
- Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators
- MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
- Disentangled Representations from Non-Disentangled Models
- Dual Variational Generation for Low-Shot Heterogeneous Face Recognition
- Knowledge-Based Regularization in Generative Modeling
- Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
- Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
- flexgrid2vec: Learning Efficient Visual Representations Vectors
- Gaussian Copula Variational Autoencoders for Mixed Data
- Model of rough surfaces with Gaussian processes
- CATE: Computation-aware Neural Architecture Encoding with Transformers
- Storchastic: A Framework for General Stochastic Automatic Differentiation
- Radial and Directional Posteriors for Bayesian Neural Networks
- Long-term Human Motion Prediction with Scene Context
- Context-aware learning for generative models
- Information Theoretic Co-Training
- Differentiable Particle Filtering without Modifying the Forward Pass
- PaintBot: A Reinforcement Learning Approach for Natural Media Painting
- Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
- Accelerated Discovery of Sustainable Building Materials
- Disentangling and Learning Robust Representations with Natural Clustering
- Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
- CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge
- Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation
- Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images
- Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
- OneFlow: One-class flow for anomaly detection based on a minimal volume region
- Reparameterization trick for discrete variables
- Neural Density Estimation and Likelihood-free Inference
- Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components
- Training Generative Reversible Networks
- Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance
- Reinforcement Learning Generalization with Surprise Minimization
- Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning
- On the Fairness of Disentangled Representations
- ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning
- Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
- Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network
- Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
- Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation
- Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
- Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data
- SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning
- Inducing Interpretable Representations with Variational Autoencoders
- Gaussian mixture models with Wasserstein distance
- AI-generated art perceptions with GenFrame -- an image-generating picture frame
- MineGAN: effective knowledge transfer from GANs to target domains with few images
- Information Potential Auto-Encoders
- Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders
- DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
- Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery
- Self-Supervised Out-of-Distribution Detection in Brain CT Scans
- Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space
- MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction
- Handloom Design Generation Using Generative Networks
- Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
- No MCMC for me: Amortized sampling for fast and stable training of energy-based models
- Deep Involutive Generative Models for Neural MCMC
- Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning
- How Bayesian Should Bayesian Optimisation Be?
- Soft then Hard: Rethinking the Quantization in Neural Image Compression
- Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server
- Locally Masked Convolution for Autoregressive Models
- Unsupervised Video Decomposition using Spatio-temporal Iterative Inference
- Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
- Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoders
- Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes
- Generative Models for Anomaly Detection and Design-Space Dimensionality Reduction in Shape Optimization
- Learning the Precise Feature for Cluster Assignment
- Hierarchical VampPrior Variational Fair Auto-Encoder
- EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
- Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications
- Persuasive Faces: Generating Faces in Advertisements
- A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features
- Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models
- Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization
- Deep Multi-Fidelity Active Learning of High-dimensional Outputs
- Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting
- Combinatorial 3D Shape Generation via Sequential Assembly
- Semantic-Aware Generation for Self-Supervised Visual Representation Learning
- Stellar Cluster Detection using GMM with Deep Variational Autoencoder
- Generating Contextual Load Profiles Using a Conditional Variational Autoencoder
- 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
- Detecting Anomalous Faces with 'No Peeking' Autoencoders
- Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning
- Neural Variational Hybrid Collaborative Filtering
- We are More than Our Joints: Predicting how 3D Bodies Move
- Multi-View representation learning in Multi-Task Scene
- Learning Actionable Representations with Goal-Conditioned Policies
- A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
- Label-Noise Robust Generative Adversarial Networks
- Image Generation from Layout
- A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model
- Instance-level Facial Attributes Transfer with Geometry-Aware Flow
- Prediction of the morphological evolution of a splashing drop using an encoder-decoder
- Object-Centric Image Generation with Factored Depths, Locations, and Appearances
- An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation
- Variational Bayesian Context-aware Representation for Grocery Recommendation
- Modelling multivariate spatio-temporal data with identifiable variational autoencoders
- Predictive Modeling, Pattern Recognition, and Spatiotemporal Representations of Plant Growth in Simulated and Controlled Environments: A Comprehensive Review
- Improving Deep Image Clustering With Spatial Transformer Layers
- Bimanual Grasp Synthesis for Dexterous Robot Hands
- DeepGalaxy: Deducing the Properties of Galaxy Mergers from Images Using Deep Neural Networks
- Generative networks as inverse problems with Scattering transforms
- Inference over radiative transfer models using variational and expectation maximization methods
- Structured Bayesian Gaussian process latent variable model
- Perturbative Black Box Variational Inference
- GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
- Improving Query Efficiency of Black-box Adversarial Attack
- Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
- Variational Inference for Computational Imaging Inverse Problems
- Uncertainty Inspired RGB-D Saliency Detection
- CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels
- Region Semantically Aligned Network for Zero-Shot Learning
- Exploratory State Representation Learning
- Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
- Minimizing FLOPs to Learn Efficient Sparse Representations
- TracInAD: Measuring Influence for Anomaly Detection
- Contrastive Variational Reinforcement Learning for Complex Observations
- Prediction of head motion from speech waveforms with a canonical-correlation-constrained autoencoder
- Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance
- Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations
- Deep Fake Detection: Survey of Facial Manipulation Detection Solutions
- Neural Recursive Belief States in Multi-Agent Reinforcement Learning
- Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
- Conditional Generative Models for Counterfactual Explanations
- Human-interpretable model explainability on high-dimensional data
- Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey
- Predictive Sampling with Forecasting Autoregressive Models
- VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
- Compound Probabilistic Context-Free Grammars for Grammar Induction
- Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
- Few-Shot Action Localization without Knowing Boundaries
- Adaptive Monte Carlo augmented with normalizing flows
- Generative Adversarial Networks for Scintillation Signal Simulation in EXO-200
- Learning Dynamic Generator Model by Alternating Back-Propagation Through Time
- Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
- Sparse Orthogonal Variational Inference for Gaussian Processes
- Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
- Performing Co-Membership Attacks Against Deep Generative Models
- On Initial Pools for Deep Active Learning
- Recursive Inference for Variational Autoencoders
- Particle Smoothing Variational Objectives
- Automatic Variational ABC
- Adversarially Approximated Autoencoder for Image Generation and Manipulation
- Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
- Discovering Dialog Structure Graph for Open-Domain Dialog Generation
- Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
- Unsupervised Phoneme and Word Discovery from Multiple Speakers using Double Articulation Analyzer and Neural Network with Parametric Bias
- Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
- Towards Empirical Sandwich Bounds on the Rate-Distortion Function
- Scalable Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Computer Vision
- Full Scaling Automation for Sustainable Development of Green Data Centers
- Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
- Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes
- TwoStreamVAN: Improving Motion Modeling in Video Generation
- Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
- highway2vec -- representing OpenStreetMap microregions with respect to their road network characteristics
- Learning Proposals for Probabilistic Programs with Inference Combinators
- Robust Ordinal VAE: Employing Noisy Pairwise Comparisons for Disentanglement
- Hand-Object Contact Consistency Reasoning for Human Grasps Generation
- Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
- Learning Latent Space Energy-Based Prior Model for Molecule Generation
- Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models
- Conditional Adversarial Generative Flow for Controllable Image Synthesis
- Geometry-Aware Hamiltonian Variational Auto-Encoder
- Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI
- Discriminator Feature-based Inference by Recycling the Discriminator of GANs
- AutoCure: Automated Tabular Data Curation Technique for ML Pipelines
- Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
- Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples
- Reachability Embeddings: Scalable Self-Supervised Representation Learning from Mobility Trajectories for Multimodal Geospatial Computer Vision
- Variational Bayesian Decision-making for Continuous Utilities
- G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
- tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder
- Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
- Variational Integrator Networks for Physically Structured Embeddings
- TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
- Self-supervised Representation Learning for Evolutionary Neural Architecture Search
- Denoising Diffusion Gamma Models
- Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression
- Make a Face: Towards Arbitrary High Fidelity Face Manipulation
- Visual Language Modeling on CNN Image Representations
- Sample-Efficient Training of Robotic Guide Using Human Path Prediction Network
- Structured Embedding Models for Grouped Data
- Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
- Capturing Label Characteristics in VAEs
- Non-Adversarial Imitation Learning and its Connections to Adversarial Methods
- Generative Class-conditional Autoencoders
- How Does GAN-based Semi-supervised Learning Work?
- Bayesian Conditional Generative Adverserial Networks
- Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration
- Semantics Preserving Adversarial Learning
- Reconstruction Bottlenecks in Object-Centric Generative Models
- CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
- RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation
- Human Trajectory Prediction via Counterfactual Analysis
- Automatic Relevance Determination For Deep Generative Models
- Learning Discrete State Abstractions With Deep Variational Inference
- DeepOBS: A Deep Learning Optimizer Benchmark Suite
- Amortized Bethe Free Energy Minimization for Learning MRFs
- Investigation of Using VAE for i-Vector Speaker Verification
- Deep Variational Sufficient Dimensionality Reduction
- Generating Smooth Pose Sequences for Diverse Human Motion Prediction
- Measuring Dependence with Matrix-based Entropy Functional
- Expected Information Maximization: Using the I-Projection for Mixture Density Estimation
- PixelCNN Models with Auxiliary Variables for Natural Image Modeling
- Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective
- Topic Modelling Meets Deep Neural Networks: A Survey
- Variational Deep Semantic Hashing for Text Documents
- Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
- Continuous Mixtures of Tractable Probabilistic Models
- Information Theory in Density Destructors
- Learning Deep Generative Models with Annealed Importance Sampling
- DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
- Normalizing Flows Across Dimensions
- Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
- TSIT: A Simple and Versatile Framework for Image-to-Image Translation
- Variational Generative Stochastic Networks with Collaborative Shaping
- MissDeepCausal: Causal Inference from Incomplete Data Using Deep Latent Variable Models
- Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
- Anytime Sampling for Autoregressive Models via Ordered Autoencoding
- Variational Leakage: The Role of Information Complexity in Privacy Leakage
- Learning Hierarchical Priors in VAEs
- Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)
- Posterior Estimation Using Deep Learning: A Simulation Study of Compartmental Modeling in Dynamic PET
- Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence
- Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits
- Improving VAEs' Robustness to Adversarial Attack
- Using Probabilistic Movement Primitives in Analyzing Human Motion Difference under Transcranial Current Stimulation
- Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation
- H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
- Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
- SocialInteractionGAN: Multi-person Interaction Sequence Generation
- What Is Considered Complete for Visual Recognition?
- Cerberus: A Multi-headed Derenderer
- Training VAEs Under Structured Residuals
- Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
- Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds
- Multimodal Variational Autoencoders for Semi-Supervised Learning: In Defense of Product-of-Experts
- Style Transfer with Time Series: Generating Synthetic Financial Data
- Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
- Local Expectation Gradients for Doubly Stochastic Variational Inference
- Pose-Guided High-Resolution Appearance Transfer via Progressive Training
- A COLD Approach to Generating Optimal Samples
- The Role of Information Complexity and Randomization in Representation Learning
- Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation
- Explaining Predictions by Approximating the Local Decision Boundary
- Connect the Dots: In Situ 4D Seismic Monitoring of CO2 Storage with Spatio-temporal CNNs
- AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
- Latent Variables on Spheres for Autoencoders in High Dimensions
- Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations
- Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults
- High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection
- Incorporating Interpretable Output Constraints in Bayesian Neural Networks
- Towards Robust Metrics for Concept Representation Evaluation
- Fast Black-box Variational Inference through Stochastic Trust-Region Optimization
- Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional
- Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Survey
- SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
- Bipartite Graph Embedding via Mutual Information Maximization
- Bayesian Optimization for Cascade-type Multi-stage Processes
- LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
- Learning Disentangled Representations for Time Series
- Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
- Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology
- 3D Shape Reconstruction from Free-Hand Sketches
- Set-Conditional Set Generation for Particle Physics
- Anomaly scores for generative models
- Learning Neurosymbolic Generative Models via Program Synthesis
- Progressive and Aligned Pose Attention Transfer for Person Image Generation
- REX: Revisiting Budgeted Training with an Improved Schedule
- Hamiltonian Variational Auto-Encoder
- Distributed Weight Consolidation: A Brain Segmentation Case Study
- Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANs
- Generative Design of Crystal Structures by Point Cloud Representations and Diffusion Model
- Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control
- Deciphering quantum fingerprints in electric conductance
- Ergodic Inference: Accelerate Convergence by Optimisation
- Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
- Max-Affine Spline Insights into Deep Generative Networks
- Latent Programmer: Discrete Latent Codes for Program Synthesis
- Quantitative Evaluation of Time-Dependent Multidimensional Projection Techniques
- Short-Term Traffic Flow Prediction Using Variational LSTM Networks
- Image-based reconstruction for the impact problems by using DPNNs
- Intrinsic Motivation for Encouraging Synergistic Behavior
- SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
- Simple Video Generation using Neural ODEs
- Independent Innovation Analysis for Nonlinear Vector Autoregressive Process
- Safe Autonomous Racing via Approximate Reachability on Ego-vision
- Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarios
- Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders
- PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
- Learning Continuous Environment Fields via Implicit Functions
- Super-Resolution Perception for Industrial Sensor Data
- Dense Pose Transfer
- A Brief Overview of Unsupervised Neural Speech Representation Learning
- Robust Multi-Output Learning with Highly Incomplete Data via Restricted Boltzmann Machines
- Learning Disentangled Representations of Timbre and Pitch for Musical Instrument Sounds Using Gaussian Mixture Variational Autoencoders
- KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
- Cost-sensitive detection with variational autoencoders for environmental acoustic sensing
- Emergent Graphical Conventions in a Visual Communication Game
- Benchmarking Deep Sequential Models on Volatility Predictions for Financial Time Series
- Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning
- Deep Auto-encoder with Neural Response
- A Method to Model Conditional Distributions with Normalizing Flows
- Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks
- ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance
- A Technical Survey on Statistical Modelling and Design Methods for Crowdsourcing Quality Control
- Provable Smoothness Guarantees for Black-Box Variational Inference
- Straight-Through Estimator as Projected Wasserstein Gradient Flow
- DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis
- MaCow: Masked Convolutional Generative Flow
- Zero-shot generation of synthetic neurosurgical data with large language models
- Adaptive Cross-Modal Few-Shot Learning
- Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
- Clustering, factor discovery and optimal transport
- Shared Generative Latent Representation Learning for Multi-view Clustering
- Variational Autoencoders for Opponent Modeling in Multi-Agent Systems
- Factored Temporal Sigmoid Belief Networks for Sequence Learning
- ChemoVerse: Manifold traversal of latent spaces for novel molecule discovery
- Generative Machine Learning for Multivariate Equity Returns
- Learning an optimal PSF-pair for ultra-dense 3D localization microscopy
- Unsupervised Recurrent Neural Network Grammars
- Learning to Navigate in Turbulent Flows with Aerial Robot Swarms: A Cooperative Deep Reinforcement Learning Approach
- Improving Direct Physical Properties Prediction of Heterogeneous Materials from Imaging Data via Convolutional Neural Network and a Morphology-Aware Generative Model
- Information Theoretic Meta Learning with Gaussian Processes
- Vela Pulsar: Single Pulses Analysis with Machine Learning Techniques
- StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
- Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling
- A Closed-Loop Perception, Decision-Making and Reasoning Mechanism for Human-Like Navigation
- A Systematic Assessment of Deep Learning Models for Molecule Generation
- mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation
- Label-Free Segmentation of COVID-19 Lesions in Lung CT
- toon2real: Translating Cartoon Images to Realistic Images
- Independent finite approximations for Bayesian nonparametric inference
- UFO-BLO: Unbiased First-Order Bilevel Optimization
- Generalization and Robustness Implications in Object-Centric Learning
- Visual Adversarial Imitation Learning using Variational Models
- Data-efficient visuomotor policy training using reinforcement learning and generative models
- Learning Functions over Sets via Permutation Adversarial Networks
- Multi-Facet Clustering Variational Autoencoders
- Hybrid VAE: Improving Deep Generative Models using Partial Observations
- BézierSketch: A generative model for scalable vector sketches
- PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
- Vector-Quantized Timbre Representation
- Neural Topic Model via Optimal Transport
- BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
- Addressing the Topological Defects of Disentanglement via Distributed Operators
- Dual Adversarial Inference for Text-to-Image Synthesis
- A Two-Step Framework for Arbitrage-Free Prediction of the Implied Volatility Surface
- A Cross-Level Information Transmission Network for Predicting Phenotype from New Genotype: Application to Cancer Precision Medicine
- Measuring the Biases and Effectiveness of Content-Style Disentanglement
- Embarrassingly Simple Binary Representation Learning
- On Energy-Based Models with Overparametrized Shallow Neural Networks
- Suggestive Annotation of Brain Tumour Images with Gradient-guided Sampling
- Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
- Outlier Detection through Null Space Analysis of Neural Networks
- Compositional uncertainty in deep Gaussian processes
- Deep Residual Mixture Models
- RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
- Manifolds for Unsupervised Visual Anomaly Detection
- A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
- Deep Reactive Planning in Dynamic Environments
- A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
- Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
- Data-Driven Topology Optimization with Multiclass Microstructures using Latent Variable Gaussian Process
- Anomaly Detection Based on Deep Learning Using Video for Prevention of Industrial Accidents
- Joint Intensity-Gradient Guided Generative Modeling for Colorization
- A survey on Variational Autoencoders from a GreenAI perspective
- Toxicity Detection in Drug Candidates using Simplified Molecular-Input Line-Entry System
- Representation learning for improved interpretability and classification accuracy of clinical factors from EEG
- Multi-Task Variational Information Bottleneck
- VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
- LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation
- Automated Discovery of Anomalous Features in Ultra-Large Planetary Remote Sensing Datasets using Variational Autoencoders
- Offline Reinforcement Learning with Pseudometric Learning
- Bidirectional Generative Modeling Using Adversarial Gradient Estimation
- Label Propagation Adaptive Resonance Theory for Semi-supervised Continuous Learning
- A Bayes-Optimal View on Adversarial Examples
- Adaptive Graph Auto-Encoder for General Data Clustering
- Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing
- A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Models
- A deep generative model for gene expression profiles from single-cell RNA sequencing
- Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
- Automatic Backward Filtering Forward Guiding for Markov processes and graphical models
- A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU
- Towards Rapid and Robust Adversarial Training with One-Step Attacks
- Trajectory Prediction with Latent Belief Energy-Based Model
- Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communication
- BachGAN: High-Resolution Image Synthesis from Salient Object Layout
- Do sequence-to-sequence VAEs learn global features of sentences?
- Probabilistic Embeddings for Cross-Modal Retrieval
- -Variational Autoencoder as an Entanglement Classifier
- P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection
- Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
- Data-Dependent Randomized Smoothing
- Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
- Generating Out of Distribution Adversarial Attack using Latent Space Poisoning
- Variational Inference with Continuously-Indexed Normalizing Flows
- MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
- Function Norms and Regularization in Deep Networks
- Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
- Attentive Action and Context Factorization
- Anomaly Detection on Graph Time Series
- Semi-supervised Multimodal Representation Learning through a Global Workspace
- Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder
- Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
- Augment and Reduce: Stochastic Inference for Large Categorical Distributions
- Device Image-IV Mapping using Variational Autoencoder for Inverse Design and Forward Prediction
- Re-parameterizing VAEs for stability
- Half-body Portrait Relighting with Overcomplete Lighting Representation
- Probabilistic Video Generation using Holistic Attribute Control
- Unsupervised multi-modal Styled Content Generation
- Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
- On importance-weighted autoencoders
- Learning to Assimilate in Chaotic Dynamical Systems
- Testing Outlier Detection Algorithms for Identifying Early-Stage Solute Clusters in Atom Probe Tomography
- A Dynamic Edge Exchangeable Model for Sparse Temporal Networks
- Learning Flat Latent Manifolds with VAEs
- dMelodies: A Music Dataset for Disentanglement Learning
- Posterior Meta-Replay for Continual Learning
- Learning to Score Behaviors for Guided Policy Optimization
- Unsupervised object-centric video generation and decomposition in 3D
- Streaming Adaptive Nonparametric Variational Autoencoder
- Deterministic Decoding for Discrete Data in Variational Autoencoders
- Energy Consumption of Deep Generative Audio Models
- Self-Constructing Graph Convolutional Networks for Semantic Labeling
- Domain-Robust Visual Imitation Learning with Mutual Information Constraints
- Domain Generalization via Inference-time Label-Preserving Target Projections
- Towards White-box Benchmarks for Algorithm Control
- SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
- Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment
- Variational online learning of neural dynamics
- Variational Auto-Encoder: not all failures are equal
- Meta Dropout: Learning to Perturb Features for Generalization
- Lossless compression with state space models using bits back coding
- Walsh-Hadamard Variational Inference for Bayesian Deep Learning
- DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
- Classifying CMB time-ordered data through deep neural networks
- Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking
- Dynamic Future Net: Diversified Human Motion Generation
- Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
- Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks
- Particle Filter Recurrent Neural Networks
- Learning Image Representations for Content Based Image Retrieval of Radiotherapy Treatment Plans
- Semantic Adversarial Network for Zero-Shot Sketch-Based Image Retrieval
- Unpaired Multi-Domain Image Generation via Regularized Conditional GANs
- mmFall: Fall Detection using 4D MmWave Radar and a Hybrid Variational RNN AutoEncoder
- Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control
- Horseshoe Regularization for Machine Learning in Complex and Deep Models
- Longitudinal Variational Autoencoder
- Indoor thermal comfort management: A Bayesian machine-learning approach to data denoising and dynamics prediction of HVAC systems
- Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
- DualDis: Dual-Branch Disentangling with Adversarial Learning
- Learning Continuous-Time Dynamics by Stochastic Differential Networks
- Detection of Deepfake Videos Using Long Distance Attention
- TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions
- A Simple Framework for Uncertainty in Contrastive Learning
- Improving Neural Topic Models with Wasserstein Knowledge Distillation
- Generalized Energy Based Models
- Deep Random Splines for Point Process Intensity Estimation of Neural Population Data
- Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming
- Robust Pollen Imagery Classification with Generative Modeling and Mixup Training
- Annealed Flow Transport Monte Carlo
- A Novel Variational Autoencoder with Applications to Generative Modelling, Classification, and Ordinal Regression
- Critical initialisation in continuous approximations of binary neural networks
- Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
- Wasserstein Measure Coresets
- Constructing the Matrix Multilayer Perceptron and its Application to the VAE
- Generative Hierarchical Features from Synthesizing Images
- SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
- TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts
- Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning
- Surfing: Iterative optimization over incrementally trained deep networks
- Learning robust speech representation with an articulatory-regularized variational autoencoder
- An Empirical Study: Extensive Deep Temporal Point Process
- Evidence Transfer for Improving Clustering Tasks Using External Categorical Evidence
- Variational Autoencoder with Learned Latent Structure
- Information Theory Measures via Multidimensional Gaussianization
- Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin
- Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders
- retina-VAE: Variationally Decoding the Spectrum of Macular Disease
- Index Tracking with Cardinality Constraints: A Stochastic Neural Networks Approach
- Bayesian Paragraph Vectors
- LumièreNet: Lecture Video Synthesis from Audio
- Label Dependent Deep Variational Paraphrase Generation
- Bayesian Structure Adaptation for Continual Learning
- Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition
- Probabilistically-autoencoded horseshoe-disentangled multidomain item-response theory models
- Adaptive Pruning of Neural Language Models for Mobile Devices
- Deep Denerative Models for Drug Design and Response
- Generative Interventions for Causal Learning
- A Fine-Grained Analysis on Distribution Shift
- Weakly Supervised Label Learning Flows
- Comparing directed networks via denoising graphlet distributions
- Visual Conceptual Blending with Large-scale Language and Vision Models
- SincVAE: A new semi-supervised approach to improve anomaly detection on EEG data using SincNet and variational autoencoder
- Variational Information Bottleneck on Vector Quantized Autoencoders
- AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models
- A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
- Global-Local Item Embedding for Temporal Set Prediction
- Semantically Multi-modal Image Synthesis
- Measuring Fairness in Generative Models
- Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
- Variational Capsules for Image Analysis and Synthesis
- Learning Latent Space Energy-Based Prior Model
- Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models
- Sliced Iterative Normalizing Flows
- Target-Embedding Autoencoders for Supervised Representation Learning
- Latent feature disentanglement for 3D meshes
- Active Decision Boundary Annotation with Deep Generative Models
- Implicit Autoencoders
- Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism
- Deep Generative Learning via Variational Gradient Flow
- Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
- GO Gradient for Expectation-Based Objectives
- The Art of Food: Meal Image Synthesis from Ingredients
- Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding
- Disentangling Content and Style via Unsupervised Geometry Distillation
- Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning
- Beyond Low Earth Orbit: Biological Research, Artificial Intelligence, and Self-Driving Labs
- Learning Implicit Generative Models by Teaching Explicit Ones
- Variational Bayesian surrogate modelling with application to robust design optimisation
- Learning from Noisy Web Data with Category-level Supervision
- Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
- Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
- Personalized Federated Learning of Driver Prediction Models for Autonomous Driving
- Learning Implicit Generative Models with Theoretical Guarantees
- The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design
- Unified Generator-Classifier for Efficient Zero-Shot Learning
- Reducing Positional Variance in Cross-sectional Abdominal CT Slices with Deep Conditional Generative Models
- FFPDG: Fast, Fair and Private Data Generation
- Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation
- Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization
- HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE
- Adaptive Stress Testing for Autonomous Vehicles
- Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
- Machine Learning Percolation Model
- Triggering Dark Showers with Conditional Dual Auto-Encoders
- On Disentanglement in Gaussian Process Variational Autoencoders
- Unbiased Gradient Estimation for Variational Auto-Encoders using Coupled Markov Chains
- Agent Modelling under Partial Observability for Deep Reinforcement Learning
- An Uncertain Future: Forecasting from Static Images using Variational Autoencoders
- Data Augmentation for Enhancing EEG-based Emotion Recognition with Deep Generative Models
- Variational Feature Disentangling for Fine-Grained Few-Shot Classification
- Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data
- Improving Disentangled Representation Learning with the Beta Bernoulli Process
- StackVAE-G: An efficient and interpretable model for time series anomaly detection
- InfoFair: Information-Theoretic Intersectional Fairness
- Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis
- GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing
- Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
- Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
- Benchmarking Unsupervised Object Representations for Video Sequences
- HumanGAN: A Generative Model of Humans Images
- GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations
- When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
- Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity
- Sparse Stochastic Zeroth-Order Optimization with an Application to Bandit Structured Prediction
- Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
- Bridging Global Context Interactions for High-Fidelity Image Completion
- AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization
- Semi-supervised Learning with Missing Values Imputation
- Log Message Anomaly Detection and Classification Using Auto-B/LSTM and Auto-GRU
- Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
- Deep Variational Semi-Supervised Novelty Detection
- Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
- Flow Contrastive Estimation of Energy-Based Models
- PSD Representations for Effective Probability Models
- Generative Ratio Matching Networks
- Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say "I don't know" for Ambiguous Cases
- View-Invariant Probabilistic Embedding for Human Pose
- BoA-PTA, A Bayesian Optimization Accelerated Error-Free SPICE Solver
- Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems
- Generating 3D People in Scenes without People
- Few Shot System Identification for Reinforcement Learning
- Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance
- Deep Tensor CCA for Multi-view Learning
- Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
- GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
- Constructing a meta-learner for unsupervised anomaly detection
- NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
- Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning
- Exploring Dynamic Context for Multi-path Trajectory Prediction
- The Thermodynamic Variational Objective
- RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval
- Trust-Region Variational Inference with Gaussian Mixture Models
- Learning to learn generative programs with Memoised Wake-Sleep
- Deep Generative Learning via Schrödinger Bridge
- Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
- Federated Estimation of Causal Effects from Observational Data
- An Attribute-Aligned Strategy for Learning Speech Representation
- Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET
- Online reinforcement learning with sparse rewards through an active inference capsule
- Task-Generic Hierarchical Human Motion Prior using VAEs
- Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
- Definition-independent Formalization of Soundscapes: Towards a Formal Methodology
- Multi-View Variational Autoencoder for Missing Value Imputation in Untargeted Metabolomics
- High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve
- Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Data
- Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
- Effect of latent space distribution on the segmentation of images with multiple annotations
- Learning to Predict Navigational Patterns from Partial Observations
- Bayesian Methods in Tensor Analysis
- A Mathematical Framework for Learning Probability Distributions
- DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
- Multi-modal data generation with a deep metric variational autoencoder
- Heredity-aware Child Face Image Generation with Latent Space Disentanglement
- SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
- WAD: A Deep Reinforcement Learning Agent for Urban Autonomous Driving
- Edge-Enhanced Global Disentangled Graph Neural Network for Sequential Recommendation
- Reviewing continual learning from the perspective of human-level intelligence
- Learning to Model the Grasp Space of an Underactuated Robot Gripper Using Variational Autoencoder
- Variational Inference with Holder Bounds
- Training Deep Spiking Auto-encoders without Bursting or Dying Neurons through Regularization
- WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data
- Contrastive Unpaired Translation using Focal Loss for Patch Classification
- CSI Clustering with Variational Autoencoding
- Causal Effect Variational Autoencoder with Uniform Treatment
- Three-body renormalization group limit cycles based on unsupervised feature learning
- Unsupervised Part Discovery from Contrastive Reconstruction
- BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning
- Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
- Sub-word Level Lip Reading With Visual Attention
- An Exploration of Learnt Representations of W Jets
- HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation
- Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation
- Learning Multimodal VAEs through Mutual Supervision
- Coupled Gradient Estimators for Discrete Latent Variables
- Unsupervised Embedding of Hierarchical Structure in Euclidean Space
- Unsupervised Object Keypoint Learning using Local Spatial Predictability
- PD-GAN: Probabilistic Diverse GAN for Image Inpainting
- Contrastive Attraction and Contrastive Repulsion for Representation Learning
- Reinforcement Learning with Efficient Active Feature Acquisition
- Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture
- Sparse Uncertainty Representation in Deep Learning with Inducing Weights
- Landmarks Augmentation with Manifold-Barycentric Oversampling
- Unsupervised dynamic modeling of medical image transformation
- Vertical-Horizontal Structured Attention for Generating Music with Chords
- Dual Contradistinctive Generative Autoencoder
- CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
- Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
- 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
- A Study on the Autoregressive and non-Autoregressive Multi-label Learning
- Planning from Pixels using Inverse Dynamics Models
- Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval
- Evolutionary Variational Optimization of Generative Models
- Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
- MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs
- Refining Deep Generative Models via Discriminator Gradient Flow
- Unpaired Image-to-Image Translation via Latent Energy Transport
- An Information-Geometric Distance on the Space of Tasks
- Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach
- Auto-Encoding Variational Bayes for Inferring Topics and Visualization
- Probabilistic Circuits for Variational Inference in Discrete Graphical Models
- Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
- Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
- Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
- Variational Autoencoders with a Structural Similarity Loss in Time of Flight MRAs
- 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
- 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
- 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
- Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
- Bayesian Transformer Language Models for Speech Recognition
- Future Urban Scenes Generation Through Vehicles Synthesis
- A unified survey of treatment effect heterogeneity modeling and uplift modeling
- Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
- Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
- Task-adaptive Neural Process for User Cold-Start Recommendation
- Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
- Combining Spiking Neural Network and Artificial Neural Network for Enhanced Image Classification
- The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction
- Efficient Learning of Generative Models via Finite-Difference Score Matching
- Novelty Detection via Robust Variational Autoencoding
- A prior-based approximate latent Riemannian metric
- Sensorimotor Visual Perception on Embodied System Using Free Energy Principle
- VAE-KRnet and its applications to variational Bayes
- CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
- Embodied Self-supervised Learning by Coordinated Sampling and Training
- Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
- Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
- Uncertainty-guided Model Generalization to Unseen Domains
- AMENet: Attentive Maps Encoder Network for Trajectory Prediction
- Learning Task Decomposition with Ordered Memory Policy Network
- Low Distortion Block-Resampling with Spatially Stochastic Networks
- The Convolution Exponential and Generalized Sylvester Flows
- Learning Global and Local Features of Normal Brain Anatomy for Unsupervised Abnormality Detection
- Review of Text Style Transfer Based on Deep Learning
- Classify and Generate: Using Classification Latent Space Representations for Image Generations
- Inclusive GAN: Improving Data and Minority Coverage in Generative Models
- Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
- Deep Inverse Feature Learning: A Representation Learning of Error
- Meta-SVDD: Probabilistic Meta-Learning for One-Class Classification in Cancer Histology Images
- Uniform Interpolation Constrained Geodesic Learning on Data Manifold
- Bringing Old Photos Back to Life
- Bayesian Reasoning with Trained Neural Networks
- TRADI: Tracking deep neural network weight distributions for uncertainty estimation
- Attentive Representation Learning with Adversarial Training for Short Text Clustering
- Joint Learning of Generative Translator and Classifier for Visually Similar Classes
- Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
- A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling
- Learning Neural Light Transport
- Robotic Motion Planning using Learned Critical Sources and Local Sampling
- Improved BiGAN training with marginal likelihood equalization
- Semi-Supervised Variational Autoencoder for Survival Prediction
- Causal Inference with Deep Causal Graphs
- Target-Focused Feature Selection Using a Bayesian Approach
- Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning
- CUDA: Contradistinguisher for Unsupervised Domain Adaptation
- Generative Mixture of Networks
- Variational Autoencoding of PDE Inverse Problems
- Invertible Zero-Shot Recognition Flows
- Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
- PRI-VAE: Principle-of-Relevant-Information Variational Autoencoders
- Location Anomalies Detection for Connected and Autonomous Vehicles
- Learning Disentangled Representations with Latent Variation Predictability
- Variance Reduction for Evolution Strategies via Structured Control Variates
- Towards Amortized Ranking-Critical Training for Collaborative Filtering
- Domain-Specific Mappings for Generative Adversarial Style Transfer
- F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
- Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
- Joint Variational Autoencoders for Recommendation with Implicit Feedback
- Self-Supervised Ultrasound to MRI Fetal Brain Image Synthesis
- Monotonic Gaussian Process Flow
- Capacity-Approaching Autoencoders for Communications
- Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
- Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
- Bigeminal Priors Variational auto-encoder
- The Variational Predictive Natural Gradient
- Continuous Graph Flow
- Truncated Gaussian-Mixture Variational AutoEncoder
- Point Process Flows
- Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation
- Animating Face using Disentangled Audio Representations
- 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
- Coloring the Black Box: Visualizing neural network behavior with a self-introspective model
- Animating Landscape: Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesis
- Latent Dirichlet Allocation in Generative Adversarial Networks
- AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
- 3D Shape Reconstruction from a Single 2D Image via 2D-3D Self-Consistency
- Predicting with High Correlation Features
- Class-Distinct and Class-Mutual Image Generation with GANs
- Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns
- Singing Voice Conversion with Disentangled Representations of Singer and Vocal Technique Using Variational Autoencoders
- Learning Latent State Spaces for Planning through Reward Prediction
- Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions
- Linear Algebra and Duality of Neural Networks
- Consensus Message Passing for Layered Graphical Models
- White Noise Analysis of Neural Networks
- Improving generalization of vocal tract feature reconstruction: from augmented acoustic inversion to articulatory feature reconstruction without articulatory data
- Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
- Adversarial Disentanglement with Grouped Observations
- Seq2seq Translation Model for Sequential Recommendation
- Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
- On the Discrepancy between Density Estimation and Sequence Generation
- A Variational Time Series Feature Extractor for Action Prediction
- Interpretable Partitioned Embedding for Customized Fashion Outfit Composition
- Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)
- Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction
- Retinal Vessel Segmentation Based on Conditional Deep Convolutional Generative Adversarial Networks
- Latent Variable Modeling for Generative Concept Representations and Deep Generative Models
- On the Transformation of Latent Space in Autoencoders
- Group Anomaly Detection using Deep Generative Models
- Variational Rejection Sampling
- Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
- Representation Learning and Recovery in the ReLU Model
- Physics-constrained, data-driven discovery of coarse-grained dynamics
- Combining Model and Parameter Uncertainty in Bayesian Neural Networks
- Event-Based Modeling with High-Dimensional Imaging Biomarkers for Estimating Spatial Progression of Dementia
- Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices
- UVA: A Universal Variational Framework for Continuous Age Analysis
- Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders
- Including Physics in Deep Learning -- An example from 4D seismic pressure saturation inversion
- Crossmodal Voice Conversion
- Importance Weighted Hierarchical Variational Inference
- TopoResNet: A hybrid deep learning architecture and its application to skin lesion classification
- Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction
- Unsupervised Classification of Street Architectures Based on InfoGAN
- Continuously tempered Hamiltonian Monte Carlo
- Continual Learning of New Sound Classes using Generative Replay
- Reconstruction and Membership Inference Attacks against Generative Models
- Augmenting and Tuning Knowledge Graph Embeddings
- k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport
- Predicting Visual Memory Schemas with Variational Autoencoders
- Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
- Generative Image Modeling using Style and Structure Adversarial Networks
- Bayesian Meta-reinforcement Learning for Traffic Signal Control
- Future Frame Prediction for Robot-assisted Surgery
- Pairwise Augmented GANs with Adversarial Reconstruction Loss
- Homotopic Gradients of Generative Density Priors for MR Image Reconstruction
- Probabilistic Discriminative Learning with Layered Graphical Models
- Generalized Latent Variable Recovery for Generative Adversarial Networks
- Learning based signal detection for MIMO systems with unknown noise statistics
- Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
- Accelerated WGAN update strategy with loss change rate balancing
- Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
- Nonparallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks
- Fair Normalizing Flows
- RoMA: Robust Model Adaptation for Offline Model-based Optimization
- Texture Synthesis with Recurrent Variational Auto-Encoder
- An information-based metric for observing strategy optimization, demonstrated in the context of photometric redshifts with applications to cosmology
- Universal Neural Vocoding with Parallel WaveNet
- Group Equivariant Conditional Neural Processes
- Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests
- Max-Margin Deep Generative Models for (Semi-)Supervised Learning
- Unsupervised Learning of Lidar Features for Use in a Probabilistic Trajectory Estimator
- Geometrically Enriched Latent Spaces
- MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
- Modular Action Concept Grounding in Semantic Video Prediction
- Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval
- Text Generation with Deep Variational GAN
- The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies
- Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
- Physics-aware, probabilistic model order reduction with guaranteed stability
- Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling
- Assessing Deep Neural Networks as Probability Estimators
- Parameterization of Forced Isotropic Turbulent Flow using Autoencoders and Generative Adversarial Networks
- Hierarchical Kinematic Human Mesh Recovery
- Artificial Neural Networks Jamming on the Beat
- Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
- Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift
- A Variational Auto-Encoder Approach for Image Transmission in Wireless Channel
- Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images
- Relational State-Space Model for Stochastic Multi-Object Systems
- Radar Odometry Combining Probabilistic Estimation and Unsupervised Feature Learning
- Joint Learning of Neural Networks via Iterative Reweighted Least Squares
- Learning to discover: expressive Gaussian mixture models for multi-dimensional simulation and parameter inference in the physical sciences
- Automatic Differentiation Variational Inference with Mixtures
- Gradient Origin Networks
- Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing
- Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
- Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes
- PAC-Bayes Analysis of Sentence Representation
- Exploring Deep Anomaly Detection Methods Based on Capsule Net
- Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement
- Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
- Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
- NWT: Towards natural audio-to-video generation with representation learning
- GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
- DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs
- Deepfake Videos in the Wild: Analysis and Detection
- Deep Learning Enables Robust and Precise Light Focusing on Treatment Needs
- Cascading Denoising Auto-Encoder as a Deep Directed Generative Model
- Generalization to Novel Objects using Prior Relational Knowledge
- Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
- Importance Sampled Stochastic Optimization for Variational Inference
- BreGMN: scaled-Bregman Generative Modeling Networks
- Flexible mean field variational inference using mixtures of non-overlapping exponential families
- Accelerating Training of Deep Neural Networks with a Standardization Loss
- Transporting Causal Mechanisms for Unsupervised Domain Adaptation
- Curriculum Learning for Deep Generative Models with Clustering
- Exploration by Maximizing Rényi Entropy for Reward-Free RL Framework
- Measure Transport with Kernel Stein Discrepancy
- Deep Generative Modeling in Network Science with Applications to Public Policy Research
- Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means
- GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes
- An ETF view of Dropout regularization
- OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
- Model-agnostic out-of-distribution detection using combined statistical tests
- A Combined Deep Learning based End-to-End Video Coding Architecture for YUV Color Space
- A Variational Autoencoder for Heterogeneous Temporal and Longitudinal Data
- Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
- Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
- Bayesian Variational Optimization for Combinatorial Spaces
- Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View
- Cross-Modal Generative Augmentation for Visual Question Answering
- Neural Allocentric Intuitive Physics Prediction from Real Videos
- Fast gradient-free activation maximization for neurons in spiking neural networks
- Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects
- Towards the Unseen: Iterative Text Recognition by Distilling from Errors
- Autoregressive Score Matching
- NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform
- The Many Moods of Emotion
- On Masked Pre-training and the Marginal Likelihood
- not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution
- Differentiable Particle Filtering using Optimal Placement Resampling
- Latent Space Optimal Transport for Generative Models
- SentenceMIM: A Latent Variable Language Model
- Research and development of MolAICal for drug design via deep learning and classical programming
- Instance-Aware Graph Convolutional Network for Multi-Label Classification
- StyleRemix: An Interpretable Representation for Neural Image Style Transfer
- On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
- How good is my GAN?
- Reconstruction of Pairwise Interactions using Energy-Based Models
- Generating private data with user customization
- Collision-Aware Target-Driven Object Grasping in Constrained Environments
- Torchbearer: A Model Fitting Library for PyTorch
- A Variational Approach to Unsupervised Sentiment Analysis
- Understanding and Improving Virtual Adversarial Training
- Machine learning in the social and health sciences
- WeLa-VAE: Learning Alternative Disentangled Representations Using Weak Labels
- Precision-Recall Curves Using Information Divergence Frontiers
- Hidden Markov Neural Networks
- Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering
- Discrete flow posteriors for variational inference in discrete dynamical systems
- Representing and Denoising Wearable ECG Recordings
- Structural Consistency and Controllability for Diverse Colorization
- Monte Carlo Filtering Objectives: A New Family of Variational Objectives to Learn Generative Model and Neural Adaptive Proposal for Time Series
- Distribution Aware Active Learning
- Diverse Plausible Shape Completions from Ambiguous Depth Images
- Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
- On the use of Nonlinear Normal Modes for Nonlinear Reduced Order Modelling
- Inferential Wasserstein Generative Adversarial Networks
- Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
- Single-View 3D Object Reconstruction from Shape Priors in Memory
- Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
- Variational Marginal Particle Filters
- Deep Learning Based Unsupervised and Semi-supervised Classification for Keratoconus
- Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
- Variational Mixture of Normalizing Flows
- CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
- MAD-VAE: Manifold Awareness Defense Variational Autoencoder
- Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks
- On Positive-Unlabeled Classification in GAN
- ColdGAN: Resolving Cold Start User Recommendation by using Generative Adversarial Networks
- Variational inference for neural network matrix factorization and its application to stochastic blockmodeling
- Semi-Implicit Generative Model
- Controllable Image Synthesis via SegVAE
- Anomaly Detection via Self-organizing Map
- Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
- Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres
- MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
- Semantics-Aware Human Motion Generation from Audio Instructions
- Symmetries and control in generative neural nets
- Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
- GSNs : Generative Stochastic Networks
- Scarce Data Driven Deep Learning of Drones via Generalized Data Distribution Space
- Random Projection in Neural Episodic Control
- DISCO Nets: DISsimilarity COefficient Networks
- Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
- DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images
- Quantum query complexity of entropy estimation
- Variational Encoders and Autoencoders : Information-theoretic Inference and Closed-form Solutions
- Structured Dropout Variational Inference for Bayesian Neural Networks
- Latent Variable Session-Based Recommendation
- On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods
- Few Shot Activity Recognition Using Variational Inference
- Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
- Learning to Manipulate Individual Objects in an Image
- Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
- Community Detection Clustering via Gumbel Softmax
- Deep Feature Response Discriminative Calibration
- Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
- From Discourse to Narrative: Knowledge Projection for Event Relation Extraction
- MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
- Hierarchical Bayesian Model for the Transfer of Knowledge on Spatial Concepts based on Multimodal Information
- Structured Variational Inference for Coupled Gaussian Processes
- Learning Controllable Disentangled Representations with Decorrelation Regularization
- It Is Likely That Your Loss Should be a Likelihood
- Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
- MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining
- Pitchtron: Towards audiobook generation from ordinary people's voices
- Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
- Interactive user interface based on Convolutional Auto-encoders for annotating CT-scans
- MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing
- Dynamic allocation of limited memory resources in reinforcement learning
- Diffusion models for Handwriting Generation
- Scenario Forecasting of Residential Load Profiles
- Simple, Scalable, and Stable Variational Deep Clustering
- "Best-of-Many-Samples" Distribution Matching
- An Alarm System For Segmentation Algorithm Based On Shape Model
- Investigation of F0 conditioning and Fully Convolutional Networks in Variational Autoencoder based Voice Conversion
- All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
- On the Existence of Optimal Transport Gradient for Learning Generative Models
- On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision
- Multi-type Disentanglement without Adversarial Training
- Learning Robust Feature Representations for Scene Text Detection
- Towards universal neural nets: Gibbs machines and ACE
- Gradient Importance Learning for Incomplete Observations
- Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval
- Application-driven Validation of Posteriors in Inverse Problems
- High-dimensional Assisted Generative Model for Color Image Restoration
- Energy-Inspired Models: Learning with Sampler-Induced Distributions
- Hierarchically Clustered Representation Learning
- Semantics, Representations and Grammars for Deep Learning
- To Beta or Not To Beta: Information Bottleneck for DigitaL Image Forensics
- EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
- Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization
- MIM: Mutual Information Machine
- Scaling Up Bayesian Uncertainty Quantification for Inverse Problems using Deep Neural Networks
- Patch-wise Auto-Encoder for Visual Anomaly Detection
- A Binded VAE for Inorganic Material Generation
- Fractional Transfer Learning for Deep Model-Based Reinforcement Learning
- Unsupervised Anomaly Detection From Semantic Similarity Scores
- On Learning the Transformer Kernel
- On the Latent Holes of VAEs for Text Generation
- Harmonization with Flow-based Causal Inference
- Variational Information Bottleneck for Effective Low-resource Audio Classification
- A similarity-based Bayesian mixture-of-experts model
- Generative Learning With Euler Particle Transport
- T-Rep: Representation Learning for Time Series using Time-Embeddings
- New Tricks for Estimating Gradients of Expectations
- DPPNet: Approximating Determinantal Point Processes with Deep Networks
- Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder
- A Commentary on the Unsupervised Learning of Disentangled Representations
- Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation
- Modeling the Biological Pathology Continuum with HSIC-regularized Wasserstein Auto-encoders
- Disentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders
- Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
- An Empirical Study of Stochastic Variational Algorithms for the Beta Bernoulli Process
- Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective
- Theoretical Connection between Locally Linear Embedding, Factor Analysis, and Probabilistic PCA
- Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey
- Solving inverse problems via auto-encoders
- Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
- Diverse Video Generation using a Gaussian Process Trigger
- Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
- Generating Semantically Valid Adversarial Questions for TableQA
- Attention Map-guided Two-stage Anomaly Detection using Hard Augmentation
- Inference and De-Noising of Non-Gaussian Particle Distribution Functions: A Generative Modeling Approach
- Attribute-Guided Sketch Generation
- Zero-shot Synthesis with Group-Supervised Learning
- Neural Network architectures to classify emotions in Indian Classical Music
- Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning
- Rectangular Flows for Manifold Learning
- A Practical Layer-Parallel Training Algorithm for Residual Networks
- Scalable Microservice Forensics and Stability Assessment Using Variational Autoencoders
- Autonomous Vehicles Drive into Shared Spaces: eHMI Design Concept Focusing on Vulnerable Road Users
- Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
- Rate-Regularization and Generalization in VAEs
- Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
- Random Polytope Descriptors
- On The Chain Rule Optimal Transport Distance
- How Tight Can PAC-Bayes be in the Small Data Regime?
- MisConv: Convolutional Neural Networks for Missing Data
- Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
- Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
- Learning to compress and search visual data in large-scale systems
- A lower bound for the ELBO of the Bernoulli Variational Autoencoder
- Likelihood Contribution based Multi-scale Architecture for Generative Flows
- Iterative VAE as a predictive brain model for out-of-distribution generalization
- Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables
- The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC
- High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models
- Computationally Efficient Bayesian Estimation of High Dimensional Copulas with Discrete and Mixed Margins
- Blur, Noise, and Compression Robust Generative Adversarial Networks
- State representation learning with recurrent capsule networks
- MCMC Variational Inference via Uncorrected Hamiltonian Annealing
- Predictive coding feedback results in perceived illusory contours in a recurrent neural network
- Generating a Doppelganger Graph: Resembling but Distinct
- Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)
- Amortized Population Gibbs Samplers with Neural Sufficient Statistics
- Linear Disentangled Representations and Unsupervised Action Estimation
- REMAX: Relational Representation for Multi-Agent Exploration
- Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples
- Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Images
- Black-Box Autoregressive Density Estimation for State-Space Models
- Path and Bone-Contour Regularized Unpaired MRI-to-CT Translation
- Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning
- Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models
- Generator Surgery for Compressed Sensing
- Semantic Editing On Segmentation Map Via Multi-Expansion Loss
- Local Competition and Stochasticity for Adversarial Robustness in Deep Learning
- Towards to Robust and Generalized Medical Image Segmentation Framework
- Separate In Latent Space: Unsupervised Single Image Layer Separation
- Provably robust deep generative models
- Dynamic Relational Inference in Multi-Agent Trajectories
- I-nteract 2.0: A Cyber-Physical System to Design 3D Models using Mixed Reality Technologies and Deep Learning for Additive Manufacturing
- Factorized Neural Processes for Neural Processes: -Shot Prediction of Neural Responses
- The Pitfall of More Powerful Autoencoders in Lidar-Based Navigation
- S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
- Deep Bayesian Unsupervised Lifelong Learning
- Instance-Dependent Partial Label Learning
- Generative Transition Mechanism to Image-to-Image Translation via Encoded Transformation
- Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness
- Solving deep-learning density functional theory via variational autoencoders
- Correspondence Learning for Controllable Person Image Generation
- Continuous Histogram Loss: Beyond Neural Similarity
- Self-Supervised Sketch-to-Image Synthesis
- Signature-Graph Networks
- Dynamic Routing Networks
- Self-supervised SAR-optical Data Fusion and Land-cover Mapping using Sentinel-1/-2 Images
- Encapsulating models and approximate inference programs in probabilistic modules
- Amortised Learning by Wake-Sleep
- Computer-Assisted Analysis of Biomedical Images
- Variational Knowledge Distillation for Disease Classification in Chest X-Rays
- Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation
- The equivalence between Stein variational gradient descent and black-box variational inference
- Prediction of liquid fuel properties using machine learning models with Gaussian processes and probabilistic conditional generative learning
- A New Distribution on the Simplex with Auto-Encoding Applications
- Gaussian variational approximation with a factor covariance structure
- Generative Feature Replay with Orthogonal Weight Modification for Continual Learning
- Clustered Reinforcement Learning
- Person-in-Context Synthesiswith Compositional Structural Space
- LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning
- Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Latent Chord Labels and Features
- Russian Natural Language Generation: Creation of a Language Modelling Dataset and Evaluation with Modern Neural Architectures
- Neural Crossbreed: Neural Based Image Metamorphosis
- NP-ODE: Neural Process Aided Ordinary Differential Equations for Uncertainty Quantification of Finite Element Analysis
- Database development and exploration of microstructure versus process relationships using variational autoencoders
- Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder
- Long-Term Human Video Generation of Multiple Futures Using Poses
- Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition
- Using Sensory Time-cue to enable Unsupervised Multimodal Meta-learning
- Improving Text to Image Generation using Mode-seeking Function
- Copula-like Variational Inference
- Generative Model without Prior Distribution Matching
- Decoupling Global and Local Representations via Invertible Generative Flows
- Informative Sample Mining Network for Multi-Domain Image-to-Image Translation
- Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck
- Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
- Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
- Variance Constrained Autoencoding
- Generative Locally Linear Embedding
- Variational Auto-Decoder: A Method for Neural Generative Modeling from Incomplete Data
- Explainability-aided Domain Generalization for Image Classification
- The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders
- Imitation Learning of Factored Multi-agent Reactive Models
- D3p -- A Python Package for Differentially-Private Probabilistic Programming
- Causality in Neural Networks -- An Extended Abstract
- LyricJam: A system for generating lyrics for live instrumental music
- Generalized Doubly Reparameterized Gradient Estimators
- Uncertainty estimation for classification and risk prediction on medical tabular data
- Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
- Cellular State Transformations using Generative Adversarial Networks
- The Bayesian Committee Approach for Computational Physics Problems
- Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales
- Fitting Skeletal Models via Graph-based Learning
- No Representation without Transformation
- Top-N: Equivariant set and graph generation without exchangeability
- Online Variational Filtering and Parameter Learning
- LAMP-HQ: A Large-Scale Multi-Pose High-Quality Database and Benchmark for NIR-VIS Face Recognition
- PRRS Outbreak Prediction via Deep Switching Auto-Regressive Factorization Modeling
- Gaussian Embedding of Temporal Networks
- Re-examination of the Role of Latent Variables in Sequence Modeling
- Flow-based Generative Models for Learning Manifold to Manifold Mappings
- DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and Regularization
- Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network
- Learning Compositional Sparse Gaussian Processes with a Shrinkage Prior
- Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
- KernelNet: A Data-Dependent Kernel Parameterization for Deep Generative Modeling
- Unsupervised Object Learning via Common Fate
- Neural Articulated Radiance Field
- Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech
- A Chain Graph Interpretation of Real-World Neural Networks
- Geometric Enclosing Networks
- Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
- Neural Contractive Dynamical Systems
- To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs
- Joints in Random Forests
- Networked Time Series Prediction with Incomplete Data via Generative Adversarial Network
- DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing
- Dependent Multi-Task Learning with Causal Intervention for Image Captioning
- Sim2Real for Self-Supervised Monocular Depth and Segmentation
- Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery
- Efficient and Robust Machine Learning for Real-World Systems
- MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
- CoPE: Conditional image generation using Polynomial Expansions
- Optimal Transport Based Generative Autoencoders
- Vision-driven UAV River Following: Benchmarking with Safe Reinforcement Learning
- Sequential Matrix Completion
- An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
- Graph Embedding VAE: A Permutation Invariant Model of Graph Structure
- A Variational View on Bootstrap Ensembles as Bayesian Inference
- Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion
- Equivariant Deep Dynamical Model for Motion Prediction
- Auto-Encoding for Shared Cross Domain Feature Representation and Image-to-Image Translation
- Mixture factorized auto-encoder for unsupervised hierarchical deep factorization of speech signal
- Digital phase-only holography using deep conditional generative models
- L-Verse: Bidirectional Generation Between Image and Text
- Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks
- SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
- Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
- Double Control Variates for Gradient Estimation in Discrete Latent Variable Models
- Use of Student's t-Distribution for the Latent Layer in a Coupled Variational Autoencoder
- Conditioned Query Generation for Task-Oriented Dialogue Systems
- Latent Network Embedding via Adversarial Auto-encoders
- Fast Hyperparameter Optimization of Deep Neural Networks via Ensembling Multiple Surrogates
- Anomaly Detection in Video Data Based on Probabilistic Latent Space Models
- Approximate Inference for Spectral Mixture Kernel
- Knowledge-Guided Object Discovery with Acquired Deep Impressions
- Low-count Time Series Anomaly Detection
- Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
- Phase Collaborative Network for Two-Phase Medical Image Segmentation
- Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrast
- Ordering Dimensions with Nested Dropout Normalizing Flows
- ATM:Adversarial-neural Topic Model
- Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features
- Automatically Generating Macro Research Reports from a Piece of News
- A Class of Algorithms for General Instrumental Variable Models
- Neural View-Interpolation for Sparse Light Field Video
- Learning Augmentation Distributions using Transformed Risk Minimization
- Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems
- Adversarial sampling of unknown and high-dimensional conditional distributions
- Predictive Uncertainty through Quantization
- Improving Generalization of Sequence Encoder-Decoder Networks for Inverse Imaging of Cardiac Transmembrane Potential
- Reinforcement Evolutionary Learning Method for self-learning
- Learning Robust Variational Information Bottleneck with Reference
- Learning the Compositional Spaces for Generalized Zero-shot Learning
- Off-Policy Policy Gradient Algorithms by Constraining the State Distribution Shift
- Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
- Region-based Energy Neural Network for Approximate Inference
- General Characterization of Agents by States they Visit
- Learning Signal-Agnostic Manifolds of Neural Fields
- Stochastic Variational Inference via Upper Bound
- Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference
- Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes
- Towards robustness under occlusion for face recognition
- Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
- Learning undirected models via query training
- Learning geometry-image representation for 3D point cloud generation
- Learning Calibratable Policies using Programmatic Style-Consistency
- A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models
- On Contrastive Representations of Stochastic Processes
- Open-Ended Content-Style Recombination Via Leakage Filtering
- Local Competition and Uncertainty for Adversarial Robustness in Deep Learning
- Recursive Least Squares Based Refinement Network for the Rollout Trajectory Prediction Methods
- Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation
- C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling
- Amortized variance reduction for doubly stochastic objectives
- Modeling Autonomous Shifts Between Focus State and Mind-Wandering Using a Predictive-Coding-Inspired Variational RNN Model
- Exploring Versatile Prior for Human Motion via Motion Frequency Guidance
- Transferable Task Execution from Pixels through Deep Planning Domain Learning
- Scalable Approximate Inference and Some Applications
- Learning Conditional Invariance through Cycle Consistency
- Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
- Intrinsic motivations and open-ended learning
- Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model
- Bandit algorithms for real-time data capture on large social medias
- Representation Learning for Words and Entities
- Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
- Electrocardio Panorama: Synthesizing New ECG Views with Self-supervision
- Text-to-image Synthesis via Symmetrical Distillation Networks
- Bilevel Continual Learning
- Variational Autoencoders: A Harmonic Perspective
- Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning
- A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
- Masking schemes for universal marginalisers
- TOMA: Topological Map Abstraction for Reinforcement Learning
- Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection
- Learning Portrait Style Representations
- Matching Embeddings for Domain Adaptation
- A Metric for Linear Symmetry-Based Disentanglement
- Autoencoding Under Normalization Constraints
- Noise Attention based Spectrum Anomaly Detection Method for Unauthorized Bands
- Exploring Autoencoder-based Error-bounded Compression for Scientific Data
- Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement
- Variational Learning for Unsupervised Knowledge Grounded Dialogs
- Probabilistic Approach for Road-Users Detection
- Recent Developments in Program Synthesis with Evolutionary Algorithms
- Lifting 2D StyleGAN for 3D-Aware Face Generation
- Residual-Recursion Autoencoder for Shape Illustration Images
- Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
- Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations
- A fast asynchronous MCMC sampler for sparse Bayesian inference
- CRL: Class Representative Learning for Image Classification
- Controllable Gradient Item Retrieval
- Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization
- Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
- Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model
- Harnessing value from data science in business: ensuring explainability and fairness of solutions
- Discrete Action On-Policy Learning with Action-Value Critic
- Assembling Semantically-Disentangled Representations for Predictive-Generative Models via Adaptation from Synthetic Domain
- Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation
- Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference
- Variational Auto Encoder Gradient Clustering
- Regularized Sequential Latent Variable Models with Adversarial Neural Networks
- Improving latent variable descriptiveness with AutoGen
- Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
- Linear, or Non-Linear, That is the Question!
- CookGAN: Meal Image Synthesis from Ingredients
- Holographic Neural Architectures
- Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
- Image Augmentation Using a Task Guided Generative Adversarial Network for Age Estimation on Brain MRI
- Stochastic Variational Bayesian Inference for a Nonlinear Forward Model
- Text Modeling with Syntax-Aware Variational Autoencoders
- Dynamic Narrowing of VAE Bottlenecks Using GECO and L0 Regularization
- Excavate Condition-invariant Space by Intrinsic Encoder
- Neuro-Symbolic Generative Art: A Preliminary Study
- Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning
- Pathwise Derivatives for Multivariate Distributions
- Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example
- Invariance-based Multi-Clustering of Latent Space Embeddings for Equivariant Learning
- Scalable Modeling of Spatiotemporal Data using the Variational Autoencoder: an Application in Glaucoma
- Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI
- Quasi-Newton Quasi-Monte Carlo for variational Bayes
- Synthesising Activity Participations and Scheduling with Deep Generative Machine Learning
- Conditional Graph Neural Processes: A Functional Autoencoder Approach
- Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?
- A Factorial Mixture Prior for Compositional Deep Generative Models
- Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
- Amortized backward variational inference in nonlinear state-space models
- Spherical Sliced-Wasserstein
- Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods
- Generative Creativity: Adversarial Learning for Bionic Design
- 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
- An Empirical Study of Generative Models with Encoders
- -Annealed Variational Autoencoder for glitches
- Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
- Intrinsically motivated option learning: a comparative study of recent methods
- Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech
- Input Dependent Sparse Gaussian Processes
- Copula-Based Normalizing Flows
- Sampling Using Neural Networks for colorizing the grayscale images
- M-estimation with the Trimmed l1 Penalty
- Policy Optimization with Second-Order Advantage Information
- A Deep Generative Artificial Intelligence system to decipher species coexistence patterns
- Untangling urban data signatures: unsupervised machine learning methods for the detection of urban archetypes at the pedestrian scale
- You Never Cluster Alone
- SVP-CF: Selection via Proxy for Collaborative Filtering Data
- Random Sum-Product Forests with Residual Links
- LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
- Variational Monocular Depth Estimation for Reliability Prediction
- Unsupervised Learning of Sequence Representations by Autoencoders
- Memory and attention in deep learning
- Model Order Selection with Variational Autoencoding
- GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization
- Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
- Out-of-Sample Testing for GANs
- ANFIC: Image Compression Using Augmented Normalizing Flows
- Acoustic feature learning using cross-domain articulatory measurements
- Synthesising Multi-Modal Minority Samples for Tabular Data
- Variational Pedestrian Detection
- Fighting Copycat Agents in Behavioral Cloning from Observation Histories
- ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects
- Learning Markov Random Fields for Combinatorial Structures via Sampling through Lovász Local Lemma
- Latent Regression Bayesian Network for Data Representation
- Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms
- Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
- Density Deconvolution with Normalizing Flows
- Towards a Mathematical Theory of Abstraction
- Bitewing Radiography Semantic Segmentation Base on Conditional Generative Adversarial Nets
- Variational Inference over Non-differentiable Cardiac Simulators using Bayesian Optimization
- Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification
- Particle Filter Bridge Interpolation
- Pose2RGBD. Generating Depth and RGB images from absolute positions
- A simulator-based autoencoder for focal plane wavefront sensing
- Symmetric Wasserstein Autoencoders
- Challenges in Vessel Behavior and Anomaly Detection: From Classical Machine Learning to Deep Learning
- Cooperative image captioning
- Semi-supervised multiple testing
- Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking
- Normalizing Flows with Multi-Scale Autoregressive Priors
- Verification of ML Systems via Reparameterization
- A Temporal Kernel Approach for Deep Learning with Continuous-time Information
- f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
- MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning
- High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
- GAN-based Pose-aware Regulation for Video-based Person Re-identification
- IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse
- Unsupervised Disentanglement of Linear-Encoded Facial Semantics
- Learning Invariances for Interpretability using Supervised VAE
- Spatially-weighted Anomaly Detection with Regression Model
- 3D Organ Shape Reconstruction from Topogram Images
- Augmented KRnet for density estimation and approximation
- Fast and Efficient Scene Categorization for Autonomous Driving using VAEs
- HUGE2: a Highly Untangled Generative-model Engine for Edge-computing
- Learning Perceptual Manifold of Fonts
- Graph-Based Method for Anomaly Prediction in Brain Network
- Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation
- Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
- Deep Switching State Space Model (DSM) for Nonlinear Time Series Forecasting with Regime Switching
- Learning GPLVM with arbitrary kernels using the unscented transformation
- Learning Scalable -constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
- Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
- An Overview on Generative AI at Scale with Edge-Cloud Computing
- Information Theoretic Lower Bounds on Negative Log Likelihood
- Discrete Point Flow Networks for Efficient Point Cloud Generation
- An Iterative Closest Points Approach to Neural Generative Models
- Wasserstein Adversarially Regularized Graph Autoencoder
- Learning to Rectify for Robust Learning with Noisy Labels
- My House, My Rules: Learning Tidying Preferences with Graph Neural Networks
- Leveraging Cross Feedback of User and Item Embeddings with Attention for Variational Autoencoder based Collaborative Filtering
- Learning the Solution Manifold in Optimization and Its Application in Motion Planning
- Resolution and Relevance Trade-offs in Deep Learning
- Disentanglement Learning via Topology
- UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning
- Hierarchical Context enabled Recurrent Neural Network for Recommendation
- Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Sampling
- ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision
- Learning Bijective Feature Maps for Linear ICA
- StyleDEM: a Versatile Model for Authoring Terrains
- Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
- Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
- Kernel Mean Matching for Content Addressability of GANs
- Deep Vocoder: Low Bit Rate Compression of Speech with Deep Autoencoder
- Hybrid system identification using switching density networks
- Tessellated Wasserstein Auto-Encoders
- Accelerated Parallel Non-conjugate Sampling for Bayesian Non-parametric Models
- An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE
- Generative networks as inverse problems with fractional wavelet scattering networks
- Artistic Style in Robotic Painting; a Machine Learning Approach to Learning Brushstroke from Human Artists
- OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression
- Variational Bayesian Quantization
- Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE
- Uncovering Obscured Phonon Dynamics from Powder Inelastic Neutron Scattering using Machine Learning
- Beyond traditional assumptions in fair machine learning
- Learning Generative Prior with Latent Space Sparsity Constraints
- End-to-end Generative Zero-shot Learning via Few-shot Learning
- Quasi-symplectic Langevin Variational Autoencoder
- Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
- Unsupervised Learning of Neurosymbolic Encoders
- Synthetic Data Augmentation for Enhancing Harmful Algal Bloom Detection with Machine Learning
- Preventing posterior collapse in variational autoencoders for text generation via decoder regularization
- Improved Training of Sparse Coding Variational Autoencoder via Weight Normalization
- Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
- MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents
- Deep Markov Random Field for Image Modeling
- Ensemble Kalman Variational Objectives: Nonlinear Latent Trajectory Inference with A Hybrid of Variational Inference and Ensemble Kalman Filter
- Privacy-Preserving Self-Taught Federated Learning for Heterogeneous Data
- Discrete Word Embedding for Logical Natural Language Understanding
- Learning Audio-Visual Correlations from Variational Cross-Modal Generation
- Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
- Metric Learning for Anti-Compression Facial Forgery Detection
- torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP
- Controllable Data Augmentation Through Deep Relighting
- CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator
- Parameter estimation in FACS-seq enables high-throughput characterization of phenotypic heterogeneity
- Disentanglement Analysis with Partial Information Decomposition
- Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
- SSN: Soft Shadow Network for Image Compositing
- End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks
- Mixture Representation Learning with Coupled Autoencoders
- Assisting Scene Graph Generation with Self-Supervision
- Conditional Generative Modeling via Learning the Latent Space
- MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
- Relaxed-Responsibility Hierarchical Discrete VAEs
- Variational Determinant Estimation with Spherical Normalizing Flows
- Domain Private and Agnostic Feature for Modality Adaptive Face Recognition
- Invertible Neural BRDF for Object Inverse Rendering
- PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
- EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision
- Detection of Alzheimer's Disease Using Graph-Regularized Convolutional Neural Network Based on Structural Similarity Learning of Brain Magnetic Resonance Images
- Structure-Aware Human-Action Generation
- StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations
- Longitudinal Self-Supervised Learning
- Learning to infer in recurrent biological networks
- Cross-Domain Latent Modulation for Variational Transfer Learning
- Quantifying and Learning Linear Symmetry-Based Disentanglement
- Exploration-Exploitation Motivated Variational Auto-Encoder for Recommender Systems
- LiveMap: Real-Time Dynamic Map in Automotive Edge Computing
- Regularization with Latent Space Virtual Adversarial Training
- Analyzing the Hidden Activations of Deep Policy Networks: Why Representation Matters
- Class-Conditional Compression and Disentanglement: Bridging the Gap between Neural Networks and Naive Bayes Classifiers
- Controlling for sparsity in sparse factor analysis models: adaptive latent feature sharing for piecewise linear dimensionality reduction
- NeuralQAAD: An Efficient Differentiable Framework for High Resolution Point Cloud Compression
- Non-Asymptotic Performance Guarantees for Neural Estimation of -Divergences
- Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
- Learning Consistent Deep Generative Models from Sparse Data via Prediction Constraints
- Unsupervised Neural Hidden Markov Models with a Continuous latent state space
- The Implicit Metropolis-Hastings Algorithm
- DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning
- Spatiotemporal Pattern Mining for Nowcasting Extreme Earthquakes in Southern California
- Neighbor Embedding Variational Autoencoder
- Out-of-Distribution Detection of Melanoma using Normalizing Flows
- Joint Estimation of Image Representations and their Lie Invariants
- Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization
- Meta-Learning with Variational Bayes
- Coupled Variational Recurrent Collaborative Filtering
- Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
- PAUL: Procrustean Autoencoder for Unsupervised Lifting
- Learning Graph-Based Priors for Generalized Zero-Shot Learning
- WakaVT: A Sequential Variational Transformer for Waka Generation
- Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
- Variational Deep Image Denoising
- A Modified Convolutional Network for Auto-encoding based on Pattern Theory Growth Function
- The backpropagation-based recollection hypothesis: Backpropagated action potentials mediate recall, imagination, language understanding and naming
- Towards GANs' Approximation Ability
- Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach
- Bayesian Quadrature on Riemannian Data Manifolds
- Defense Through Diverse Directions
- A Generative Learning Approach for Spatio-temporal Modeling in Connected Vehicular Network
- Hierarchical Models: Intrinsic Separability in High Dimensions
- Multi-View Image-to-Image Translation Supervised by 3D Pose
- MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
- Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
- Incremental Learning from Scratch for Task-Oriented Dialogue Systems
- Autonomous learning of multiple, context-dependent tasks
- Transductive Zero-Shot Learning by Decoupled Feature Generation
- Deep Variational Luenberger-type Observer for Stochastic Video Prediction
- Planning with Expectation Models for Control
- Modeling Graph Node Correlations with Neighbor Mixture Models
- IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay
- Lossless Compression with Latent Variable Models
- Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
- DEFT: Distilling Entangled Factors by Preventing Information Diffusion
- Modeling Grasp Motor Imagery through Deep Conditional Generative Models
- Stochastic Talking Face Generation Using Latent Distribution Matching
- Bayesian Sparsification Methods for Deep Complex-valued Networks
- Training End-to-end Single Image Generators without GANs
- 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
- Probabilistic Trust Intervals for Out of Distribution Detection
- Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models
- Deep Koopman-based Control of Quality Variation in Multistage Manufacturing Systems
- Learning Informative Representations of Biomedical Relations with Latent Variable Models
- NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps
- Inverse Design of Quantum Holograms in Three-Dimensional Nonlinear Photonic Crystals
- Lipschitz standardization for multivariate learning
- Lightweight Data Fusion with Conjugate Mappings
- Variational Inference with Numerical Derivatives: variance reduction through coupling
- Gradient Boosted Normalizing Flows
- AriEL: volume coding for sentence generation
- Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit
- End-To-End Dilated Variational Autoencoder with Bottleneck Discriminative Loss for Sound Morphing -- A Preliminary Study
- Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
- Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation
- Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks
- Multi-Decoder RNN Autoencoder Based on Variational Bayes Method
- A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion
- Medical data wrangling with sequential variational autoencoders
- Bayesian Subspace HMM for the Zerospeech 2020 Challenge
- Minority Class Oversampling for Tabular Data with Deep Generative Models
- Unsupervised Program Synthesis for Images By Sampling Without Replacement
- Planning from Images with Deep Latent Gaussian Process Dynamics
- Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
- Controllable Emotion Transfer For End-to-End Speech Synthesis
- A Block-based Generative Model for Attributed Networks Embedding
- Anomalous sound detection based on interpolation deep neural network
- SINVAD: Search-based Image Space Navigation for DNN Image Classifier Test Input Generation
- Unsupposable Test-data Generation for Machine-learned Software
- Model-free Policy Learning with Reward Gradients
- Latent Multi-Criteria Ratings for Recommendations
- Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems
- Debiasing a First-order Heuristic for Approximate Bi-level Optimization
- VCE: Variational Convertor-Encoder for One-Shot Generalization
- Discriminative, Generative and Self-Supervised Approaches for Target-Agnostic Learning
- Continuous normalizing flows on manifolds
- Testing for Typicality with Respect to an Ensemble of Learned Distributions
- Deep Automodulators
- OPAL-Net: A Generative Model for Part-based Object Layout Generation
- Automated Dependence Plots
- Sparsely Activated Networks: A new method for decomposing and compressing data
- Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings
- Auto-encoding brain networks with applications to analyzing large-scale brain imaging datasets
- Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis
- Eccentric Regularization: Minimizing Hyperspherical Energy without explicit projection
- Noise Robust Generative Adversarial Networks
- Towards Better Understanding of Disentangled Representations via Mutual Information
- Quantized Variational Inference
- Deep Clustering of Compressed Variational Embeddings
- Supervised Encoding for Discrete Representation Learning
- Statistical Guarantees for Transformation Based Models with Applications to Implicit Variational Inference
- A New Perspective on Learning Context-Specific Independence
- Zero-Shot Recognition via Optimal Transport
- GO Hessian for Expectation-Based Objectives
- TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction
- Deep Goal-Oriented Clustering
- Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems
- Bridging the Gap Between -GANs and Wasserstein GANs
- Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
- EvoVGM: a Deep Variational Generative Model for Evolutionary Parameter Estimation
- Modeling continuous-time stochastic processes using -Curve mixtures
- Efficient training for future video generation based on hierarchical disentangled representation of latent variables
- Anomaly Detection with Inexact Labels
- Amortized Variational Deep Q Network
- Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection
- Attribute-controlled face photo synthesis from simple line drawing
- Learning Priors for Adversarial Autoencoders
- Semi-supervised Autoencoding Projective Dependency Parsing
- Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
- Lattice Representation Learning
- Interpreting Graph Drawing with Multi-Agent Reinforcement Learning
- Data Augmentation with Variational Autoencoders and Manifold Sampling
- Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
- GAN pretraining for deep convolutional autoencoders applied to Software-based Fingerprint Presentation Attack Detection
- Learning What To Do by Simulating the Past
- SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment
- Decoder-free Robustness Disentanglement without (Additional) Supervision
- Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning
- VAE-based Domain Adaptation for Speaker Verification
- Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL
- Compositional Video Prediction
- A Practical & Unified Notation for Information-Theoretic Quantities in ML
- A Multi-Implicit Neural Representation for Fonts
- The FMRIB Variational Bayesian Inference Tutorial II: Stochastic Variational Bayes
- Self-Reflective Variational Autoencoder
- Towards Robust Classification with Deep Generative Forests
- 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?
- Low-Variance Policy Gradient Estimation with World Models
- Evidential Turing Processes
- TD-GEN: Graph Generation With Tree Decomposition
- Coarse Grained Exponential Variational Autoencoders
- Learning and Generalization in Overparameterized Normalizing Flows
- Visual-Relation Conscious Image Generation from Structured-Text
- Probabilistic task modelling for meta-learning
- ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models
- Pulling back information geometry
- Improve variational autoEncoder with auxiliary softmax multiclassifier
- Channel Decomposition into Painting Actions
- EMFlow: Data Imputation in Latent Space via EM and Deep Flow Models
- Robust Disentanglement of a Few Factors at a Time
- A Linear Systems Theory of Normalizing Flows
- Learning Identity-Preserving Transformations on Data Manifolds
- Large-Angle Convergent-Beam Electron Diffraction Patterns via Conditional Generative Adversarial Networks
- Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation
- DSBERT:Unsupervised Dialogue Structure learning with BERT
- Survival-oriented embeddings for improving accessibility to complex data structures
- Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations
- Towards Verified Stochastic Variational Inference for Probabilistic Programs
- Node Attribute Generation on Graphs
- Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
- Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
- Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
- Improving Generative Adversarial Networks with Local Coordinate Coding
- Cascade Decoders-Based Autoencoders for Image Reconstruction
- PatchGame: Learning to Signal Mid-level Patches in Referential Games
- Interactive Optimization of Generative Image Modeling using Sequential Subspace Search and Content-based Guidance
- Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages
- Towards Representation Learning with Tractable Probabilistic Models
- MLMOD: Machine Learning Methods for Data-Driven Modeling in LAMMPS
- VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
- Learning Correlated Latent Representations with Adaptive Priors
- The pursuit of beauty: Converting image labels to meaningful vectors
- A Neural-Symbolic Framework for Mental Simulation
- Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent Modeling
- P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening
- Stochastic Function Norm Regularization of Deep Networks
- DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction
- Neural Scene Decoration from a Single Photograph
- Fine-Grained Control of Artistic Styles in Image Generation
- Conditional Deep Gaussian Processes: empirical Bayes hyperdata learning
- Group-disentangled Representation Learning with Weakly-Supervised Regularization
- Differentiable TAN Structure Learning for Bayesian Network Classifiers
- Capturing Evolution Genes for Time Series Data
- Investigating the Effect of Intraclass Variability in Temporal Ensembling
- Towards Stable Imbalanced Data Classification via Virtual Big Data Projection
- DiverseNet: When One Right Answer is not Enough
- Missingness Augmentation: A General Approach for Improving Generative Imputation Models
- Quantization-Based Regularization for Autoencoders
- Information Bottleneck Approach to Spatial Attention Learning
- Sufficient Dimension Reduction for High-Dimensional Regression and Low-Dimensional Embedding: Tutorial and Survey
- Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation
- PixelPyramids: Exact Inference Models from Lossless Image Pyramids
- Implicit Generative Copulas
- MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
- GaussED: A Probabilistic Programming Language for Sequential Experimental Design
- The Neglected Sibling: Isotropic Gaussian Posterior for VAE
- Supervised Topological Maps
- Diffusion Normalizing Flow
- Multiple Style Transfer via Variational AutoEncoder
- Visualization of AE's Training on Credit Card Transactions with Persistent Homology
- Computational Analysis of Deformable Manifolds: from Geometric Modelling to Deep Learning
- Normalized Diversification
- Entropic Issues in Likelihood-Based OOD Detection
- Perturbative estimation of stochastic gradients
- Generative latent neural models for automatic word alignment
- 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
- Point-to-Point Video Generation
- A comparison of classical and variational autoencoders for anomaly detection
- DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
- Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning
- Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
- Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes
- Contrastive String Representation Learning using Synthetic Data
- MFPC-Net: Multi-fidelity Physics-Constrained Neural Process
- Mixture-of-Variational-Experts for Continual Learning
- Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
- Realistic molecule optimization on a learned graph manifold
- Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent
- Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
- Intelligent image synthesis to attack a segmentation CNN using adversarial learning
- Information Theoretic Structured Generative Modeling
- Semi-supervised voice conversion with amortized variational inference
- CoRGi: Content-Rich Graph Neural Networks with Attention
- Differential Similarity in Higher Dimensional Spaces: Theory and Applications
- Multilevel Monte Carlo Variational Inference
- Manifold Optimization Assisted Gaussian Variational Approximation
- Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models
- On the Limitations of Multimodal VAEs
- Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
- ErrorNet: Learning error representations from limited data to improve vascular segmentation
- Neural Estimation of Statistical Divergences
- Collaging Class-specific GANs for Semantic Image Synthesis
- Learning disentangled representation for classical models
- Investigating Semi-Supervised Learning Algorithms in Text Datasets
- Video Autoencoder: self-supervised disentanglement of static 3D structure and motion
- Reconsidering Analytical Variational Bounds for Output Layers of Deep Networks
- High Mutual Information in Representation Learning with Symmetric Variational Inference
- Towards Learning to Imitate from a Single Video Demonstration
- Stacked Wasserstein Autoencoder
- Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical Systems
- Barlow Graph Auto-Encoder for Unsupervised Network Embedding
- Relay Variational Inference: A Method for Accelerated Encoderless VI
- Irregular Convolutional Auto-Encoder on Point Clouds
- Using Neural Networks for Programming by Demonstration
- Bayesian Neural Decoding Using A Diversity-Encouraging Latent Representation Learning Method
- Contrastive Active Inference
- On-Demand Video Dispatch Networks: A Scalable End-to-End Learning Approach
- Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
- Efficient Modelling Across Time of Human Actions and Interactions
- On the Generative Utility of Cyclic Conditionals
- Causal Discovery from Conditionally Stationary Time Series
- Label-Conditioned Next-Frame Video Generation with Neural Flows
- Domain Mismatch Robust Acoustic Scene Classification using Channel Information Conversion
- -Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap
- Physics-Informed Deep Learning Characterizes Morphodynamics of Asian Soybean Rust Disease
- Decoupling feature propagation from the design of graph auto-encoders
- LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial Network
- Learning to Learn Graph Topologies
- Generating synthetic transactional profiles
- Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
- Lossless Compression with Probabilistic Circuits
- Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
- Language coverage and generalization in RNN-based continuous sentence embeddings for interacting agents
- Sequential Variational Autoencoders for Collaborative Filtering
- Intuitive Shape Editing in Latent Space
- Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features
- PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network
- Layered Controllable Video Generation
- A General Divergence Modeling Strategy for Salient Object Detection
- DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
- Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods
- Multi-way Clustering and Discordance Analysis through Deep Collective Matrix Tri-Factorization
- SimVAE: Simulator-Assisted Training forInterpretable Generative Models
- Learning mappings onto regularized latent spaces for biometric authentication
- Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
- Image-Based Reconstruction for a 3D-PFHS Heat Transfer Problem by ReConNN
- Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
- From Persistent Homology to Reinforcement Learning with Applications for Retail Banking
- Representation Learning: A Statistical Perspective
- Discovering Latent Representations of Relations for Interacting Systems
- Efficient Approximate Inference with Walsh-Hadamard Variational Inference
- Local Disentanglement in Variational Auto-Encoders Using Jacobian Regularization
- Generating new pictures in complex datasets with a simple neural network
- 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
- Explainability Requires Interactivity
- 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
- 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
- 3-Dimensional Deep Learning with Spatial Erasing for Unsupervised Anomaly Segmentation in Brain MRI
- Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes
- Generation Drawing/Grinding Trajectoy Based on Hierarchical CVAE
- Group-based Learning of Disentangled Representations with Generalizability for Novel Contents
- Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks
- Encoding Causal Macrovariables
- Graph Convolutional Memory using Topological Priors
- Bayesian task embedding for few-shot Bayesian optimization
- Roof Age Determination for the Automated Site-Selection of Rooftop Solar
- Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension
- LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies
- Generating Object Stamps
- Neural network based order parameter for phase transitions and its applications in high-entropy alloys
- MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
- Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees
- Stochastic Contrastive Learning
- Self-supervised similarity search for large scientific datasets
- On the Practical Consistency of Meta-Reinforcement Learning Algorithms
- Unsupervised Feature Learning for Online Voltage Stability Evaluation and Monitoring Based on Variational Autoencoder
- Stay Positive: Non-Negative Image Synthesis for Augmented Reality
- Deep Measurement Updates for Bayes Filters
- The RenAIssance: Caption-Guided Diffusion Models for Historical-Art Visual Media
- Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
- Forward Operator Estimation in Generative Models with Kernel Transfer Operators
- From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
- Representation Learning for Efficient and Effective Similarity Search and Recommendation
- 3D-Aware Semantic-Guided Generative Model for Human Synthesis
- Domain Adaptation for Deviating Acquisition Protocols in CNN-based Lesion Classification on Diffusion-Weighted MR Images
- Probabilistic Re-aggregation Algorithm [First Draft]
- ConRPG: Paraphrase Generation using Contexts as Regularizer
- Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates
- Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
- Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation
- GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction
- Synthesizing Photorealistic Images with Deep Generative Learning
- Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
- Enhancing audio quality for expressive Neural Text-to-Speech
- Flow-based SVDD for anomaly detection
- Measuring global properties of neural generative model outputs via generating mathematical objects
- Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning
- NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps
- Multilevel Monte Carlo estimation of log marginal likelihood
- Applying the Information Bottleneck Principle to Prosodic Representation Learning
- Analysis of ODE2VAE with Examples
- DGST : Discriminator Guided Scene Text detector
- Joint Wasserstein Distribution Matching
- Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction
- What Remains of Visual Semantic Embeddings
- A Robust Speaker Clustering Method Based on Discrete Tied Variational Autoencoder
- Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error
- Type I Attack for Generative Models
- Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective
- Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
- Introducing: DeepHead, Wide-band Electromagnetic Imaging Paradigm
- Network Learning with Local Propagation
- Replicating Active Appearance Model by Generator Network
- Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
- Automatic Quantification of Volumes and Biventricular Function in Cardiac Resonance. Validation of a New Artificial Intelligence Approach
- Joint Mapping and Calibration via Differentiable Sensor Fusion
- A Survey on Role-Oriented Network Embedding
- Unsupervised Skill-Discovery and Skill-Learning in Minecraft
- Action2video: Generating Videos of Human 3D Actions
- Enhanced Variational Inference with Dyadic Transformation
- Learning Aesthetic Layouts via Visual Guidance
- A Closer Look at the Adversarial Robustness of Information Bottleneck Models
- Lifelong Twin Generative Adversarial Networks
- Semantic and Geometric Unfolding of StyleGAN Latent Space
- Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
- Unsupervised Representation Learning via Neural Activation Coding
- Efficient Model Identification for Tensegrity Locomotion
- Variational Composite Autoencoders
- On Inductive Biases for Machine Learning in Data Constrained Settings
- When Can Neural Networks Learn Connected Decision Regions?
- Bi-Discriminator Class-Conditional Tabular GAN
- X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering
- Convolutional Normalizing Flows for Deep Gaussian Processes
- TzK: Flow-Based Conditional Generative Model
- Dynamic Variational Autoencoders for Visual Process Modeling
- Reparameterized Sampling for Generative Adversarial Networks
- Diverse Exploration via Conjugate Policies for Policy Gradient Methods
- Dual Adversarial Variational Embedding for Robust Recommendation
- Leveraging Hidden Structure in Self-Supervised Learning
- Generating the Graph Gestalt: Kernel-Regularized Graph Representation Learning
- A Mechanism for Producing Aligned Latent Spaces with Autoencoders
- Efficient State-space Exploration in Massively Parallel Simulation Based Inference
- Improving Generalization of Deep Networks for Inverse Reconstruction of Image Sequences
- Coulomb Autoencoders
- Based on Graph-VAE Model to Predict Student's Score
- GILBO: One Metric to Measure Them All
- Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy
- WiSE-ALE: Wide Sample Estimator for Approximate Latent Embedding
- MVAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood
- The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
- What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations
- Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
- Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
- High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling
- Approximate Inference via Fibrations of Statistical Games
- Toroidal AutoEncoder
- Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
- Learning in Sparse Rewards settings through Quality-Diversity algorithms
- Towards bio-inspired unsupervised representation learning for indoor aerial navigation
- Learning to Organize Knowledge and Answer Questions with N-Gram Machines
- Learning Sparsity of Representations with Discrete Latent Variables
- A Variational Auto-Encoder Model for Stochastic Point Processes
- Generating Data Augmentation samples for Semantic Segmentation of Salt Bodies in a Synthetic Seismic Image Dataset
- Asymmetric Variational Autoencoders
- Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure
- Processsing Simple Geometric Attributes with Autoencoders
- Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
- Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
- Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition
- Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization
- Discrete Auto-regressive Variational Attention Models for Text Modeling
- Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation
- Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
- Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
- Boosting Generative Models by Leveraging Cascaded Meta-Models
- Efficient Deep Gaussian Process Models for Variable-Sized Input
- Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
- Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation
- A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
- Semi-supervised Learning with Contrastive Predicative Coding
- Learning by stochastic serializations
- Disentangled Variational Information Bottleneck for Multiview Representation Learning
- Understanding the Behaviour of the Empirical Cross-Entropy Beyond the Training Distribution
- A Self-Supervised Framework for Function Learning and Extrapolation
- 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
- Automatic design of novel potential 3CL and PL inhibitors
- On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
- Fast Non-Parametric Tests of Relative Dependency and Similarity
- Accelerating Continuous Normalizing Flow with Trajectory Polynomial Regularization
- From the Expectation Maximisation Algorithm to Autoencoded Variational Bayes
- HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception
- Exploiting Uncertainty of Loss Landscape for Stochastic Optimization
- 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
- NEMR: Network Embedding on Metric of Relation
- Neural Topic Models with Survival Supervision: Jointly Predicting Time-to-Event Outcomes and Learning How Clinical Features Relate
- Improving Uncertainty Calibration via Prior Augmented Data
- MCMC-Interactive Variational Inference
- Efficient Semi-Implicit Variational Inference
- Adversarial Machine Learning in Text Analysis and Generation
- Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
- Variational Bayesian Framework for Advanced Image Generation with Domain-Related Variables
- Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation
- Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
- Automatic Feature Extraction for Heartbeat Anomaly Detection
- Learning to Shift Attention for Motion Generation
- Uncertainty in Neural Processes
- Contextualisation of eCommerce Users
- Formalising Concepts as Grounded Abstractions
- Data-driven Regularized Inference Privacy
- Domain Adaptation for Learning Generator from Paired Few-Shot Data
- Transformations between deep neural networks
- A Tutorial on the Mathematical Model of Single Cell Variational Inference
- Spectral Synthesis for Satellite-to-Satellite Translation
- Atlas Based Representation and Metric Learning on Manifolds
- One-element Batch Training by Moving Window
- Covariate Distribution Aware Meta-learning
- Compressed Sensing via Measurement-Conditional Generative Models
- Learning to Reconstruct and Segment 3D Objects
- How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
- Fisher Auto-Encoders
- OffCon: What is state of the art anyway?
- Approximation Based Variance Reduction for Reparameterization Gradients
- Continual Density Ratio Estimation in an Online Setting
- Recurrent Flow Networks: A Recurrent Latent Variable Model for Density Modelling of Urban Mobility
- Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring
- A Generalised Linear Model Framework for -Variational Autoencoders based on Exponential Dispersion Families
- Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment