Auto-Encoding Variational Bayes

2013/12/20 by Diederik P. Kingma, Diederik P Kingma, Max Welling +2 · 3 voices · 15,631 citations
Computer Science · Mathematics · #Algorithm #Applied mathematics #Approximate inference #Artificial intelligence #Bayes' theorem #Bayesian Methods and Mixture Models #Bayesian inference #Bayesian probability #Computer science #Differentiable function #Estimator #Gaussian Processes and Bayesian Inference #Inference #Latent variable #Machine Learning and Algorithms #Mathematics #Posterior probability #Probabilistic logic #Statistics #Upper and lower bounds

paper · pdf · open access · doi:10.48550/arxiv.1312.6114

published in UvA-DARE (University of Amsterdam) (University of Amsterdam)

openalex publication_date 2013/12/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

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.

Cited by

• Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
• Low Distortion Block-Resampling with Spatially Stochastic Networks
• From superposition to sparse codes: interpretable representations in neural networks
• Bayesian Transformer Language Models for Speech Recognition
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments
• Linear, or Non-Linear, That is the Question!
• Graph Learning Network: A Structure Learning Algorithm
• Based on Graph-VAE Model to Predict Student's Score
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• Random Feature Attention
• Variational Autoencoding of PDE Inverse Problems
• Distributed Weight Consolidation: A Brain Segmentation Case Study
• Probabilistic Embeddings for Cross-Modal Retrieval
• Molecular Hypergraph Grammar with its Application to Molecular Optimization
• Neural Network architectures to classify emotions in Indian Classical Music
• Unsupervised Object Learning via Common Fate
• Regularized Sequential Latent Variable Models with Adversarial Neural Networks
• Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
• Towards causal generative scene models via competition of experts
• Understanding Overparameterization in Generative Adversarial Networks
• GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
• TopoResNet: A hybrid deep learning architecture and its application to skin lesion classification
• Kamino: Constraint-Aware Differentially Private Data Synthesis
• A Variational Perspective on Diffusion-Based Generative Models and Score Matching
• The Power Spherical distribution
• Transitive Invariance for Self-supervised Visual Representation Learning
• A Combined Deep Learning based End-to-End Video Coding Architecture for YUV Color Space
• Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning
• Icebreaker: Element-wise Active Information Acquisition with Bayesian\n Deep Latent Gaussian Model
• Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression
• Multi-class Gaussian Process Classification with Noisy Inputs
• "Best-of-Many-Samples" Distribution Matching
• Attribute2Image: Conditional Image Generation from Visual Attributes
• VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
• Capturing Evolution Genes for Time Series Data
• Variational Dropout and the Local Reparameterization Trick
• SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery
• Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)
• Constrained Graph Variational Autoencoders for Molecule Design
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• TzK: Flow-Based Conditional Generative Model
• Maximum Likelihood Training of Score-Based Diffusion Models
• Explaining Predictions by Approximating the Local Decision Boundary
• Short-Term Traffic Flow Prediction Using Variational LSTM Networks
• On the Discrepancy between Density Estimation and Sequence Generation
• A Study on the Autoregressive and non-Autoregressive Multi-label Learning
• Jointly Deep Multi-View Learning for Clustering Analysis
• Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
• GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing
• Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation
• An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection
• Decoder-free Robustness Disentanglement without (Additional) Supervision
• Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders
• Semantics, Representations and Grammars for Deep Learning
• Boundless: Generative Adversarial Networks for Image Extension
• White Paper Machine Learning in Certified Systems
• Diverse Video Generation using a Gaussian Process Trigger
• Deep diffusion models for seismic processing
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• Exploring Bias in GAN-based Data Augmentation for Small Samples
• Estimating Gradients for Discrete Random Variables by Sampling without Replacement
• Causal Effect Variational Autoencoder with Uniform Treatment
• On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
• Symmetries and control in generative neural nets
• Attention Map-guided Two-stage Anomaly Detection using Hard Augmentation
• Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models
• Hidden Markov Neural Networks
• MFPC-Net: Multi-fidelity Physics-Constrained Neural Process
• Soft then Hard: Rethinking the Quantization in Neural Image Compression
• Two Methods For Wild Variational Inference
• DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting
• Convolutional Generation of Textured 3D Meshes
• Latent Variables on Spheres for Autoencoders in High Dimensions
• Generative Ratio Matching Networks
• Variational Auto-Encoder Architectures that Excel at Causal Inference
• Disentangling Physical Parameters for Anomalous Sound Detection Under Domain Shifts
• Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
• SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
• Learning Signal-Agnostic Manifolds of Neural Fields
• BasisVAE: Translation-invariant feature-level clustering with Variational Autoencoders
• TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
• Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes
• Multilevel Monte Carlo Variational Inference
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
• Learning Human Objectives by Evaluating Hypothetical Behavior
• Joint Wasserstein Distribution Matching
• Towards Stable Imbalanced Data Classification via Virtual Big Data Projection
• Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages
• ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imaging
• Intuitive Shape Editing in Latent Space
• A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models
• Neural Scene Decoration from a Single Photograph
• Developing Bug-Free Machine Learning Systems With Formal Mathematics
• Predicting Visual Memory Schemas with Variational Autoencoders
• On the Opportunities and Risks of Foundation Models
• Generalized Variational Inference: Three arguments for deriving new Posteriors
• Crystal Diffusion Variational Autoencoder for Periodic Material Generation
• Learning to Fly via Deep Model-Based Reinforcement Learning
• Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
• Learning Implicit Fields for Generative Shape Modeling
• Strategic Attentive Writer for Learning Macro-Actions
• Intelligent image synthesis to attack a segmentation CNN using adversarial learning
• A Deep Generative Artificial Intelligence system to decipher species coexistence patterns
• Text-to-image Synthesis via Symmetrical Distillation Networks
• Distance-Based Learning from Errors for Confidence Calibration
• Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
• GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
• Statistical Inference for Generative Models with Maximum Mean Discrepancy
• Learning Actionable Representations with Goal-Conditioned Policies
• Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness
• Glow: Generative Flow with Invertible 1x1 Convolutions
• How good is my GAN?
• Shared Nodes of Overlapping Communities in Complex Networks
• Early Inference in Energy-Based Models Approximates Back-Propagation
• Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
• Robotic Motion Planning using Learned Critical Sources and Local Sampling
• NAS-Bench-x11 and the Power of Learning Curves
• On the Generative Utility of Cyclic Conditionals
• Learning Sparse Neural Networks through L₀ Regularization
• Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Semi-Supervised Learning with Deep Generative Models
• X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering
• Variational Graph Auto-Encoders
• Deep Conversational Recommender in Travel
• Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
• On Energy-Based Models with Overparametrized Shallow Neural Networks
• Self-attention fusion and adaptive continual updating for multimodal federated learning with heterogeneous data
• RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Learning to Assimilate in Chaotic Dynamical Systems
• Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
• Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
• MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
• Neural Baselines for Word Alignment
• Neural Ordinary Differential Equations
• General Characterization of Agents by States they Visit
• Stacked Wasserstein Autoencoder
• Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
• Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
• Reweighted Expectation Maximization
• Inducing Interpretable Representations with Variational Autoencoders
• ErrorNet: Learning error representations from limited data to improve vascular segmentation
• Towards Empirical Sandwich Bounds on the Rate-Distortion Function
• Neural network based order parameter for phase transitions and its applications in high-entropy alloys
• Task-adaptive Neural Process for User Cold-Start Recommendation
• A Variational View on Bootstrap Ensembles as Bayesian Inference
• Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
• Unsupervised Model Selection for Variational Disentangled Representation Learning
• Controllable Emotion Transfer For End-to-End Speech Synthesis
• TherML: Thermodynamics of Machine Learning
• Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
• Symmetric Variational Autoencoder and Connections to Adversarial Learning
• You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
• Privacy-Preserving Self-Taught Federated Learning for Heterogeneous Data
• From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
• High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models
• HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
• A Non-Parametric Test to Detect Data-Copying in Generative Models
• Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
• Towards Robust Classification with Deep Generative Forests
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
• Grasping Field: Learning Implicit Representations for Human Grasps
• Disentangling by Partitioning: A Representation Learning Framework for Multimodal Sensory Data
• Tractable Regularization of Probabilistic Circuits
• Towards universal neural nets: Gibbs machines and ACE
• Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
• UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
• FREE: Feature Refinement for Generalized Zero-Shot Learning
• Cellular State Transformations using Generative Adversarial Networks
• On the Transfer of Disentangled Representations in Realistic Settings
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
• A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
• Uncertainty-guided Model Generalization to Unseen Domains
• Lipschitz standardization for multivariate learning
• Content and Style Aware Generation of Text-line Images for Handwriting Recognition
• Learning Hierarchical Priors in VAEs
• Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
• Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
• A Probabilistic U-Net for Segmentation of Ambiguous Images
• LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
• Adversarial Autoencoders
• Mastering Atari with Discrete World Models
• A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion
• Autonomous Vehicles Drive into Shared Spaces: eHMI Design Concept Focusing on Vulnerable Road Users
• WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
• Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
• Hybrid Modeling of Photoplethysmography for Non-invasive Monitoring of Cardiovascular Parameters
• Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
• Artificial Intelligence-Enabled Spirometry for Early Detection of Right Heart Failure
• TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing
• DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving
• A Deep Reinforcement Learning Chatbot
• Conditional Diffusion Model for Multi-Agent Dynamic Task Decomposition
• Dimension vs. Precision: A Comparative Analysis of Autoencoders and Quantization for Efficient Vector Retrieval on BEIR SciFact
• TacEleven: generative tactic discovery for football open play
• Invertible Neural BRDF for Object Inverse Rendering
• Vector-Quantized Timbre Representation
• Constrained Bayesian Optimization for Automatic Chemical Design
• MMGAN: Generative Adversarial Networks for Multi-Modal Distributions
• Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
• Sub-word Level Lip Reading With Visual Attention
• Predicting with High Correlation Features
• TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions
• DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images
• Domain Generalization via Inference-time Label-Preserving Target Projections
• MineGAN: effective knowledge transfer from GANs to target domains with few images
• Learning to Generate and Reconstruct 3D Meshes with only 2D Supervision
• Learning Compositional Radiance Fields of Dynamic Human Heads
• Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction
• An Evaluation of Representation Learning Methods in Particle Physics Foundation Models
• GraphDF: A Discrete Flow Model for Molecular Graph Generation
• Learning Audio-Visual Correlations from Variational Cross-Modal Generation
• Variational Auto-Encoder: not all failures are equal
• A Robust Speaker Clustering Method Based on Discrete Tied Variational Autoencoder
• Variational Sequential Monte Carlo
• Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders
• Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Modular Action Concept Grounding in Semantic Video Prediction
• LiveMap: Real-Time Dynamic Map in Automotive Edge Computing
• Disentangling by Factorising
• Representation Learning for Efficient and Effective Similarity Search and Recommendation
• Leveraging Hidden Structure in Self-Supervised Learning
• Recent Advances in Convolutional Neural Networks
• Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
• Disentangled Representation Learning and Generation with Manifold Optimization
• Stochastic Variational Inference via Upper Bound
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms
• Walsh-Hadamard Variational Inference for Bayesian Deep Learning
• FitVid: Overfitting in Pixel-Level Video Prediction
• Structured Dropout Variational Inference for Bayesian Neural Networks
• Towards White-box Benchmarks for Algorithm Control
• Towards Representation Learning with Tractable Probabilistic Models
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Variational Bayesian Optimal Experimental Design
• A Variational Approach to Unsupervised Sentiment Analysis
• Deep Image Prior
• Improving Query Efficiency of Black-box Adversarial Attack
• Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey
• Designed to Spread: A Generative Approach to Enhance Information Diffusion
• DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection
• SculptDrug : A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design
• Hybrid VAE: Improving Deep Generative Models using Partial Observations
• Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
• Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
• Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
• VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
• LiDAR-GS++:Improving LiDAR Gaussian Reconstruction via Diffusion Priors
• Reinforcement Learning through Active Inference
• Deep Active Inference
• TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy Modalities
• Arcee: Differentiable Recurrent State Chain for Generative Vision Modeling with Mamba SSMs
• Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design
• Physics informed Transformer-VAE for biophysical parameter estimation: PROSAIL model inversion in Sentinel-2 imagery
• Out-of-Context Misinformation Detection via Variational Domain-Invariant Learning with Test-Time Training
• GPDM: Generation-Prior Diffusion Model for Accelerated Direct Attenuation and Scatter Correction of Whole-body 18F-FDG PET
• Annealed Flow Transport Monte Carlo
• Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
• Rate-Regularization and Generalization in VAEs
• Robust Compressed Sensing MRI with Deep Generative Priors
• Orientation-Disentangled Unsupervised Representation Learning for Computational Pathology
• not-MIWAE: Deep Generative Modelling with Missing not at Random Data
• Automatic Variational ABC
• Minibatch optimal transport distances; analysis and applications
• Learning Image Representations by Completing Damaged Jigsaw Puzzles
• Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models
• Black-box α-divergence Minimization
• Causal Discovery from Conditionally Stationary Time Series
• Multi-Granularity Mutual Refinement Network for Zero-Shot Learning
• PC-Diffusion: Aligning Diffusion Models with Human Preferences via Preference Classifier
• Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling
• TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling
• Pixel Recurrent Neural Networks
• Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning
• VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling
• Hamiltonian Variational Auto-Encoder
• Latent ODEs for Irregularly-Sampled Time Series
• Grammar Variational Autoencoder
• RelightMaster: Precise Video Relighting with Multi-plane Light Images
• Clockwork Variational Autoencoders
• Learnable Explicit Density for Continuous Latent Space and Variational Inference
• Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
• The Causal Round Trip: Generating Authentic Counterfactuals by Eliminating Information Loss
• AStF: Motion Style Transfer via Adaptive Statistics Fusor
• Autoencoding Dynamics: Topological Limitations and Capabilities
• Generative Visual Manipulation on the Natural Image Manifold
• Learning to Perform Physics Experiments via Deep Reinforcement Learning
• The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
• Leveraging exploration in off-policy algorithms via normalizing flows
• GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras
• Lossless Compression with Probabilistic Circuits
• Score-based Generative Modeling in Latent Space
• Generalizing Face Forgery Detection with High-frequency Features
• Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension
• Detecting Anomalous Faces with 'No Peeking' Autoencoders
• Rethinking Robust Adversarial Concept Erasure in Diffusion Models
• A Step Toward World Models: A Survey on Robotic Manipulation
• Bias-Corrected Data Synthesis for Imbalanced Learning
• Automatic Differentiation Variational Inference
• BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning
• Deep Gaussian Processes for Multi-fidelity Modeling
• Perturbative Black Box Variational Inference
• A Recurrent Latent Variable Model for Sequential Data
• Hyperbolic Deep Neural Networks: A Survey
• Toward Multimodal Image-to-Image Translation
• Affinity and Diversity: Quantifying Mechanisms of Data Augmentation
• Deep Multi-Fidelity Active Learning of High-dimensional Outputs
• Synthesising Multi-Modal Minority Samples for Tabular Data
• Overdispersed Black-Box Variational Inference
• Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation
• Uncertainty-Aware Attention for Reliable Interpretation and Prediction
• The Variational Gaussian Process
• Governance of Generative AI
• Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
• Accounting for Variance in Machine Learning Benchmarks
• DualDis: Dual-Branch Disentangling with Adversarial Learning
• Predictive Uncertainty Estimation via Prior Networks
• Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
• Concrete Autoencoders for Differentiable Feature Selection and Reconstruction
• A Tutorial on Sparse Gaussian Processes and Variational Inference
• Probabilistic Trust Intervals for Out of Distribution Detection
• Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking
• DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis
• NeRF-VAE: A Geometry Aware 3D Scene Generative Model
• CogView: Mastering Text-to-Image Generation via Transformers
• In the Eye of the Beholder: Gaze and Actions in First Person Video
• Deferred Neural Rendering: Image Synthesis using Neural Textures
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
• Harnessing Deep Neural Networks with Logic Rules
• Compositional Video Prediction
• Generative Modeling by Estimating Gradients of the Data Distribution
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Anomaly Detection in Video Data Based on Probabilistic Latent Space Models
• Learning Identity-Preserving Transformations on Data Manifolds
• Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case
• A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
• Wasserstein Auto-Encoders
• On the Detection of Digital Face Manipulation
• Training Deep Spiking Auto-encoders without Bursting or Dying Neurons through Regularization
• Neural Relational Inference for Interacting Systems
• Bayesian Bits: Unifying Quantization and Pruning
• Generalizable Adversarial Attacks with Latent Variable Perturbation\n Modelling
• Equivariant Deep Dynamical Model for Motion Prediction
• Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks
• Atlas Based Representation and Metric Learning on Manifolds
• How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?
• T-Rep: Representation Learning for Time Series using Time-Embeddings
• Improving Variational Encoder-Decoders in Dialogue Generation
• Factorized Neural Processes for Neural Processes: K-Shot Prediction of\n Neural Responses
• Bayesian Conditional Generative Adverserial Networks
• Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
• An Overview of Deep Semi-Supervised Learning
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• Toward Deeper Understanding of Camouflaged Object Detection
• Composing graphical models with neural networks for structured representations and fast inference
• High-Resolution Image Synthesis with Latent Diffusion Models
• KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
• Deep Multimodal Learning: A Survey on Recent Advances and Trends
• Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing
• TrajectoryCNN: A New Spatio-Temporal Feature Learning Network for Human Motion Prediction
• Novelty Detection via Robust Variational Autoencoding
• TextStyleBrush: Transfer of Text Aesthetics From a Single Example
• Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
• Self-supervised similarity search for large scientific datasets
• Layered Controllable Video Generation
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Probabilistic Circuits for Variational Inference in Discrete Graphical Models
• Learning the Solution Manifold in Optimization and Its Application in Motion Planning
• Ergodic Inference: Accelerate Convergence by Optimisation
• Learning Robust Representations via Multi-View Information Bottleneck
• Large Scale Adversarial Representation Learning
• Missingness Augmentation: A General Approach for Improving Generative Imputation Models
• Scalable Bayesian Optimization Using Deep Neural Networks
• Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
• FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis
• CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
• Domain-Robust Visual Imitation Learning with Mutual Information Constraints
• Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows
• Categorical Normalizing Flows via Continuous Transformations
• On-Demand Video Dispatch Networks: A Scalable End-to-End Learning Approach
• Incremental Learning from Scratch for Task-Oriented Dialogue Systems
• Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation
• GP-VAE: Deep Probabilistic Time Series Imputation
• Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
• Extending Unsupervised Neural Image Compression With Supervised Multitask Learning
• Latent Convolutional Models
• The Art of Food: Meal Image Synthesis from Ingredients
• Capturing Label Characteristics in VAEs
• Visual Adversarial Imitation Learning using Variational Models
• Bayesian Layers: A Module for Neural Network Uncertainty
• Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
• Neural Spline Flows
• PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference
• On Mutual Information Maximization for Representation Learning
• Differential Similarity in Higher Dimensional Spaces: Theory and Applications
• Bridging Global Context Interactions for High-Fidelity Image Completion
• Towards Biologically Plausible Deep Learning
• GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images
• Dependent Multi-Task Learning with Causal Intervention for Image Captioning
• Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
• Multivariate Time-series Anomaly Detection via Graph Attention Network
• Multi-Facet Clustering Variational Autoencoders
• Normalized Diversification
• Conditional Generative Models for Counterfactual Explanations
• Nonlinear Invariant Risk Minimization: A Causal Approach
• Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
• Fair Normalizing Flows
• Inference Suboptimality in Variational Autoencoders
• The State of Sparsity in Deep Neural Networks
• MisConv: Convolutional Neural Networks for Missing Data
• Stateful Detection of Model Extraction Attacks
• Modelling hydrodynamic processes within Pumicestone Passage, Northern Moreton Bay, Queensland
• Training End-to-end Single Image Generators without GANs
• Analysis of ODE2VAE with Examples
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Data Augmentation For Medical MR Image Using Generative Adversarial Networks
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
• Image Synthesis with a Single (Robust) Classifier
• Invertible Generative Modeling using Linear Rational Splines
• Vector-quantized Image Modeling with Improved VQGAN
• Adversarial Domain Adaptation with Domain Mixup
• PathVQA: 30000+ Questions for Medical Visual Question Answering
• Predictive Sampling with Forecasting Autoregressive Models
• MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
• Modeling the Biological Pathology Continuum with HSIC-regularized Wasserstein Auto-encoders
• On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision
• SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
• One-Shot Generalization in Deep Generative Models
• SSN: Soft Shadow Network for Image Compositing
• Semi-Amortized Variational Autoencoders
• Noisy Parallel Approximate Decoding for Conditional Recurrent Language Model
• Pre-training Molecular Graph Representation with 3D Geometry
• Multi-Domain Level Generation and Blending with Sketches via Example-Driven BSP and Variational Autoencoders
• Longitudinal Self-Supervised Learning
• Towards Information-Seeking Agents
• Variational Marginal Particle Filters
• The Consciousness Prior
• Do Deep Generative Models Know What They Don't Know?
• Exploiting Uncertainty of Loss Landscape for Stochastic Optimization
• Continual Learning in Recurrent Neural Networks
• Towards Rapid and Robust Adversarial Training with One-Step Attacks
• DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
• Pseudo-Marginal Hamiltonian Monte Carlo
• Refining Deep Generative Models via Discriminator Gradient Flow
• Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
• Neural View-Interpolation for Sparse Light Field Video
• Learning Post-Hoc Causal Explanations for Recommendation
• Untangling urban data signatures: unsupervised machine learning methods for the detection of urban archetypes at the pedestrian scale
• Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
• Modeling Uncertainty with Hedged Instance Embedding
• Class-Conditional VAE-GAN for Local-Ancestry Simulation
• Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Latent Chord Labels and Features
• Measuring Dependence with Matrix-based Entropy Functional
• Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
• Diffusion Models in Vision: A Survey
• A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series
• A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
• A Theory of Usable Information Under Computational Constraints
• Variational Calibration of Computer Models
• Data Consistent Deep Rigid MRI Motion Correction
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
• Anytime Sampling for Autoregressive Models via Ordered Autoencoding
• An Information-Geometric Distance on the Space of Tasks
• Bayesian Meta-reinforcement Learning for Traffic Signal Control
• Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
• From Variational to Deterministic Autoencoders
• DRAW: A Recurrent Neural Network For Image Generation
• Truncated Variational Expectation Maximization
• Sequential Variational Autoencoders for Collaborative Filtering
• NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps
• Deep Facial Expression Recognition: A Survey
• Latent Dirichlet Allocation in Generative Adversarial Networks
• Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
• Uncertainty-based Continual Learning with Adaptive Regularization
• Fighting Copycat Agents in Behavioral Cloning from Observation Histories
• Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
• Exploring Autoencoder-based Error-bounded Compression for Scientific Data
• PD-GAN: Probabilistic Diverse GAN for Image Inpainting
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Stochastic Prototype Embeddings
• State representation learning with recurrent capsule networks
• Capacity-Approaching Autoencoders for Communications
• Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
• Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models
• Mind the Gap when Conditioning Amortised Inference in Sequential\n Latent-Variable Models
• Block Neural Autoregressive Flow
• Dense Intrinsic Appearance Flow for Human Pose Transfer
• Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
• Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional
• Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning
• Uniform Discrete Diffusion with Metric Path for Video Generation
• VideoGPT: Video Generation using VQ-VAE and Transformers
• Energy-based Out-of-distribution Detection
• A Comprehensive Evaluation Framework for Synthetic Trip Data Generation in Public Transport
• Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
• Causal Convolutional Neural Networks as Finite Impulse Response Filters
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization
• WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data
• Hierarchical Autoregressive Image Models with Auxiliary Decoders
• Local Competition and Uncertainty for Adversarial Robustness in Deep Learning
• Memory-based control with recurrent neural networks
• Advances in Variational Inference
• Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders
• How Does GAN-based Semi-supervised Learning Work?
• Disentangled Representation Learning with Wasserstein Total Correlation
• Universally Quantized Neural Compression
• Revealing the Potential of Learnable Perturbation Ensemble Forecast Model for Tropical Cyclone Prediction
• Debiasing Reward Models by Representation Learning with Guarantees
• Autonomous construction of parameterizable 3D leaf models from scanned sweet pepper leaves with deep generative networks
• Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation
• More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
• Transporting Causal Mechanisms for Unsupervised Domain Adaptation
• Joint Mapping and Calibration via Differentiable Sensor Fusion
• Character Controllers Using Motion VAEs
• VIKING: Deep variational inference with stochastic projections
• Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
• Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced Distortions
• Matching Reverberant Speech Through Learned Acoustic Embeddings and Feedback Delay Networks
• Isometric Autoencoders
• Coupled Flow Matching
• VALA: Learning Latent Anchors for Training-Free and Temporally Consistent
• Switchable Token-Specific Codebook Quantization For Face Image Compression
• Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
• Explaining by Removing: A Unified Framework for Model Explanation
• Disentangling User Interest and Conformity for Recommendation with Causal Embedding
• LO-SDA: Latent Optimization for Score-based Atmospheric Data Assimilation
• Toward Robust Signed Graph Learning through Joint Input-Target Denoising
• MMbeddings: Parameter-Efficient, Low-Overfitting Probabilistic Embeddings Inspired by Nonlinear Mixed Models
• Scaling Non-Parametric Sampling with Representation
• On Masked Pre-training and the Marginal Likelihood
• Input Adaptive Bayesian Model Averaging
• Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability
• Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspective
• WorldGrow: Generating Infinite 3D World
• Generative Correlation Manifolds: Generating Synthetic Data with Preserved Higher-Order Correlations
• DreamerV3-XP: Optimizing exploration through uncertainty estimation
• Self-diffusion for Solving Inverse Problems
• Low-Complexity MIMO Channel Estimation with Latent Diffusion Models
• Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems
• On the flow matching interpretability
• Active Learning: Problem Settings and Recent Developments
• ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs
• A deep-learning search for technosignatures from 820 nearby stars
• Fisher meets Feynman: score-based variational inference with a product of experts
• Unsupervised Part Discovery from Contrastive Reconstruction
• Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
• Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
• Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications
• Exploration through Generation: Applying GFlowNets to Structured Search
• LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting
• To MCMC or not to MCMC: Evaluating non-MCMC methods for Bayesian penalized regression
• Video-As-Prompt: Unified Semantic Control for Video Generation
• Merlion: A Machine Learning Library for Time Series
• Evidential Turing Processes
• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• Single-View 3D Object Reconstruction from Shape Priors in Memory
• Generating Images with Sparse Representations
• Future Frame Prediction for Robot-assisted Surgery
• Learning Discrete Distributions by Dequantization
• Solving Mixed Integer Programs Using Neural Networks
• Neural Contractive Dynamical Systems
• Face-MakeUpV2: Facial Consistency Learning for Controllable Text-to-Image Generation
• Accelerated WGAN update strategy with loss change rate balancing
• Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
• Sparse Graphical Memory for Robust Planning
• Contrastive Variational Reinforcement Learning for Complex Observations
• Continual Density Ratio Estimation in an Online Setting
• CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
• Learning to compress and search visual data in large-scale systems
• Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
• AliGraph: A Comprehensive Graph Neural Network Platform
• The Evolving Nature of Latent Spaces: From GANs to Diffusion
• Neural Architecture Optimization with Graph VAE
• PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
• Terra: Explorable Native 3D World Model with Point Latents
• LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
• An Active Inference Model of Mouse Point-and-Click Behaviour
• Tutorial on Variational Autoencoders
• Exploring Image Representation with Decoupled Classical Visual Descriptors
• Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation
• Machine Learning Percolation Model
• Overfitting for Fun and Profit: Instance-Adaptive Data Compression
• Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation
• Isolation-based Spherical Ensemble Representations for Anomaly Detection
• PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
• Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
• EMFlow: Data Imputation in Latent Space via EM and Deep Flow Models
• Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
• VCTR: A Transformer-Based Model for Non-parallel Voice Conversion
• Robustness May Be at Odds with Accuracy
• Generalization and Robustness Implications in Object-Centric Learning
• Generic Inference in Latent Gaussian Process Models
• Anomaly Detection with Inexact Labels
• Generative networks as inverse problems with Scattering transforms
• Homotopic Gradients of Generative Density Priors for MR Image Reconstruction
• Unsupervised State Representation Learning in Atari
• GO Gradient for Expectation-Based Objectives
• Learning a Deep ConvNet for Multi-label Classification with Partial Labels
• An Exploration of Learnt Representations of W Jets
• LumièreNet: Lecture Video Synthesis from Audio
• Lossless Compression with Latent Variable Models
• SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
• Disentanglement Analysis with Partial Information Decomposition
• A Trifecta of Deep Learning Models: Assessing Brain Health by Integrating Assessment and Neuroimaging Data
• Latent Regression Bayesian Network for Data Representation
• Information Competing Process for Learning Diversified Representations
• Generative Neural Machine Translation
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• Leveraging the Exact Likelihood of Deep Latent Variable Models
• Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
• Improving Generalization in Meta Reinforcement Learning using Learned Objectives
• Deep Visual Foresight for Planning Robot Motion
• Physics-Informed High-order Graph Dynamics Identification Learning for Predicting Complex Networks Long-term Dynamics
• Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization
• Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
• Integer Discrete Flows and Lossless Compression
• Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
• ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
• Flow-based SVDD for anomaly detection
• Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement
• Ctrl-VI: Controllable Video Synthesis via Variational Inference
• Variational Interaction Information Maximization for Cross-domain Disentanglement
• Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation
• Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference
• Hierarchical Bayesian Model for the Transfer of Knowledge on Spatial Concepts based on Multimodal Information
• OffCon³: What is state of the art anyway?
• Generative Model without Prior Distribution Matching
• Object-Centric Image Generation with Factored Depths, Locations, and\n Appearances
• Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin
• 3DMolNet: A Generative Network for Molecular Structures
• ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model
• Continuous normalizing flows on manifolds
• An End-to-End Framework for Molecular Conformation Generation via\n Bilevel Programming
• Variational Inference with Holder Bounds
• Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?
• Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
• Causal Discovery from Incomplete Data: A Deep Learning Approach
• DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
• A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
• Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
• Information Potential Auto-Encoders
• Phase Collaborative Network for Two-Phase Medical Image Segmentation
• P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening
• Out-of-Sample Testing for GANs
• Adaptive Stress Testing for Autonomous Vehicles
• Masked Autoregressive Flow for Density Estimation
• Variational Bayesian Monte Carlo with Noisy Likelihoods
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
• Can multi-label classification networks know what they don't know?
• DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
• Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
• SMS: Self-supervised Model Seeding for Verification of Machine Unlearning
• Variational Bayesian Decision-making for Continuous Utilities
• Regularized Autoencoders via Relaxed Injective Probability Flow
• Deep Vocoder: Low Bit Rate Compression of Speech with Deep Autoencoder
• Consensus Message Passing for Layered Graphical Models
• Mixture-of-Variational-Experts for Continual Learning
• Model-Based Reinforcement Learning for Atari
• Deep Auto-encoder with Neural Response
• Hamiltonian Generative Networks
• Learning to Decompose and Disentangle Representations for Video Prediction
• A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning
• Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks
• Anomalous sound detection based on interpolation deep neural network
• Neural Density Estimation and Likelihood-free Inference
• Machine learning for synthetic gene circuit engineering
• DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction
• Unsupervised Recurrent Neural Network Grammars
• A Spectral Regularizer for Unsupervised Disentanglement
• Application-driven validation of posteriors in inverse problems
• Locality and compositionality in zero-shot learning
• A Block-based Generative Model for Attributed Networks Embedding
• Calibration of Model Uncertainty for Dropout Variational Inference
• GO Hessian for Expectation-Based Objectives
• View-Invariant Probabilistic Embedding for Human Pose
• Modeling Grasp Motor Imagery through Deep Conditional Generative Models
• High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks
• Facing & mitigating common challenges when working with real-world data: The Data Learning Paradigm
• Generative Image Modeling Using Spatial LSTMs
• Model-Augmented Actor-Critic: Backpropagating through Paths
• Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval
• Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance
• Deep Temporal Sigmoid Belief Networks for Sequence Modeling
• Community Detection Clustering via Gumbel Softmax
• (Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification
• The molecular memory code and synaptic plasticity: A synthesis
• Graph networks as learnable physics engines for inference and control
• Information bottleneck through variational glasses
• Probabilistic Binary Neural Networks
• Parameter estimation in FACS-seq enables high-throughput characterization of phenotypic heterogeneity
• Robust Locally-Linear Controllable Embedding
• ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects
• Learning Likelihoods with Conditional Normalizing Flows
• Conditional Generative Moment-Matching Networks
• Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
• PAC-Bayes Analysis of Sentence Representation
• Weight Uncertainty in Neural Networks
• Canonical Correlation Analysis (CCA) Based Multi-View Learning: An Overview
• Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections
• Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series
• Sensitivity to geometric shape regularity in humans and baboons: A putative signature of human singularity
• Mathematics for Machine Learning
• Learning Compositional Sparse Gaussian Processes with a Shrinkage Prior
• High Fidelity Face Manipulation with Extreme Poses and Expressions
• Physics-aware, probabilistic model order reduction with guaranteed stability
• Efficient Semi-Implicit Variational Inference
• Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
• Transformations between deep neural networks
• Estimating uncertainty in flood model outputs using machine learning informed by Monte Carlo analysis
• Unsupervised Classification of Street Architectures Based on InfoGAN
• Continual Learning of New Sound Classes using Generative Replay
• TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
• Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction
• BreGMN: scaled-Bregman Generative Modeling Networks
• ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder
• Latent Matters: Learning Deep State-Space Models
• SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
• EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
• Particle Filter Recurrent Neural Networks
• Deep Bayesian Unsupervised Lifelong Learning
• Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
• Generative causal explanations of black-box classifiers
• A Generative Learning Approach for Spatio-temporal Modeling in Connected Vehicular Network
• Semi-supervised Disentanglement with Independent Vector Variational Autoencoders
• Variance Reduction for Evolution Strategies via Structured Control Variates
• Symbolic Music Generation with Diffusion Models
• Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
• Practical Lossless Compression with Latent Variables using Bits Back Coding
• Generating and designing DNA with deep generative models
• SSD: A Unified Framework for Self-Supervised Outlier Detection
• A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
• Conditional Generative Modeling via Learning the Latent Space
• The Neglected Sibling: Isotropic Gaussian Posterior for VAE
• VAEs in the Presence of Missing Data
• Adversarial Symmetric Variational Autoencoder
• BEiT: BERT Pre-Training of Image Transformers
• All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
• Learning geometry-image representation for 3D point cloud generation
• Adversarially Regularized Autoencoders
• Generating unseen complex scenes: are we there yet?
• Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
• Cascaded Text Generation with Markov Transformers
• Focal Frequency Loss for Image Reconstruction and Synthesis
• Generating Sentences by Editing Prototypes
• Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
• Structure-Aware Human-Action Generation
• NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport
• Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
• Graph Residual Flow for Molecular Graph Generation
• Deep Amortized Clustering
• Semi-Implicit Generative Model
• Causal Effect Inference with Deep Latent-Variable Models
• Cooperative image captioning
• Deep Active Inference for Autonomous Robot Navigation
• A Unified Particle-Optimization Framework for Scalable Bayesian Sampling
• Cerberus: A Multi-headed Derenderer
• Unsupervised Learning of 3D Structure from Images
• A Model to Search for Synthesizable Molecules
• A deep generative model for gene expression profiles from single-cell RNA sequencing
• Quantum Hamiltonian-Based Models and the Variational Quantum Thermalizer Algorithm
• Angular Dispersion Accelerates k-Nearest Neighbors Machine Translation
• Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking
• Variational inference for Monte Carlo objectives
• VAE-based Domain Adaptation for Speaker Verification
• Kuramoto Orientation Diffusion Models
• Computer-Aided Design as Language
• Gradient Boosted Normalizing Flows
• Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
• Applying the Information Bottleneck Principle to Prosodic Representation Learning
• G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
• Learning FRAME Models Using CNN Filters
• Generative Models of Visually Grounded Imagination
• X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
• Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
• Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation
• A similarity-based Bayesian mixture-of-experts model
• Unsupervised Discovery of 3D Physical Objects from Video
• CookGAN: Meal Image Synthesis from Ingredients
• Hierarchical Quantized Autoencoders
• From Machine Learning to Robotics: Challenges and Opportunities for\n Embodied Intelligence
• Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• Reconsidering Analytical Variational Bounds for Output Layers of Deep Networks
• AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization
• Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• Identification of Gaussian Process State Space Models
• A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
• Non-Asymptotic Performance Guarantees for Neural Estimation of f-Divergences
• Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach
• Reconstruction and Membership Inference Attacks against Generative Models
• Scalable Bayesian Inverse Reinforcement Learning
• TSIT: A Simple and Versatile Framework for Image-to-Image Translation
• Marginalized State Distribution Entropy Regularization in Policy Optimization
• A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
• Barlow Graph Auto-Encoder for Unsupervised Network Embedding
• Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales
• GLALLM: Adapting LLMs for spatio-temporal wind speed forecasting via global–local aware modeling
• Online Variational Filtering and Parameter Learning
• Conditional Image Generation with Score-Based Diffusion Models
• The continuous Bernoulli: fixing a pervasive error in variational autoencoders
• MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
• Goal-Oriented Gaze Estimation for Zero-Shot Learning
• Diagnosing and Enhancing VAE Models
• A Class of Algorithms for General Instrumental Variable Models
• Black-Box Autoregressive Density Estimation for State-Space Models
• Neural Design Network: Graphic Layout Generation with Constraints
• Rate-Distortion Optimization Guided Autoencoder for Isometric Embedding in Euclidean Latent Space
• Label-Noise Robust Generative Adversarial Networks
• Kernel Exponential Family Estimation via Doubly Dual Embedding
• Artificial neural networks for neuroscientists: A primer
• Pyro: Deep Universal Probabilistic Programming
• Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
• Make a Face: Towards Arbitrary High Fidelity Face Manipulation
• Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
• Tackling Over-pruning in Variational Autoencoders
• Learning Disentangled Representations with Reference-Based Variational Autoencoders
• Deep Variational Luenberger-type Observer for Stochastic Video Prediction
• PRRS Outbreak Prediction via Deep Switching Auto-Regressive Factorization Modeling
• A Framework for Interdomain and Multioutput Gaussian Processes
• Neural Autoregressive Distribution Estimation
• On the Effectiveness of Least Squares Generative Adversarial Networks
• A COLD Approach to Generating Optimal Samples
• Learning Robust Feature Representations for Scene Text Detection
• A Graph to Graphs Framework for Retrosynthesis Prediction
• Contrastive Learning with Stronger Augmentations
• Early Visual Concept Learning with Unsupervised Deep Learning
• Unsupervised Word Segmentation from Speech with Attention
• Simple, Scalable, and Stable Variational Deep Clustering
• Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA
• A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
• Learning Implicit Generative Models by Teaching Explicit Ones
• Deep Survival Analysis
• Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
• Spherical Sliced-Wasserstein
• Progressive and Aligned Pose Attention Transfer for Person Image Generation
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Meta-Learning with Variational Bayes
• Learning Augmentation Distributions using Transformed Risk Minimization
• Can deep learning beat numerical weather prediction?
• Sparse Uncertainty Representation in Deep Learning with Inducing Weights
• iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling
• Learning to Synthesize Programs as Interpretable and Generalizable Policies
• Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
• On the Evaluation of Conditional GANs
• Towards Visually Explaining Variational Autoencoders
• Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
• Sequential Matrix Completion
• A probabilistic approach to tomography and adjoint state methods, with an application to full waveform inversion in medical ultrasound
• RPC: A Large-Scale Retail Product Checkout Dataset
• Counterfactual Reasoning for Fair Clinical Risk Prediction
• Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications
• Regularization with Latent Space Virtual Adversarial Training
• Sparsity in Variational Autoencoders
• Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation
• Bilevel Continual Learning
• Variational Diffusion Models
• Variational Autoencoder with Learned Latent Structure
• Zero-Shot Semantic Segmentation
• Data Uncertainty Learning in Face Recognition
• Traversing Time with Multi-Resolution Gaussian Process State-Space Models
• Deep Convolutional Inverse Graphics Network
• Generative Models as Distributions of Functions
• Least Squares Generative Adversarial Networks
• Discovering Discrete Latent Topics with Neural Variational Inference
• Texture and geometric feature-fusion-based network for Dunhuang mural inpainting
• Compressing Neural Networks using the Variational Information Bottleneck
• Explaining Visual Models by Causal Attribution
• Deep Proxy Causal Learning and its Application to Confounded Bandit\n Policy Evaluation
• Reconstruction Student with Attention for Student-Teacher Pyramid Matching
• Lower Bounds for Compressed Sensing with Generative Models
• Understanding Instance-based Interpretability of Variational Auto-Encoders
• Stochastic Variational Bayesian Inference for a Nonlinear Forward Model
• Are Disentangled Representations Helpful for Abstract Visual Reasoning?
• TRADI: Tracking deep neural network weight distributions for uncertainty estimation
• One-shot emotional voice conversion based on feature separation
• Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
• Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
• Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
• Neural Recursive Belief States in Multi-Agent Reinforcement Learning
• Learning Latent Space Energy-Based Prior Model
• A review of radar-based nowcasting of precipitation and applicable machine learning techniques
• NeuralQAAD: An Efficient Differentiable Framework for High Resolution Point Cloud Compression
• SDM-NET: Deep Generative Network for Structured Deformable Mesh
• Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL
• PuVAE: A Variational Autoencoder to Purify Adversarial Examples
• Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables
• Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
• Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI
• Augmented KRnet for density estimation and approximation
• Causal Discovery in Physical Systems from Videos
• Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
• DroneSR: Rethinking Few-shot Thermal Image Super-Resolution from Drone-based Perspective
• Neural Topic Model via Optimal Transport
• Variational Mixture of Normalizing Flows
• Jukebox: A Generative Model for Music
• Diverse Plausible Shape Completions from Ambiguous Depth Images
• Stochastic Function Norm Regularization of Deep Networks
• Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates
• DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using Generative Adversarial Networks
• Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks
• Online reinforcement learning with sparse rewards through an active inference capsule
• Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• We are More than Our Joints: Predicting how 3D Bodies Move
• Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
• Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement
• Deep Learning in Mobile and Wireless Networking: A Survey
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• When Can Neural Networks Learn Connected Decision Regions?
• Independent Prototype Propagation for Zero-Shot Compositionality
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Graph Generation with Variational Recurrent Neural Network
• Learning an optimal PSF-pair for ultra-dense 3D localization microscopy
• Amortized Inference of Variational Bounds for Learning Noisy-OR
• Controllable Invariance through Adversarial Feature Learning
• Improving Generative Imagination in Object-Centric World Models
• Bigeminal Priors Variational auto-encoder
• Turbulence forecasting via Neural ODE
• Lossless Image Compression through Super-Resolution
• Reliable training and estimation of variance networks
• Deep Involutive Generative Models for Neural MCMC
• Density Deconvolution with Normalizing Flows
• Unsupervised Object Keypoint Learning using Local Spatial Predictability
• Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
• The Pitfall of More Powerful Autoencoders in Lidar-Based Navigation
• A Chain Graph Interpretation of Real-World Neural Networks
• Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network
• On Disentangled Representations Learned From Correlated Data
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• CoPE: Conditional image generation using Polynomial Expansions
• Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
• Intriguing Properties of Contrastive Losses
• The continuous categorical: a novel simplex-valued exponential family
• Diffusion Normalizing Flow
• Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
• Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
• Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
• Acoustic feature learning using cross-domain articulatory measurements
• Private-Shared Disentangled Multimodal VAE for Learning of Hybrid Latent Representations
• Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic\n Circuits
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Provable Mixed-Noise Learning with Flow-Matching
• Behavior From the Void: Unsupervised Active Pre-Training
• Continual State Representation Learning for Reinforcement Learning using Generative Replay
• Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults
• Efficient Approximate Inference with Walsh-Hadamard Variational Inference
• Symbolic Music Loop Generation with VQ-VAE
• BachGAN: High-Resolution Image Synthesis from Salient Object Layout
• Semantic-Aware Generation for Self-Supervised Visual Representation Learning
• Contrastively Disentangled Sequential Variational Autoencoder
• RoMA: Robust Model Adaptation for Offline Model-based Optimization
• A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
• NP-ODE: Neural Process Aided Ordinary Differential Equations for Uncertainty Quantification of Finite Element Analysis
• Group Anomaly Detection using Deep Generative Models
• Measuring the Biases and Effectiveness of Content-Style Disentanglement
• Noise Attention based Spectrum Anomaly Detection Method for Unauthorized Bands
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder
• Variational Bayesian Context-aware Representation for Grocery Recommendation
• Importance Weighted Hierarchical Variational Inference
• Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
• A Short Survey On Memory Based Reinforcement Learning
• Replicating Active Appearance Model by Generator Network
• Generative Adversarial Networks
• Asymptotic Consistency of α-Rényi-Approximate Posteriors
• LyricJam: A system for generating lyrics for live instrumental music
• SDEC: Semantic Deep Embedded Clustering
• Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
• Generative Moment Matching Networks
• Deepfake Videos in the Wild: Analysis and Detection
• Balancing Reconstruction Quality and Regularisation in ELBO for VAEs
• Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
• Discrete Word Embedding for Logical Natural Language Understanding
• A Tutorial on Deep Latent Variable Models of Natural Language
• Design by adaptive sampling
• Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
• Iterative VAE as a predictive brain model for out-of-distribution generalization
• Normalizing Flows on Riemannian Manifolds
• Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
• Optimal Transport Based Generative Autoencoders
• Probabilistic Re-aggregation Algorithm [First Draft]
• Deep Automodulators
• In Search of Lost Domain Generalization
• Invariant Representations from Adversarially Censored Autoencoders
• Structured Embedding Models for Grouped Data
• Approximate Inference with Amortised MCMC
• Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
• Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
• Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features
• DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
• The Role of Information Complexity and Randomization in Representation Learning
• Structured Pruning of a BERT-based Question Answering Model
• Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space
• Provable Smoothness Guarantees for Black-Box Variational Inference
• Soft Actor-Critic for Discrete Action Settings
• Graph Embedding VAE: A Permutation Invariant Model of Graph Structure
• Formalising Concepts as Grounded Abstractions
• Decoupling feature propagation from the design of graph auto-encoders
• Joint Variational Autoencoders for Recommendation with Implicit Feedback
• Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
• Robust Pollen Imagery Classification with Generative Modeling and Mixup Training
• Wasserstein Adversarially Regularized Graph Autoencoder
• Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests
• PatchGame: Learning to Signal Mid-level Patches in Referential Games
• AriEL: volume coding for sentence generation
• Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
• CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
• Multi-Task Time Series Forecasting With Shared Attention
• How much progress have we made in neural network training? A New Evaluation Protocol for Benchmarking Optimizers
• Enhanced Variational Inference with Dyadic Transformation
• Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• Biphasic Learning of GANs for High-Resolution Image-to-Image Translation
• Phase Transitions for the Information Bottleneck in Representation Learning
• Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks
• Unsupervised Neural Hidden Markov Models with a Continuous latent state space
• Prediction of liquid fuel properties using machine learning models with Gaussian processes and probabilistic conditional generative learning
• Distribution Matching in Variational Inference
• Patterns for Learning with Side Information
• Memory and attention in deep learning
• Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)
• Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
• Understanding the Limitations of Variational Mutual Information Estimators
• Variational Rejection Sampling
• Trajectory Prediction with Latent Belief Energy-Based Model
• Semantics Preserving Adversarial Learning
• Graphite: Iterative Generative Modeling of Graphs
• Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
• Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
• Physical Layer Authentication Based on Hierarchical Variational Auto-Encoder for Industrial Internet of Things
• Towards Better Understanding of Disentangled Representations via Mutual Information
• KernelNet: A Data-Dependent Kernel Parameterization for Deep Generative Modeling
• Sliced Iterative Normalizing Flows
• Channel Decomposition into Painting Actions
• Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models
• Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example
• Representation Learning for Words and Entities
• Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
• The Bayesian Committee Approach for Computational Physics Problems
• X-MoGen: Unified Motion Generation across Humans and Animals
• Joint Estimation of Image Representations and their Lie Invariants
• AU-IQA: A Benchmark Dataset for Perceptual Quality Assessment of AI-Enhanced User-Generated Content
• Learning undirected models via query training
• Attentive Representation Learning with Adversarial Training for Short Text Clustering
• Mixture Representation Learning with Coupled Autoencoders
• Variational Composite Autoencoders
• von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
• Auto-Encoding Sequential Monte Carlo
• Reinforcement Evolutionary Learning Method for self-learning
• Modeling documents with Generative Adversarial Networks
• READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation
• Approximation Based Variance Reduction for Reparameterization Gradients
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism
• MILD: Multi-Layer Diffusion Strategy for Complex and Precise Multi-IP Aware Human Erasing
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Guided Variational Autoencoder for Disentanglement Learning
• StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
• Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space
• Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
• A Meta-Learning Framework for Generalized Zero-Shot Learning
• Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection
• Desiderata for Representation Learning: A Causal Perspective
• Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data
• Efficient State-space Exploration in Massively Parallel Simulation Based Inference
• M²VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation
• Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
• Multi-resolution Multi-task Gaussian Processes
• Generative Mixture of Networks
• Probabilistic Video Generation using Holistic Attribute Control
• Generating Smooth Pose Sequences for Diverse Human Motion Prediction
• Source Separation with Deep Generative Priors
• Flow Contrastive Estimation of Energy-Based Models
• CompILE: Compositional Imitation Learning and Execution
• Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
• WeLa-VAE: Learning Alternative Disentangled Representations Using Weak Labels
• Towards neural networks that provably know when they don't know
• Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
• Improved Training of Sparse Coding Variational Autoencoder via Weight Normalization
• Contrastive Unpaired Translation using Focal Loss for Patch Classification
• Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model
• Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks
• Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration
• Harnessing value from data science in business: ensuring explainability and fairness of solutions
• HUGE2: a Highly Untangled Generative-model Engine for Edge-computing
• Coupled Gradient Estimators for Discrete Latent Variables
• One-element Batch Training by Moving Window
• DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding
• A Simple Framework for Uncertainty in Contrastive Learning
• Progressive Pose Attention Transfer for Person Image Generation
• Manifold Optimization Assisted Gaussian Variational Approximation
• On Adaptive Attacks to Adversarial Example Defenses
• Learning 3D Dense Correspondence via Canonical Point Autoencoder
• Unsupervised Feature Learning for Online Voltage Stability Evaluation and Monitoring Based on Variational Autoencoder
• Resolution and Relevance Trade-offs in Deep Learning
• StyleRemix: An Interpretable Representation for Neural Image Style Transfer
• Deep Factors with Gaussian Processes for Forecasting
• Debiasing a First-order Heuristic for Approximate Bi-level Optimization
• Attractive and Repulsive Perceptual Biases Naturally Emerge in Generative Adversarial Inference
• Deep Music Analogy Via Latent Representation Disentanglement
• Data Augmentation for Enhancing EEG-based Emotion Recognition with Deep Generative Models
• Self-supervised human mobility learning for next location prediction and trajectory classification
• Semantics Disentangling for Generalized Zero-Shot Learning
• Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds
• Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
• Coupled Generative Adversarial Networks
• Flow-Grounded Spatial-Temporal Video Prediction from Still Images
• Noise Robust Generative Adversarial Networks
• Implicit Generation and Generalization in Energy-Based Models
• Universal Boosting Variational Inference
• The Six Fronts of the Generative Adversarial Networks
• Learning Portrait Style Representations
• Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
• Learning Disentangled Representations via Mutual Information Estimation
• Densely connected normalizing flows
• VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
• DSBERT:Unsupervised Dialogue Structure learning with BERT
• Latent Translation: Crossing Modalities by Bridging Generative Models
• Sparse Stochastic Zeroth-Order Optimization with an Application to Bandit Structured Prediction
• Zero-Shot Recommender Systems
• Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
• TOMA: Topological Map Abstraction for Reinforcement Learning
• Amortized backward variational inference in nonlinear state-space models
• The Convolution Exponential and Generalized Sylvester Flows
• Deep-learning-based reduced-order modeling for subsurface flow simulation
• Curriculum Learning for Deep Generative Models with Clustering
• Attribute-controlled face photo synthesis from simple line drawing
• Dynamic Word Embeddings
• Measuring Fairness in Generative Models
• Discrete flow posteriors for variational inference in discrete dynamical systems
• McGan: Mean and Covariance Feature Matching GAN
• A Bayes-Optimal View on Adversarial Examples
• A Gentle Introduction to Deep Learning for Graphs
• A Closer Look at the Adversarial Robustness of Information Bottleneck Models
• Bayesian task embedding for few-shot Bayesian optimization
• Synthetic Data Generators: Sequential and Private
• Neural Estimation of Statistical Divergences
• Structured Object-Aware Physics Prediction for Video Modeling and Planning
• Variational Monocular Depth Estimation for Reliability Prediction
• Generalized Latent Variable Recovery for Generative Adversarial Networks
• Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation
• Using Neural Networks for Programming by Demonstration
• Towards meaningful physics from generative models
• Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
• Reinforcement Learning Generalization with Surprise Minimization
• Variational Feature Disentangling for Fine-Grained Few-Shot Classification
• Predictive modeling, pattern recognition, and spatiotemporal representations of plant growth in simulated and controlled environments: A comprehensive review
• Performing Co-Membership Attacks Against Deep Generative Models
• S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
• Learning Wake-Sleep Recurrent Attention Models
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• Quantifying and Learning Linear Symmetry-Based Disentanglement
• A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
• DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and L₀ Regularization
• BoA-PTA, A Bayesian Optimization Accelerated Error-Free SPICE Solver
• High-dimensional Assisted Generative Model for Color Image Restoration
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Enhancing audio quality for expressive Neural Text-to-Speech
• Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
• Quasi-symplectic Langevin Variational Autoencoder
• Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model
• Exploration by Maximizing Rényi Entropy for Reward-Free RL Framework
• CoRGi: Content-Rich Graph Neural Networks with Attention
• Diffusion models for Handwriting Generation
• Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence
• Variational AutoEncoder For Regression: Application to Brain Aging Analysis
• Assembling Semantically-Disentangled Representations for Predictive-Generative Models via Adaptation from Synthetic Domain
• Learning Neurosymbolic Generative Models via Program Synthesis
• Analyzing the Hidden Activations of Deep Policy Networks: Why Representation Matters
• Language as a Latent Variable: Discrete Generative Models for Sentence Compression
• Self-Supervised Sketch-to-Image Synthesis
• KATE: K-Competitive Autoencoder for Text
• Weakly-Supervised Action Localization by Generative Attention Modeling
• Human-interpretable model explainability on high-dimensional data
• How Tight Can PAC-Bayes be in the Small Data Regime?
• The FMRIB Variational Bayesian Inference Tutorial II: Stochastic Variational Bayes
• Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
• Metric Learning for Anti-Compression Facial Forgery Detection
• Investigating the Effect of Intraclass Variability in Temporal Ensembling
• Hierarchical Adversarially Learned Inference
• Zero-shot Domain Adaptation without Domain Semantic Descriptors
• The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders
• Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning
• Learning Implicit Generative Models with Theoretical Guarantees
• CRL: Class Representative Learning for Image Classification
• Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks
• InfoFair: Information-Theoretic Intersectional Fairness
• On Inductive Biases for Machine Learning in Data Constrained Settings
• Efficient and Robust Machine Learning for Real-World Systems
• Learning Latent Space Energy-Based Prior Model for Molecule Generation
• Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models
• Maximum Entropy Generators for Energy-Based Models
• Improving Uncertainty Calibration via Prior Augmented Data
• Amortized Population Gibbs Samplers with Neural Sufficient Statistics
• The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
• Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity
• Precision-Recall Curves Using Information Divergence Frontiers
• Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
• Amortized Variational Deep Q Network
• Latent Network Embedding via Adversarial Auto-encoders
• Radon Sobolev Variational Auto-Encoders
• Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
• Unsupervised Embedding of Hierarchical Structure in Euclidean Space
• Modality Conversion of Handwritten Patterns by Cross Variational Autoencoders
• Data Augmentation with Variational Autoencoders and Manifold Sampling
• Automatic Relevance Determination For Deep Generative Models
• Unsupervised Representation Learning via Neural Activation Coding
• Dynamic Relational Inference in Multi-Agent Trajectories
• The equivalence between Stein variational gradient descent and black-box variational inference
• Variational Generative Stochastic Networks with Collaborative Shaping
• Data-Driven Topology Optimization with Multiclass Microstructures using Latent Variable Gaussian Process
• Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
• Copula-Based Normalizing Flows
• An Empirical Study of Generative Models with Encoders
• Multi-way Clustering and Discordance Analysis through Deep Collective Matrix Tri-Factorization
• Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data
• Entity Abstraction in Visual Model-Based Reinforcement Learning
• Learning a face space for experiments on human identity
• Generative Creativity: Adversarial Learning for Bionic Design
• SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
• Statistical Guarantees for Transformation Based Models with Applications to Implicit Variational Inference
• Identifying Invariant Texture Violation for Robust Deepfake Detection
• Visual Language Modeling on CNN Image Representations
• Benchmarking Graph Neural Networks on Link Prediction
• Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning
• Using Sign Language Production as Data Augmentation to enhance Sign Language Translation
• Semi-Supervised Generation with Cluster-aware Generative Models
• Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres
• Attribute-Guided Sketch Generation
• Instance-Dependent Partial Label Learning
• A practical tutorial on Variational Bayes
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Automatic design of novel potential 3CL^pro and PL^pro inhibitors
• Towards GANs' Approximation Ability
• Interactive Image Manipulation with Natural Language Instruction Commands
• Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
• CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
• Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems
• Fairness in Rankings and Recommendations: An Overview
• Parametric UMAP embeddings for representation and semi-supervised learning
• Deep Active Inference as Variational Policy Gradients
• Singing Voice Conversion with Disentangled Representations of Singer and Vocal Technique Using Variational Autoencoders
• Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions
• Learning Task Decomposition with Ordered Memory Policy Network
• Variational Deep Semantic Hashing for Text Documents
• Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
• Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
• M-estimation with the Trimmed l1 Penalty
• Manifold Modeling in Embedded Space: A Perspective for Interpreting Deep Image Prior
• F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
• Seq2seq Translation Model for Sequential Recommendation
• Generative Adversarial Zero-shot Learning via Knowledge Graphs
• Locally Masked Convolution for Autoregressive Models
• Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
• LayoutVAE: Stochastic Scene Layout Generation From a Label Set
• NWT: Towards natural audio-to-video generation with representation learning
• Computer-Assisted Analysis of Biomedical Images
• What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations
• TabSyM: A Generative Pipeline for Small Multi-Cohort Omics Tabular Data
• StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations
• Gradient Origin Networks
• Using latent space regression to analyze and leverage compositionality in GANs
• Learning Generative Prior with Latent Space Sparsity Constraints
• Measure Transport with Kernel Stein Discrepancy
• HumanGAN: A Generative Model of Humans Images
• Modeling Tabular data using Conditional GAN
• Collaging Class-specific GANs for Semantic Image Synthesis
• Machine Learning for Spatiotemporal Sequence Forecasting: A Survey
• Meta Dropout: Learning to Perturb Features for Generalization
• Bayesian policy selection using active inference
• Emotional voice conversion: Theory, databases and ESD
• Probabilistic Discriminative Learning with Layered Graphical Models
• Eccentric Regularization: Minimizing Hyperspherical Energy without explicit projection
• Joint Intensity-Gradient Guided Generative Modeling for Colorization
• Copula Flows for Synthetic Data Generation
• Multi-Time Attention Networks for Irregularly Sampled Time Series
• A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
• Pulling back information geometry
• ATISS: Autoregressive Transformers for Indoor Scene Synthesis
• Action2video: Generating Videos of Human 3D Actions
• Compositional uncertainty in deep Gaussian processes
• Compressed Sensing via Measurement-Conditional Generative Models
• Autoencoding Variational Autoencoder
• Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior
• Generating 3D People in Scenes without People
• Energy-Inspired Models: Learning with Sampler-Induced Distributions
• Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
• SCAN: Learning Hierarchical Compositional Visual Concepts
• Russian Natural Language Generation: Creation of a Language Modelling Dataset and Evaluation with Modern Neural Architectures
• Self-Reflective Variational Autoencoder
• Towards Learning to Imitate from a Single Video Demonstration
• DPPNet: Approximating Determinantal Point Processes with Deep Networks
• β-Variational Classifiers Under Attack
• Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering
• A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
• Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction
• BézierSketch: A generative model for scalable vector sketches
• NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
• Fast Non-Parametric Tests of Relative Dependency and Similarity
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
• Manifolds for Unsupervised Visual Anomaly Detection
• Off-Policy Deep Reinforcement Learning without Exploration
• From optimal transport to generative modeling: the VEGAN cookbook
• Semantic Adversarial Network for Zero-Shot Sketch-Based Image Retrieval
• Auto-encoding brain networks with applications to analyzing large-scale brain imaging datasets
• The Angel is in the Priors: Improving GAN based Image and Sequence Inpainting with Better Noise and Structural Priors
• Variance Constrained Autoencoding
• Loss is its own Reward: Self-Supervision for Reinforcement Learning
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• Learning Calibratable Policies using Programmatic Style-Consistency
• State Space LSTM Models with Particle MCMC Inference
• A New Perspective on Learning Context-Specific Independence
• An information-based metric for observing strategy optimization, demonstrated in the context of photometric redshifts with applications to cosmology
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• NICE: Non-linear Independent Components Estimation
• Semantic Communication for Cooperative Multi-Tasking over Rate-Limited Wireless Channels with Implicit Optimal Prior
• Monte Carlo Filtering Objectives: A New Family of Variational Objectives to Learn Generative Model and Neural Adaptive Proposal for Time Series
• Class-Conditional Compression and Disentanglement: Bridging the Gap between Neural Networks and Naive Bayes Classifiers
• Deep Synthetic Minority Over-Sampling Technique
• Data-Dependent Randomized Smoothing
• Unsupervised Anomaly Detection for X-Ray Images
• Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
• Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
• Implicit Autoencoders
• Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
• Region-based Energy Neural Network for Approximate Inference
• Learning to Generate with Memory
• MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
• Using Sensory Time-cue to enable Unsupervised Multimodal Meta-learning
• Particle Filter Bridge Interpolation
• Multi-Decoder RNN Autoencoder Based on Variational Bayes Method
• DiffSBR: A diffusion model for session-based recommendation
• Minority Class Oversampling for Tabular Data with Deep Generative Models
• Flows and Diffusions on the Neural Manifold
• Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
• VAE-KRnet and its applications to variational Bayes
• Point-to-Point Video Generation
• Scenario Forecasting of Residential Load Profiles
• Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
• Dynamic Future Net: Diversified Human Motion Generation
• Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition
• Rao-Blackwellized Stochastic Gradients for Discrete Distributions
• Residual Flows for Invertible Generative Modeling
• A Binded VAE for Inorganic Material Generation
• Incorporating Interpretable Output Constraints in Bayesian Neural Networks
• Generating synthetic transactional profiles
• Normalizing Flows with Multi-Scale Autoregressive Priors
• A unified survey of treatment effect heterogeneity modeling and uplift modeling
• Storchastic: A Framework for General Stochastic Automatic Differentiation
• Gaussian variational approximation with a factor covariance structure
• Generator Surgery for Compressed Sensing
• Image Generation from Layout
• Modeling Graph Node Correlations with Neighbor Mixture Models
• A Novel Variational Autoencoder with Applications to Generative Modelling, Classification, and Ordinal Regression
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
• Processsing Simple Geometric Attributes with Autoencoders
• Generating private data with user customization
• Latent Variable Modeling for Generative Concept Representations and Deep Generative Models
• Disentangled Person Image Generation
• Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
• Learning to Reconstruct and Segment 3D Objects
• Supervised Topological Maps
• Variational Inference with Normalizing Flows
• PSD Representations for Effective Probability Models
• DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning
• A Two-Step Framework for Arbitrage-Free Prediction of the Implied Volatility Surface
• Jointly Dynamic Topic Model for Recognition of Lead-lag Relationship in Two Text Corpora
• Towards a Neural Statistician
• Learning Informative Representations of Biomedical Relations with Latent Variable Models
• High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection
• Testing for Typicality with Respect to an Ensemble of Learned Distributions
• Super-Resolution Perception for Industrial Sensor Data
• Self-supervised SAR-optical Data Fusion and Land-cover Mapping using Sentinel-1/-2 Images
• Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning
• When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes
• A Modified Convolutional Network for Auto-encoding based on Pattern Theory Growth Function
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Information Theoretic Lower Bounds on Negative Log Likelihood
• Missing Data Imputation using Optimal Transport
• Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
• SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
• Weight-Covariance Alignment for Adversarially Robust Neural Networks
• Learning Robust Variational Information Bottleneck with Reference
• GANimation: Anatomically-aware Facial Animation from a Single Image
• Controllable Gradient Item Retrieval
• Quasi-Newton Quasi-Monte Carlo for variational Bayes
• GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization
• Differentially Private Data Generative Models
• PRI-VAE: Principle-of-Relevant-Information Variational Autoencoders
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Attentive Action and Context Factorization
• Factorizable Graph Convolutional Networks
• Autoencoding beyond pixels using a learned similarity metric
• Outlier Detection through Null Space Analysis of Neural Networks
• Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
• Anomaly Detection on Graph Time Series
• C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling
• Diverse Image Captioning with Context-Object Split Latent Spaces
• A Self-Supervised Framework for Function Learning and Extrapolation
• Scalable Gaussian Process Variational Autoencoders
• Uncertainty in Neural Processes
• ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models
• Generative Image Modeling using Style and Structure Adversarial Networks
• Efficient Deep Gaussian Process Models for Variable-Sized Input
• Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems
• Posterior Meta-Replay for Continual Learning
• Learning by Playing - Solving Sparse Reward Tasks from Scratch
• Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
• Instance-Aware Graph Convolutional Network for Multi-Label Classification
• Multi-Task Variational Information Bottleneck
• Robust Disentanglement of a Few Factors at a Time
• Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
• NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps
• Efficient inference in occlusion-aware generative models of images
• Detection of Alzheimer's Disease Using Graph-Regularized Convolutional Neural Network Based on Structural Similarity Learning of Brain Magnetic Resonance Images
• Multiple Style Transfer via Variational AutoEncoder
• Disentangling Disentanglement in Variational Autoencoders
• Explainable modeling of single-cell perturbation data using attention and sparse dictionary learning
• Adaptive Pruning of Neural Language Models for Mobile Devices
• Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means
• Capsule Routing via Variational Bayes
• A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
• High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
• A Method to Model Conditional Distributions with Normalizing Flows
• Learning What and Where to Draw
• Uncertainty Quantification with Generative Models
• Variational Pedestrian Detection
• You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
• Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
• Hierarchical Variational Models
• Digital phase-only holography using deep conditional generative models
• Scalable Microservice Forensics and Stability Assessment Using Variational Autoencoders
• Using RGB Image as Visual Input for Mapless Robot Navigation
• Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
• Pose-Guided High-Resolution Appearance Transfer via Progressive Training
• Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
• Probabilistic Active Meta-Learning
• Reinforcement Learning with Efficient Active Feature Acquisition
• Cross-Modal Contrastive Learning for Text-to-Image Generation
• Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing
• Simple and Effective VAE Training with Calibrated Decoders
• Generating Object Stamps
• Deep Random Splines for Point Process Intensity Estimation of Neural Population Data
• Irregular Convolutional Auto-Encoder on Point Clouds
• Minimum Width for Universal Approximation
• The Thermodynamic Variational Objective
• Multi-Agent Reinforcement Learning with Multi-Step Generative Models
• Roof Age Determination for the Automated Site-Selection of Rooftop Solar
• Single Episode Policy Transfer in Reinforcement Learning
• Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder
• Spatially-weighted Anomaly Detection with Regression Model
• Unsupervised Learning of Video Representations using LSTMs
• Variational Neural Discourse Relation Recognizer
• Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
• 3D-Aware Semantic-Guided Generative Model for Human Synthesis
• Human Trajectory Prediction via Counterfactual Analysis
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
• Discovering Dialog Structure Graph for Open-Domain Dialog Generation
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity
• Anime Style Space Exploration Using Metric Learning and Generative Adversarial Networks
• Learning robust speech representation with an articulatory-regularized variational autoencoder
• Domain Private and Agnostic Feature for Modality Adaptive Face Recognition
• StackVAE-G: An efficient and interpretable model for time series anomaly detection
• TwoStreamVAN: Improving Motion Modeling in Video Generation
• Disentangling Content and Style via Unsupervised Geometry Distillation
• Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data
• How to Train Your Energy-Based Models
• Compute Trends Across Three Eras of Machine Learning
• Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings
• MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
• 3D Organ Shape Reconstruction from Topogram Images
• Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation
• It Is Likely That Your Loss Should be a Likelihood
• Exchangeable Neural ODE for Set Modeling
• Expected Information Maximization: Using the I-Projection for Mixture Density Estimation
• Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
• Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
• Top-N: Equivariant set and graph generation without exchangeability
• Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement
• Symmetric Wasserstein Autoencoders
• Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective
• Pose Guided Human Video Generation
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
• Expressive TTS Training with Frame and Style Reconstruction Loss
• Relevance Factor VAE: Learning and Identifying Disentangled Factors
• Nonparametric Inference for Auto-Encoding Variational Bayes
• Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs
• Deep Residual Mixture Models
• PAUL: Procrustean Autoencoder for Unsupervised Lifting
• Decoupling Global and Local Representations via Invertible Generative Flows
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image\n Restoration
• Conditional Flow Variational Autoencoders for Structured Sequence Prediction
• A Tutorial on VAEs: From Bayes' Rule to Lossless Compression
• Input Dependent Sparse Gaussian Processes
• CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
• Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
• Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
• Variational Auto Encoder Gradient Clustering
• SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
• Variational Inference using Implicit Distributions
• A Variational Auto-Encoder Approach for Image Transmission in Wireless Channel
• Encoders and Ensembles for Task-Free Continual Learning
• Bridging the Gap Between f-GANs and Wasserstein GANs
• Cost-sensitive detection with variational autoencoders for environmental acoustic sensing
• Mixture factorized auto-encoder for unsupervised hierarchical deep factorization of speech signal
• Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
• Combining Model and Parameter Uncertainty in Bayesian Neural Networks
• Are Generative Classifiers More Robust to Adversarial Attacks?
• Policy Optimization with Second-Order Advantage Information
• Exploiting Persona Information for Diverse Generation of Conversational Responses
• Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement
• DwNet: Dense warp-based network for pose-guided human video generation
• Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
• Neural Code Search Revisited: Enhancing Code Snippet Retrieval through Natural Language Intent
• Digging deeper: deep joint species distribution modeling reveals environmental drivers of Earthworm Communities
• SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation
• Dual Variational Generation for Low-Shot Heterogeneous Face Recognition
• Vertical-Horizontal Structured Attention for Generating Music with Chords
• Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
• Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
• Statistics of Deep Generated Images
• Audio query-based music source separation
• Lifting 2D StyleGAN for 3D-Aware Face Generation
• MPG: A Multi-ingredient Pizza Image Generator with Conditional StyleGANs
• Scalable and Efficient Comparison-based Search without Features
• Structured Black Box Variational Inference for Latent Time Series Models
• Lifelong Twin Generative Adversarial Networks
• Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods
• LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
• Disentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders
• ANFIC: Image Compression Using Augmented Normalizing Flows
• Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations
• Exponential Family Estimation via Adversarial Dynamics Embedding
• On the Limitations of Multimodal VAEs
• Recent Advances in Autoencoder-Based Representation Learning
• Bringing Old Photos Back to Life
• Topic Modelling Meets Deep Neural Networks: A Survey
• Adversarially Approximated Autoencoder for Image Generation and Manipulation
• Neural Photo Editing with Introspective Adversarial Networks
• Entropic Issues in Likelihood-Based OOD Detection
• Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models
• Neural Manifold Ordinary Differential Equations
• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
• The Variational Predictive Natural Gradient
• The Dynamic Embedded Topic Model
• Hierarchical Kinematic Human Mesh Recovery
• Cascading Denoising Auto-Encoder as a Deep Directed Generative Model
• Controllable Level Blending between Games using Variational Autoencoders
• Treatment effect estimation with disentangled latent factors
• Generalized Energy Based Models
• A Metric for Linear Symmetry-Based Disentanglement
• Rethinking Losses for Diffusion Bridge Samplers
• MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing
• Planning from Pixels using Inverse Dynamics Models
• Learning to Rectify for Robust Learning with Noisy Labels
• Planning from Images with Deep Latent Gaussian Process Dynamics
• A Semantic-based Medical Image Fusion Approach
• Visual Reinforcement Learning with Imagined Goals
• Bi-Discriminator Class-Conditional Tabular GAN
• Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
• Flow-based Generative Models for Learning Manifold to Manifold Mappings
• Variational Autoencoder with Arbitrary Conditioning
• Edge-Enhanced Global Disentangled Graph Neural Network for Sequential Recommendation
• Evaluating representations by the complexity of learning low-loss predictors
• Geometric Disentanglement by Random Convex Polytopes
• Uncertainty Quantification in Computer-Aided Diagnosis: Make Your Model say "I don't know" for Ambiguous Cases
• Disentangled Variational Representation for Heterogeneous Face Recognition
• A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU
• A Factorial Mixture Prior for Compositional Deep Generative Models
• Generalization to Novel Objects using Prior Relational Knowledge
• Video Content Swapping Using GAN
• Adversarial Network Embedding
• CATE: Computation-aware Neural Architecture Encoding with Transformers
• Learning normalized image densities via dual score matching
• WiSE-ALE: Wide Sample Estimator for Approximate Latent Embedding
• Boosting Variational Inference
• Risk-Averse Offline Reinforcement Learning
• A lower bound for the ELBO of the Bernoulli Variational Autoencoder
• Auto-Encoding Knockoff Generator for FDR Controlled Variable Selection
• SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
• Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
• Reweighted Wake-Sleep
• End-to-end Learning of Driving Models from Large-scale Video Datasets
• Attentive Neural Processes
• Denoising Diffusion Gamma Models
• Image-Based Reconstruction for a 3D-PFHS Heat Transfer Problem by ReConNN
• Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity
• Bandwidth Extension on Raw Audio via Generative Adversarial Networks
• On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset
• Probabilistic Approach for Road-Users Detection
• Variable-rate discrete representation learning
• Few-Shot Adaptation of Generative Adversarial Networks
• Spectral Synthesis for Satellite-to-Satellite Translation
• Dense Uncertainty Estimation
• Interactive user interface based on Convolutional Auto-encoders for annotating CT-scans
• Autoencoding Under Normalization Constraints
• Bayesian Compression for Deep Learning
• Coarse Grained Exponential Variational Autoencoders
• Regularizing Model-Based Planning with Energy-Based Models
• Uniform Interpolation Constrained Geodesic Learning on Data Manifold
• Creativity in the era of artificial intelligence
• Amortised Learning by Wake-Sleep
• OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
• Deep Learning Enables Robust and Precise Light Focusing on Treatment Needs
• Wasserstein Dependency Measure for Representation Learning
• Unrestricted Adversarial Examples via Semantic Manipulation
• Stabilizing Generative Adversarial Networks: A Survey
• Dynamic Narrowing of VAE Bottlenecks Using GECO and L0 Regularization
• Representing and Denoising Wearable ECG Recordings
• Data-driven Regularized Inference Privacy
• Offline Reinforcement Learning with Reverse Model-based Imagination
• Expected path length on random manifolds
• Recurrent Latent Variable Networks for Session-Based Recommendation
• Learning Multimodal VAEs through Mutual Supervision
• Deep Variational Sufficient Dimensionality Reduction
• Learning to Shift Attention for Motion Generation
• Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks
• Towards QoE-Driven Optimization of Multi-Dimensional Content Streaming
• Semi-Supervised Domain Generalization with Stochastic StyleMatch
• Invertible Manifold Learning for Dimension Reduction
• Variational Gaussian Copula Inference
• MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
• CNN in CT Image Segmentation: Beyound Loss Function for Expoliting Ground Truth Images
• Variational Attention for Sequence-to-Sequence Models
• Training Generative Reversible Networks
• Unsupposable Test-data Generation for Machine-learned Software
• Adversarial Disentanglement with Grouped Observations
• A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
• Distribution Aware Active Learning
• Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
• Safer Classification by Synthesis
• A Universal Music Translation Network
• Flexible mean field variational inference using mixtures of non-overlapping exponential families
• Improving Direct Physical Properties Prediction of Heterogeneous Materials from Imaging Data via Convolutional Neural Network and a Morphology-Aware Generative Model
• Ensemble Kalman Variational Objectives: Nonlinear Latent Trajectory Inference with A Hybrid of Variational Inference and Ensemble Kalman Filter
• Radial and Directional Posteriors for Bayesian Neural Networks
• Causal Inference with Deep Causal Graphs
• Text Generation with Deep Variational GAN
• Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations
• Graph Convolutional Memory using Topological Priors
• Lung Cancer Risk Estimation with Incomplete Data: A Joint Missing Imputation Perspective
• PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network
• On denoising autoencoders trained to minimise binary cross-entropy
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Perturbative estimation of stochastic gradients
• Long-term Human Motion Prediction with Scene Context
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
• StructureNet: Hierarchical Graph Networks for 3D Shape Generation
• StyleDEM: a Versatile Model for Authoring Terrains
• HuGeDiff: 3D Human Generation via Diffusion with Gaussian Splatting
• Deep Learning on Graphs: A Survey
• Variational Saccading: Efficient Inference for Large Resolution Images
• Deep Markov Random Field for Image Modeling
• Generative Neurosymbolic Machines
• ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
• Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
• An Uncertain Future: Forecasting from Static Images using Variational Autoencoders
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Group Equivariant Conditional Neural Processes
• Variational Inference via χ-Upper Bound Minimization
• BOSS: Bayesian Optimization over String Spaces
• Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
• Path and Bone-Contour Regularized Unpaired MRI-to-CT Translation
• Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
• Improving Generalization in Meta-RL with Imaginary Tasks from Latent\n Dynamics Mixture
• Neural representation and generation for RNA secondary structures
• FIGR: Few-shot Image Generation with Reptile
• Variational Inference for Computational Imaging Inverse Problems
• Learning GPLVM with arbitrary kernels using the unscented transformation
• Differentiable TAN Structure Learning for Bayesian Network Classifiers
• Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation
• New Tricks for Estimating Gradients of Expectations
• Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks
• Unconditional CNN denoisers contain sparse semantic representation of images
• Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Variational Bayesian Quantization
• Local Expectation Gradients for Doubly Stochastic Variational Inference
• Learning Neural Light Transport
• MONet: Unsupervised Scene Decomposition and Representation
• Shapley explainability on the data manifold
• Responsible Disclosure of Generative Models Using Scalable Fingerprinting
• DDTCDR: Deep Dual Transfer Cross Domain Recommendation
• Deep Generative Dual Memory Network for Continual Learning
• Unified Adversarial Invariance
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies
• SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions
• A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning
• NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform
• Generative 3D Part Assembly via Dynamic Graph Learning
• Pitchtron: Towards audiobook generation from ordinary people's voices
• Stochastic Talking Face Generation Using Latent Distribution Matching
• DiffWave: A Versatile Diffusion Model for Audio Synthesis
• Multilevel Monte Carlo estimation of log marginal likelihood
• A Dynamic Edge Exchangeable Model for Sparse Temporal Networks
• Task-Generic Hierarchical Human Motion Prior using VAEs
• Cyrus+: A DRL-based Puncturing Solution to URLLC/eMBB Multiplexing in O-RAN
• InfoColorizer: Interactive Recommendation of Color Palettes for Infographics
• Structured Bayesian Gaussian process latent variable model
• Emergent Graphical Conventions in a Visual Communication Game
• Inductive Representation Learning on Temporal Graphs
• Unsupervised Image-to-Image Translation Networks
• The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design
• Explainability Requires Interactivity
• Statistical and Topological Properties of Sliced Probability Divergences
• Dense Pose Transfer
• Deep Copula Classifier: Theory, Consistency, and Empirical Evaluation
• Learning to Predict Explainable Plots for Neural Story Generation
• Disentangled Variational Information Bottleneck for Multiview Representation Learning
• Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
• Variational Determinant Estimation with Spherical Normalizing Flows
• Invertible Zero-Shot Recognition Flows
• Bayesian Quadrature on Riemannian Data Manifolds
• Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
• Self-Constructing Graph Convolutional Networks for Semantic Labeling
• Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
• Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction
• Embodied Self-supervised Learning by Coordinated Sampling and Training
• Improving Text to Image Generation using Mode-seeking Function
• Rectangular Flows for Manifold Learning
• Learning to Generate Chairs, Tables and Cars with Convolutional Networks
• Label-Free Segmentation of COVID-19 Lesions in Lung CT
• Pairwise Augmented GANs with Adversarial Reconstruction Loss
• ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
• Assisting Scene Graph Generation with Self-Supervision
• Generating Semantically Valid Adversarial Questions for TableQA
• A Benchmark of Medical Out of Distribution Detection
• Solving inverse problems via auto-encoders
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
• Towards robustness under occlusion for face recognition
• Discrete Action On-Policy Learning with Action-Value Critic
• Continuous Graph Flow
• Video Autoencoder: self-supervised disentanglement of static 3D structure and motion
• UFO-BLO: Unbiased First-Order Bilevel Optimization
• Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits
• VCE: Variational Convertor-Encoder for One-Shot Generalization
• S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
• From the Expectation Maximisation Algorithm to Autoencoded Variational Bayes
• Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
• Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting
• Automatic Feature Extraction for Heartbeat Anomaly Detection
• All You Need is a Good Functional Prior for Bayesian Deep Learning
• Probabilistic Autoencoder
• Physics-constrained, data-driven discovery of coarse-grained dynamics
• Causal Discovery with Cascade Nonlinear Additive Noise Models
• Unsupervised Learning of Lidar Features for Use in a Probabilistic Trajectory Estimator
• Deep Learning Based Text Classification: A Comprehensive Review
• Self-Supervised Out-of-Distribution Detection in Brain CT Scans
• TD-GEN: Graph Generation With Tree Decomposition
• Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders
• A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model
• Tighter Variational Bounds are Not Necessarily Better
• Recursive Inference for Variational Autoencoders
• LAFITE: Towards Language-Free Training for Text-to-Image Generation
• Verification of ML Systems via Reparameterization
• Gradient Estimation with Stochastic Softmax Tricks
• LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning
• Reinforced Latent Reasoning for LLM-based Recommendation
• Planning with Expectation Models for Control
• Automatic Backward Filtering Forward Guiding for Markov processes and\n graphical models
• WakaVT: A Sequential Variational Transformer for Waka Generation
• Style Transfer with Time Series: Generating Synthetic Financial Data
• Relay Variational Inference: A Method for Accelerated Encoderless VI
• Gradients as Features for Deep Representation Learning
• EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision
• Generative Interventions for Causal Learning
• Deep Generative Models for Distribution-Preserving Lossy Compression
• MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents
• Fixing a Broken ELBO
• Lightweight Data Fusion with Conjugate Mappings
• Multi-View Variational Autoencoder for Missing Value Imputation in Untargeted Metabolomics
• Guided Image Generation with Conditional Invertible Neural Networks
• Predictive Uncertainty Quantification with Compound Density Networks
• Deep Learning Based Unsupervised and Semi-supervised Classification for Keratoconus
• Combining Spiking Neural Network and Artificial Neural Network for Enhanced Image Classification
• Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
• Learning Global and Local Features of Normal Brain Anatomy for Unsupervised Abnormality Detection
• Posterior inference unchained with EL₂O
• Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit
• A Practical & Unified Notation for Information-Theoretic Quantities in ML
• On the Practical Consistency of Meta-Reinforcement Learning Algorithms
• Generative Learning With Euler Particle Transport
• Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
• PLAS: Latent Action Space for Offline Reinforcement Learning
• ColdGAN: Resolving Cold Start User Recommendation by using Generative Adversarial Networks
• Variational Recurrent Neural Machine Translation
• Anomaly Detection Based on Deep Learning Using Video for Prevention of Industrial Accidents
• Deep k-Means: Jointly clustering with k-Means and learning representations
• Maximizing Mutual Information for Tacotron
• Factored Temporal Sigmoid Belief Networks for Sequence Learning
• Auto-Encoding Variational Bayes for Inferring Topics and Visualization
• Perpetual Motion: Generating Unbounded Human Motion
• Deep Goal-Oriented Clustering
• Predicting Deeper into the Future of Semantic Segmentation
• Amortized Bethe Free Energy Minimization for Learning MRFs
• MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
• SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
• An ETF view of Dropout regularization
• Bayesian Sparsification Methods for Deep Complex-valued Networks
• Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems
• Model Selection for Bayesian Autoencoders
• Learning Controllable Disentangled Representations with Decorrelation Regularization
• Particle Smoothing Variational Objectives
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Graph-Conditional Flow Matching for Relational Data Generation
• Copula-like Variational Inference
• Neural Topic Models with Survival Supervision: Jointly Predicting Time-to-Event Outcomes and Learning How Clinical Features Relate
• Nonparallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks
• Learning Continuous-Time Dynamics by Stochastic Differential Networks
• Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis
• Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding
• Fast uncertainty quantification of reservoir simulation with variational U-Net
• Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
• Surfing: Iterative optimization over incrementally trained deep networks
• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control
• Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
• Quantitative Evaluation of Time-Dependent Multidimensional Projection Techniques
• Interspatial Attention for Efficient 4D Human Video Generation
• Monotonic Gaussian Process Flow
• Controllable Image Synthesis via SegVAE
• Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization
• Reconstruction Bottlenecks in Object-Centric Generative Models
• Accelerating Continuous Normalizing Flow with Trajectory Polynomial Regularization
• IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse
• Deep Predictive Policy Training using Reinforcement Learning
• Towards Verified Stochastic Variational Inference for Probabilistic Programs
• Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations
• Bayesian Variational Optimization for Combinatorial Spaces
• Training Deep Learning Based Denoisers without Ground Truth Data
• P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection
• Generative Hierarchical Features from Synthesizing Images
• Pathwise Derivatives Beyond the Reparameterization Trick
• A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
• Design, Benchmarking and Explainability Analysis of a Game-Theoretic Framework towards Energy Efficiency in Smart Infrastructure
• Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
• Class-Distinct and Class-Mutual Image Generation with GANs
• Disentangled Representations from Non-Disentangled Models
• Random Projection in Neural Episodic Control
• GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes
• Latent Programmer: Discrete Latent Codes for Program Synthesis
• Random Feature Expansions for Deep Gaussian Processes
• Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
• Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
• Deep Semi-Supervised Anomaly Detection
• Gaussian Copula Variational Autoencoders for Mixed Data
• What Is Considered Complete for Visual Recognition?
• Data Generation as Sequential Decision Making
• Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective
• Semantic Editing On Segmentation Map Via Multi-Expansion Loss
• IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System
• Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
• Challenges in Disentangling Independent Factors of Variation
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data
• Intrinsic motivations and open-ended learning
• Research and development of MolAICal for drug design via deep learning and classical programming
• DeepOBS: A Deep Learning Optimizer Benchmark Suite
• Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models
• Learning Beyond Human Expertise with Generative Models for Dental Restorations
• Machine learning in the social and health sciences
• Geometrically Enriched Latent Spaces
• Predictive coding feedback results in perceived illusory contours in a recurrent neural network
• TensorFlow Distributions
• Unpaired Image-to-Image Translation via Latent Energy Transport
• Space Group Equivariant Crystal Diffusion
• How Sequence-to-Sequence Models Perceive Language Styles?
• Deep generative modelling of aircraft trajectories in terminal maneuvering areas
• Data-efficient visuomotor policy training using reinforcement learning and generative models
• A Cross-Level Information Transmission Network for Predicting Phenotype from New Genotype: Application to Cancer Precision Medicine
• Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery
• Deep learning technology for face forgery detection: A survey
• Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
• TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
• Unmasking DeepFakes with simple Features
• Demystifying Inter-Class Disentanglement
• No MCMC for me: Amortized sampling for fast and stable training of energy-based models
• A Tutorial on the Mathematical Model of Single Cell Variational Inference
• Black-box Adversarial Attacks with Bayesian Optimization
• Unsupervised multi-modal Styled Content Generation
• Database development and exploration of microstructure versus process relationships using variational autoencoders
• Autoregressive Score Matching
• Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
• Uncertainty Inspired RGB-D Saliency Detection
• Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling
• Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder
• Bandit algorithms for real-time data capture on large social medias
• Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes
• TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud Generation
• Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes
• Realistic molecule optimization on a learned graph manifold
• Contrastive Active Inference
• Reparameterized Sampling for Generative Adversarial Networks
• Scalable Modeling of Spatiotemporal Data using the Variational Autoencoder: an Application in Glaucoma
• A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features
• Generative Transition Mechanism to Image-to-Image Translation via Encoded Transformation
• From Artificial Neural Networks to Deep Learning for Music Generation -- History, Concepts and Trends
• Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder
• ConDiSim: Conditional Diffusion Models for Simulation Based Inference
• What Do We Mean by Generalization in Federated Learning?
• DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
• GAN-based Pose-aware Regulation for Video-based Person Re-identification
• Sparse Orthogonal Variational Inference for Gaussian Processes
• The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
• Model Inversion Networks for Model-Based Optimization
• Semantic and Geometric Unfolding of StyleGAN Latent Space
• Deep Directed Generative Autoencoders
• Learning mappings onto regularized latent spaces for biometric\n authentication
• Contextualisation of eCommerce Users
• Exposure: A White-Box Photo Post-Processing Framework
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
• Variational Capsules for Image Analysis and Synthesis
• Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
• Meta-SVDD: Probabilistic Meta-Learning for One-Class Classification in Cancer Histology Images
• Nonparametric Density Estimation under Adversarial Losses
• Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation
• Recurrent Flow Networks: A Recurrent Latent Variable Model for Density Modelling of Urban Mobility
• Generative Melody Composition with Human-in-the-Loop Bayesian Optimization
• Multi-Terminal Remote Generation and Estimation Over a Broadcast Channel With Correlated Priors
• Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders
• Exploring Dynamic Context for Multi-path Trajectory Prediction
• Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)
• Zero-Shot Recognition via Optimal Transport
• A Systematic Assessment of Deep Learning Models for Molecule Generation
• Energy Consumption of Deep Generative Audio Models
• Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
• Coulomb Autoencoders
• Smoothed Action Value Functions for Learning Gaussian Policies
• Learning Continuous Environment Fields via Implicit Functions
• Modeling continuous-time stochastic processes using \N-Curve\n mixtures
• Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
• AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
• tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder
• VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
• Restricting the Flow: Information Bottlenecks for Attribution
• Hierarchically Clustered Representation Learning
• Gmail Smart Compose: Real-Time Assisted Writing
• The backpropagation-based recollection hypothesis: Backpropagated action potentials mediate recall, imagination, language understanding and naming
• Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
• AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation
• Learning to infer in recurrent biological networks
• Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections
• Variational Inference: A Review for Statisticians
• Latent feature disentanglement for 3D meshes
• The Implicit Metropolis-Hastings Algorithm
• Calibrating Deep Convolutional Gaussian Processes
• Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
• AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models
• Deep Reinforcement Learning: An Overview
• Deep Learning for Genomics: A Concise Overview
• Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation
• An Empirical Study of Stochastic Variational Algorithms for the Beta Bernoulli Process
• Detection of Deepfake Videos Using Long Distance Attention
• Customizing Sequence Generation with Multi-Task Dynamical Systems
• Latent Multi-Criteria Ratings for Recommendations
• SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations
• Learning to learn generative programs with Memoised Wake-Sleep
• Node Attribute Generation on Graphs
• Training VAEs Under Structured Residuals
• Conditional Adversarial Generative Flow for Controllable Image Synthesis
• A PCA-like Autoencoder
• Local Competition and Stochasticity for Adversarial Robustness in Deep Learning
• Truncated Gaussian-Mixture Variational AutoEncoder
• Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
• Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning
• CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge
• Leveraging Cross Feedback of User and Item Embeddings with Attention for Variational Autoencoder based Collaborative Filtering
• Neural Articulated Radiance Field
• Nonlinear reduced-order modeling for three-dimensional turbulent flow by large-scale machine learning
• Sim2Real for Self-Supervised Monocular Depth and Segmentation
• Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
• Geometry-Aware Hamiltonian Variational Auto-Encoder
• Fractional Transfer Learning for Deep Model-Based Reinforcement Learning
• Visualization of AE's Training on Credit Card Transactions with Persistent Homology
• Synthesizing Filamentary Structured Images with GANs
• Deep Tensor CCA for Multi-view Learning
• Combinatorial 3D Shape Generation via Sequential Assembly
• Variational Inference with Numerical Derivatives: variance reduction through coupling
• Unsupervised Visual Representation Learning by Context Prediction
• MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
• Spatio-Temporal Anomaly Detection with Graph Networks for Data Quality Monitoring of the Hadron Calorimeter
• MAD-VAE: Manifold Awareness Defense Variational Autoencoder
• MIM: Mutual Information Machine
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models
• PixelCNN Models with Auxiliary Variables for Natural Image Modeling
• Bayesian Neural Decoding Using A Diversity-Encouraging Latent Representation Learning Method
• A Style-Based Generator Architecture for Generative Adversarial Networks
• Low-Variance Policy Gradient Estimation with World Models
• Bidirectional Generative Modeling Using Adversarial Gradient Estimation
• Wasserstein Measure Coresets
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks
• Holographic Neural Architectures
• A Practical Layer-Parallel Training Algorithm for Residual Networks
• Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition
• NVAE: A Deep Hierarchical Variational Autoencoder
• Generating Images from Captions with Attention
• Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extraction
• Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift
• Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder
• Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks
• Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
• Variational Encoders and Autoencoders : Information-theoretic Inference and Closed-form Solutions
• MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
• Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
• Domain-Specific Mappings for Generative Adversarial Style Transfer
• NAOMI: Non-Autoregressive Multiresolution Sequence Imputation
• From Persistent Homology to Reinforcement Learning with Applications for Retail Banking
• Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech
• Language coverage and generalization in RNN-based continuous sentence embeddings for interacting agents
• Information Theoretic Structured Generative Modeling
• ProBO: Versatile Bayesian Optimization Using Any Probabilistic Programming Language
• dMelodies: A Music Dataset for Disentanglement Learning
• Unsupervised Disentanglement of Linear-Encoded Facial Semantics
• Zero-shot Synthesis with Group-Supervised Learning
• Latent Variable Session-Based Recommendation
• Beyond Low Earth Orbit: Biological Research, Artificial Intelligence, and Self-Driving Labs
• State of the Art on Neural Rendering
• An Interactive Insight Identification and Annotation Framework for Power Grid Pixel Maps using DenseU-Hierarchical VAE
• Augmenting Physical Simulators with Stochastic Neural Networks: Case\n Study of Planar Pushing and Bouncing
• Artificial intelligence in radiology
• CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation
• A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
• Signature-Graph Networks
• Towards the Unseen: Iterative Text Recognition by Distilling from Errors
• Reconciling deep learning with symbolic artificial intelligence: representing objects and relations
• Dynamic Routing Networks
• Stochastic Adversarial Video Prediction
• Game Theoretical Adversarial Deep Learning With Variational Adversaries
• A Test of Relative Similarity For Model Selection in Generative Models
• Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
• Semi-Supervised Learning with Generative Adversarial Networks
• Deep Variational Semi-Supervised Novelty Detection
• Stochastic Backpropagation through Mixture Density Distributions
• Transductive Zero-Shot Learning by Decoupled Feature Generation
• Embedding Empirical Distributions for Computing Optimal Transport Maps
• DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
• Learning Latent State Spaces for Planning through Reward Prediction
• Investigation of Using VAE for i-Vector Speaker Verification
• Image Generation From Small Datasets via Batch Statistics Adaptation
• Disentangled Recurrent Wasserstein Autoencoder
• Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation
• Low-Resource Knowledge-Grounded Dialogue Generation
• Towards bio-inspired unsupervised representation learning for indoor aerial navigation
• Learning Mesh Representations via Binary Space Partitioning Tree Networks
• Learning Functions over Sets via Permutation Adversarial Networks
• Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
• On Disentanglement in Gaussian Process Variational Autoencoders
• Addressing the Topological Defects of Disentanglement via Distributed\n Operators
• mmFall: Fall Detection using 4D MmWave Radar and a Hybrid Variational RNN AutoEncoder
• Unsupervised machine learning of topological phase transitions from experimental data
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• Graphusion: Latent Diffusion for Graph Generation
• I-nteract 2.0: A Cyber-Physical System to Design 3D Models using Mixed Reality Technologies and Deep Learning for Additive Manufacturing
• Physics-informed GANs for Coastal Flood Visualization
• Learning Document Embeddings Along With Their Uncertainties
• Fast Black-box Variational Inference through Stochastic Trust-Region Optimization
• MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning
• Inf-VAE
• Swapping Autoencoder for Deep Image Manipulation
• Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
• Learning feed-forward one-shot learners
• Signal Retrieval With Measurement System Knowledge Using Variational Generative Model
• UVA: A Universal Variational Framework for Continuous Age Analysis
• Towards to Robust and Generalized Medical Image Segmentation Framework
• Inferential Wasserstein Generative Adversarial Networks
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning
• Sensorimotor Visual Perception on Embodied System Using Free Energy Principle
• Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks
• Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
• Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network
• Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
• Survival-oriented embeddings for improving accessibility to complex data structures
• Accelerated Discovery of Sustainable Building Materials
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
• Augmenting and Tuning Knowledge Graph Embeddings
• Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning
• Provably robust deep generative models
• Out-of-Distribution Detection of Melanoma using Normalizing Flows
• Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
• Learning the Compositional Spaces for Generalized Zero-shot Learning
• Discriminative, Generative and Self-Supervised Approaches for Target-Agnostic Learning
• Learning Conditionally Independent Transformations using Normal Subgroups in Group Theory
• Stochastic Optimization of Sorting Networks via Continuous Relaxations
• Dual Adversarial Inference for Text-to-Image Synthesis
• Robust Ordinal VAE: Employing Noisy Pairwise Comparisons for Disentanglement
• GILBO: One Metric to Measure Them All
• Unsupervised Generative Modeling Using Matrix Product States
• Representation, learning, and planning algorithms for geometric task and motion planning
• Hyperspectral Denoising Using Unsupervised Disentangled Spatiospectral Deep Priors
• Integration of Adversarial Autoencoders With Residual Dense Convolutional Networks for Estimation of Non‐Gaussian Hydraulic Conductivities
• A comparison of classical and variational autoencoders for anomaly\n detection
• Intent-aware Diffusion with Contrastive Learning for Sequential Recommendation
• Compound Probabilistic Context-Free Grammars for Grammar Induction
• Autoencoding sensory substitution
• Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
• Learning Perceptual Manifold of Fonts
• Deep learning of thermodynamics-aware reduced-order models from data
• Dynamic Variational Autoencoders for Visual Process Modeling
• Radar Odometry Combining Probabilistic Estimation and Unsupervised\n Feature Learning
• Functional generative design
• Recursive Least Squares Based Refinement Network for the Rollout Trajectory Prediction Methods
• Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes
• Anomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation
• Residual-Recursion Autoencoder for Shape Illustration Images
• A survey on Variational Autoencoders from a GreenAI perspective
• Dimensionality Reduction for Categorical Data
• Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
• Image-based reconstruction for the impact problems by using DPNNs
• Metropolis-Hastings view on variational inference and adversarial training
• Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures
• Causal Contextual Prediction for Learned Image Compression
• Tensorial Mixture Models
• Deep learning methods for solving linear inverse problems: Research directions and paradigms
• Boosting Generative Models by Leveraging Cascaded Meta-Models
• Style-transfer GANs for bridging the domain gap in synthetic pose estimator training
• Bidirectional Helmholtz Machines
• Learning pose-invariant 3D object reconstruction from single-view images
• Hierarchical VampPrior Variational Fair Auto-Encoder
• Target-Focused Feature Selection Using a Bayesian Approach
• Understanding and Improving Virtual Adversarial Training
• Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
• Artificial intelligence and deep learning algorithms for epigenetic sequence analysis: A review for epigeneticists and AI experts
• Implicit Generative Copulas
• On the Latent Holes of VAEs for Text Generation
• A causal view of compositional zero-shot recognition
• A Brief Overview of Unsupervised Neural Speech Representation Learning
• Parameter estimation for the cosmic microwave background with Bayesian neural networks
• Relational State-Space Model for Stochastic Multi-Object Systems
• Information Dropout: Learning Optimal Representations Through Noisy\n Computation
• PaintBot: A Reinforcement Learning Approach for Natural Media Painting
• Tackling Dynamics in Federated Incremental Learning with Variational\n Embedding Rehearsal
• End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning\n Tasks
• Tessellated Wasserstein Auto-Encoders
• Crossmodal Voice Conversion
• Kernel Mean Matching for Content Addressability of GANs
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Convolutional Normalizing Flows for Deep Gaussian Processes
• Preventing Posterior Collapse with delta-VAEs
• The Many Moods of Emotion
• A Linear Systems Theory of Normalizing Flows
• Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
• Reconstruction of pairwise interactions using energy-based models*
• IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay
• Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent
• OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
• Dual Contradistinctive Generative Autoencoder
• Domain Mismatch Robust Acoustic Scene Classification using Channel Information Conversion
• Semi-supervised Learning with Contrastive Predicative Coding
• Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild
• Scalable Multi-task Edge Sensing via Task-oriented Joint Information Gathering and Broadcast
• SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing
• Counterfactual state explanations for reinforcement learning agents via generative deep learning
• Towards Distribution Matching between Collaborative and Language Spaces for Generative Recommendation
• Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network
• Information Theoretic Meta Learning with Gaussian Processes
• Knowledge-Guided Object Discovery with Acquired Deep Impressions

Discussions

• It’s mind boggling for someone like me who works in a discipline (philosophy) that accords a lot to journal prestige that this paper in machine learning, a preprint (!) has 42298 citations on Google t [bsky, 20 points, 1 comments]
• Arxiv links so that it gets picked up by the paper discussion feed. VAE: arxiv.org/abs/1312.6114 and VQ-VAE: arxiv.org/abs/1711.00937 [bsky, 9 points, 1 comments]
• arxiv.org/abs/1312.6114 [bsky, 0 points, 0 comments]

Related

• Stick-Breaking Variational Autoencoders
• Variationally Inferred Sampling Through a Refined Bound for Probabilistic Programs
• Nonparametric Inference for Auto-Encoding Variational Bayes
• Training Variational Autoencoders with Buffered Stochastic Variational Inference
• Training Latent Variable Models with Auto-encoding Variational Bayes: A Tutorial