{"total":124,"rows":[{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239,"area":"diffusion"},{"id":"2106.06819","title":"D2C: Diffusion-Denoising Models for Few-shot Conditional Generation","created":"2021-06-12","cited_by_count":96,"area":null},{"id":"2102.07810","title":"HDMI: High-order Deep Multiplex Infomax","created":"2021-02-15","cited_by_count":82,"area":null},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72,"area":null},{"id":"2306.08757","title":"InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models","created":"2023-06-14","cited_by_count":50,"area":"diffusion"},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"area":null},{"id":"2303.16535","title":"Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning","created":"2023-03-29","cited_by_count":48,"area":null},{"id":"2307.13125","title":"Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review","created":"2023-07-24","cited_by_count":48,"area":null},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42,"area":null},{"id":"2102.09117","title":"Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking","created":"2021-02-18","cited_by_count":35,"area":null},{"id":"2310.14230","title":"A comprehensive survey on deep active learning in medical image analysis","created":"2023-10-22","cited_by_count":35,"area":null},{"id":"2303.10610","title":"DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification","created":"2023-03-19","cited_by_count":32,"area":"diffusion"},{"id":"2312.02156","title":"Latent Feature-Guided Diffusion Models for Shadow Removal","created":"2023-12-04","cited_by_count":29,"area":"diffusion"},{"id":"2402.09712","title":"Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement","created":"2024-02-15","cited_by_count":27,"area":"diffusion"},{"id":"2206.08309","title":"Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case","created":"2022-06-16","cited_by_count":26,"area":null},{"id":"2109.04999","title":"Fairness without the sensitive attribute via Causal Variational Autoencoder","created":"2021-09-10","cited_by_count":21,"area":null},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2509.02055","title":"Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance","created":"2025-09-02","cited_by_count":20,"area":"vla"},{"id":"2105.11730","title":"Exploring Autoencoder-based Error-bounded Compression for Scientific Data","created":"2021-05-25","cited_by_count":19,"area":null},{"id":"2306.01843","title":"Lifting Architectural Constraints of Injective Flows","created":"2023-06-02","cited_by_count":18,"area":null},{"id":"2312.09597","title":"Deep Generative Models for Detector Signature Simulation: A Taxonomic Review","created":"2023-12-15","cited_by_count":18,"area":null},{"id":"2111.06636","title":"Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction","created":"2021-11-12","cited_by_count":17,"area":null},{"id":"2303.12484","title":"Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions","created":"2023-03-22","cited_by_count":16,"area":null},{"id":"2501.00910","title":"Population Aware Diffusion for Time Series Generation","created":"2025-01-01","cited_by_count":16,"area":"diffusion"},{"id":"2106.05886","title":"Group Equivariant Subsampling","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2203.00412","title":"Interpretable Molecular Graph Generation via Monotonic Constraints","created":"2022-02-28","cited_by_count":15,"area":null},{"id":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14,"area":null},{"id":"2207.04624","title":"Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting","created":"2022-07-11","cited_by_count":14,"area":null},{"id":"2312.11243","title":"GraspLDM: Generative 6-DoF Grasp Synthesis using Latent Diffusion Models","created":"2023-12-18","cited_by_count":13,"area":"diffusion"},{"id":"2203.00411","title":"Disentangled Spatiotemporal Graph Generative Models","created":"2022-02-28","cited_by_count":12,"area":null},{"id":"2207.04895","title":"Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility","created":"2022-07-11","cited_by_count":12,"area":null},{"id":"2307.00761","title":"Learning Degradation-Independent Representations for Camera ISP Pipelines","created":"2023-07-03","cited_by_count":11,"area":null},{"id":"2106.16091","title":"Exploring the Latent Space of Autoencoders with Interventional Assays","created":"2021-06-30","cited_by_count":10,"area":null},{"id":"2205.05862","title":"AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2205.11640","title":"Generalization Gap in Amortized Inference","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2403.19026","title":"EgoNav: Egocentric Scene-aware Human Trajectory Prediction","created":"2024-03-27","cited_by_count":9,"area":"diffusion"},{"id":"2404.04920","title":"Regularized Conditional Diffusion Model for Multi-Task Preference Alignment","created":"2024-04-07","cited_by_count":9,"area":"diffusion"},{"id":"2104.01109","title":"AI Fairness via Domain Adaptation","created":"2021-03-15","cited_by_count":8,"area":null},{"id":"2104.05064","title":"Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling","created":"2021-04-11","cited_by_count":8,"area":null},{"id":"2210.11779","title":"Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2202.12154","title":"Towards Effective and Robust Neural Trojan Defenses via Input Filtering","created":"2022-02-24","cited_by_count":7,"area":null},{"id":"2202.13341","title":"Overlooked Implications of the Reconstruction Loss for VAE Disentanglement","created":"2022-02-27","cited_by_count":7,"area":null},{"id":"2207.09535","title":"Forget-me-not! Contrastive Critics for Mitigating Posterior Collapse","created":"2022-07-19","cited_by_count":6,"area":null},{"id":"2209.05485","title":"CustOmics: A versatile deep-learning based strategy for multi-omics integration","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2307.12586","title":"InVAErt networks: a data-driven framework for model synthesis and identifiability analysis","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2310.06557","title":"Data efficient deep learning for medical image analysis: A survey","created":"2023-10-10","cited_by_count":6,"area":null},{"id":"2411.16370","title":"A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation","created":"2024-11-25","cited_by_count":6,"area":null},{"id":"2109.07399","title":"Disentangling Generative Factors of Physical Fields Using Variational Autoencoders","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2210.13634","title":"Vitruvio: 3D Building Meshes via Single Perspective Sketches","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2307.05317","title":"Automatic Generation of Semantic Parts for Face Image Synthesis","created":"2023-07-11","cited_by_count":5,"area":null},{"id":"2307.15977","title":"Model Synthesis for Zero-Shot Model Attribution","created":"2023-07-29","cited_by_count":5,"area":null},{"id":"2402.01514","title":"Mapping the Multiverse of Latent Representations","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2505.15217","title":"Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2507.03054","title":"LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection","created":"2025-07-03","cited_by_count":5,"area":"diffusion"},{"id":"2510.21887","title":"Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications","created":"2025-10-23","cited_by_count":5,"area":"diffusion"},{"id":"2103.16442","title":"SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks","created":"2021-03-30","cited_by_count":4,"area":null},{"id":"2109.14216","title":"Spread Flows for Manifold Modelling","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2110.04616","title":"Discriminative Multimodal Learning via Conditional Priors in Generative Models","created":"2021-10-09","cited_by_count":4,"area":null},{"id":"2210.05677","title":"Application of Deep Learning on Single-Cell RNA-sequencing Data Analysis: A Review","created":"2022-10-11","cited_by_count":4,"area":null},{"id":"2402.15710","title":"A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data","created":"2024-02-24","cited_by_count":4,"area":null},{"id":"2410.02060","title":"PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2410.23820","title":"Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models","created":"2024-10-31","cited_by_count":4,"area":"diffusion"},{"id":"2103.11265","title":"Bayesian Distributional Policy Gradients","created":"2021-03-20","cited_by_count":3,"area":null},{"id":"2202.05694","title":"Continual Learning with Invertible Generative Models","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2204.03030","title":"Statistical Model Criticism of Variational Auto-Encoders","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2206.03211","title":"Variational Meta Reinforcement Learning for Social Robotics","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2311.06527","title":"TURBO: The Swiss Knife of Auto-Encoders","created":"2023-11-11","cited_by_count":3,"area":null},{"id":"2410.08824","title":"One-shot Generative Domain Adaptation in 3D GANs","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2506.08957","title":"IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2506.08963","title":"Evaluating Generative Vehicle Trajectory Models for Traffic Intersection Dynamics","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2602.01536","title":"UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2101.02568","title":"HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification","created":"2021-01-06","cited_by_count":2,"area":null},{"id":"2112.01583","title":"The Representation Jensen-R\\'enyi Divergence","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2206.00436","title":"Top-down inference in an early visual cortex inspired hierarchical Variational Autoencoder","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2307.16694","title":"Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging","created":"2023-07-31","cited_by_count":2,"area":null},{"id":"2401.02739","title":"Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors","created":"2024-01-05","cited_by_count":2,"area":"diffusion"},{"id":"2401.03341","title":"Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection","created":"2024-01-07","cited_by_count":2,"area":null},{"id":"2405.15268","title":"ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks","created":"2024-05-24","cited_by_count":2,"area":null},{"id":"2504.13476","title":"Variational Autoencoder Framework for Hyperspectral Retrievals (Hyper-VAE) of Phytoplankton Absorption and Chlorophyll a in Coastal Waters for NASA's EMIT and PACE Missions","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2506.13658","title":"Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2603.29634","title":"MacTok: Robust Continuous Tokenization for Image Generation","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2101.09979","title":"A Unified Joint Maximum Mean Discrepancy for Domain Adaptation","created":"2021-01-25","cited_by_count":1,"area":null},{"id":"2106.10471","title":"Neural Network Classifier as Mutual Information Evaluator","created":"2021-06-19","cited_by_count":1,"area":null},{"id":"2107.13625","title":"Adaptation and Generalization for Unknown Sensitive Factors of Variations","created":"2021-07-28","cited_by_count":1,"area":null},{"id":"2205.13640","title":"Spatio-temporally separable non-linear latent factor learning: an application to somatomotor cortex fMRI data","created":"2022-05-26","cited_by_count":1,"area":null},{"id":"2206.09891","title":"Latent Variable Modelling Using Variational Autoencoders: A survey","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2210.14981","title":"Fast and Efficient Scene Categorization for Autonomous Driving using VAEs","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2211.07954","title":"An Overview on Controllable Text Generation via Variational Auto-Encoders","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2302.11269","title":"Learning from Multiple Sources for Data-to-Text and Text-to-Data","created":"2023-02-22","cited_by_count":1,"area":null},{"id":"2407.21195","title":"Diffusion-Based Generation of Neural Activity from Disentangled Latent Codes","created":"2024-07-30","cited_by_count":1,"area":"diffusion"},{"id":"2410.08826","title":"Towards virtual painting recolouring using Vision Transformer on X-Ray Fluorescence datacubes","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2411.01978","title":"Understanding Variational Autoencoders with Intrinsic Dimension and Information Imbalance","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2506.00136","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","created":"2025-05-30","cited_by_count":1,"area":"diffusion"},{"id":"2509.10367","title":"A Discrepancy-Based Perspective on Dataset Condensation","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.21511","title":"Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.14655","title":"Galaxy Morphology Classification with Counterfactual Explanation","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2607.00461","title":"Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2102.12289","title":"Automatic Feature Extraction for Heartbeat Anomaly Detection","created":"2021-02-24","cited_by_count":0,"area":null},{"id":"2111.10346","title":"Global and Local Alignment Networks for Unpaired Image-to-Image Translation","created":"2021-11-19","cited_by_count":0,"area":null}],"next_cursor":"100"}