{"total":100,"rows":[{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312,"area":null},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221,"area":null},{"id":"2103.02582","title":"D'ya like DAGs? A Survey on Structure Learning and Causal Discovery","created":"2021-03-03","cited_by_count":211,"area":null},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77,"area":"diffusion"},{"id":"2311.04056","title":"Multi-View Causal Representation Learning with Partial Observability","created":"2023-11-07","cited_by_count":74,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"area":null},{"id":"2206.01101","title":"Weakly Supervised Representation Learning with Sparse Perturbations","created":"2022-06-02","cited_by_count":65,"area":null},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61,"area":null},{"id":"2210.00482","title":"Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language","created":"2022-10-02","cited_by_count":42,"area":null},{"id":"2109.04173","title":"Relating Graph Neural Networks to Structural Causal Models","created":"2021-09-09","cited_by_count":41,"area":null},{"id":"2305.18378","title":"Disentanglement via Latent Quantization","created":"2023-05-28","cited_by_count":40,"area":null},{"id":"2210.07347","title":"Disentanglement of Correlated Factors via Hausdorff Factorized Support","created":"2022-10-13","cited_by_count":37,"area":null},{"id":"2102.10543","title":"Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View","created":"2021-02-21","cited_by_count":34,"area":null},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2301.13721","title":"DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models","created":"2023-01-31","cited_by_count":30,"area":"diffusion"},{"id":"2303.13325","title":"DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices","created":"2023-03-23","cited_by_count":28,"area":null},{"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":"2310.18555","title":"Group Robust Classification Without Any Group Information","created":"2023-10-28","cited_by_count":25,"area":null},{"id":"2210.00364","title":"DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability","created":"2022-10-01","cited_by_count":23,"area":null},{"id":"2112.05746","title":"On Causally Disentangled Representations","created":"2021-12-10","cited_by_count":22,"area":null},{"id":"2310.11011","title":"From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling","created":"2023-10-17","cited_by_count":22,"area":null},{"id":"2106.02923","title":"Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization","created":"2021-06-05","cited_by_count":17,"area":null},{"id":"2109.00545","title":"Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks","created":"2021-09-01","cited_by_count":16,"area":null},{"id":"2210.13604","title":"The Robustness Limits of SoTA Vision Models to Natural Variation","created":"2022-10-24","cited_by_count":15,"area":null},{"id":"2310.18777","title":"Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings","created":"2023-10-28","cited_by_count":15,"area":null},{"id":"2205.10093","title":"Visual Concepts Tokenization","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2206.13872","title":"When are Post-hoc Conceptual Explanations Identifiable?","created":"2022-06-28","cited_by_count":14,"area":null},{"id":"2207.12258","title":"Equivariance and Invariance Inductive Bias for Learning from Insufficient Data","created":"2022-07-25","cited_by_count":14,"area":null},{"id":"2102.06204","title":"Disentangled Representations from Non-Disentangled Models","created":"2021-02-11","cited_by_count":13,"area":null},{"id":"2404.10282","title":"Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning","created":"2024-04-16","cited_by_count":13,"area":null},{"id":"2506.04870","title":"Aligning Multimodal Representations through an Information Bottleneck","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2507.07102","title":"Does Data Scaling Lead to Visual Compositional Generalization?","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2107.05686","title":"The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents","created":"2021-07-12","cited_by_count":12,"area":null},{"id":"2111.14825","title":"Latent Transformations via NeuralODEs for GAN-based Image Editing","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2204.02283","title":"Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2112.14278","title":"Beta-VAE Reproducibility: Challenges and Extensions","created":"2021-12-28","cited_by_count":10,"area":null},{"id":"2504.10143","title":"On the Value of Cross-Modal Misalignment in Multimodal Representation Learning","created":"2025-04-14","cited_by_count":10,"area":null},{"id":"2204.00492","title":"Provable concept learning for interpretable predictions using variational autoencoders","created":"2022-04-01","cited_by_count":9,"area":null},{"id":"2402.02346","title":"Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback","created":"2024-02-04","cited_by_count":9,"area":"diffusion"},{"id":"2112.14754","title":"Disentanglement and Generalization Under Correlation Shifts","created":"2021-12-29","cited_by_count":8,"area":null},{"id":"2303.01384","title":"DAVA: Disentangling Adversarial Variational Autoencoder","created":"2023-03-02","cited_by_count":8,"area":null},{"id":"2506.04877","title":"There Was Never a Bottleneck in Concept Bottleneck Models","created":"2025-06-05","cited_by_count":8,"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":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2211.16499","title":"Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing","created":"2022-11-29","cited_by_count":6,"area":null},{"id":"2305.18063","title":"Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2603.11970","title":"Statistical and structural identifiability in representation learning","created":"2026-03-12","cited_by_count":6,"area":null},{"id":"2203.01629","title":"Learning Group Importance using the Differentiable Hypergeometric Distribution","created":"2022-03-03","cited_by_count":5,"area":null},{"id":"2403.04701","title":"ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2308.12696","title":"Disentanglement Learning via Topology","created":"2023-08-24","cited_by_count":4,"area":null},{"id":"2408.05599","title":"Sequential Representation Learning via Static-Dynamic Conditional Disentanglement","created":"2024-08-10","cited_by_count":4,"area":null},{"id":"2408.06638","title":"COD: Learning Conditional Invariant Representation for Domain Adaptation Regression","created":"2024-08-13","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":"2411.00588","title":"$\\alpha$-TCVAE: On the relationship between Disentanglement and Diversity","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2105.03164","title":"Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification","created":"2021-05-07","cited_by_count":3,"area":null},{"id":"2209.09115","title":"Compositional Law Parsing with Latent Random Functions","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2209.10623","title":"SW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping","created":"2022-09-21","cited_by_count":3,"area":null},{"id":"2212.12570","title":"Pearl Causal Hierarchy on Image Data: Intricacies & Challenges","created":"2022-12-23","cited_by_count":3,"area":null},{"id":"2305.16841","title":"Differentiable Random Partition Models","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2312.16731","title":"Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2401.13721","title":"Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression","created":"2024-01-24","cited_by_count":3,"area":null},{"id":"2412.12242","title":"OmniPrism: Learning Disentangled Visual Concept for Image Generation","created":"2024-12-16","cited_by_count":3,"area":"diffusion"},{"id":"2507.06613","title":"Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2305.11512","title":"Enriching Disentanglement: From Logical Definitions to Quantitative Metrics","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2503.09679","title":"DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2507.02619","title":"L-VAE: Variational Auto-Encoder with Learnable Beta for Disentangled Representation","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2602.05214","title":"Disentangled Representation Learning via Flow Matching","created":"2026-02-05","cited_by_count":2,"area":"diffusion"},{"id":"2109.13156","title":"DAReN: A Collaborative Approach Towards Reasoning And Disentangling","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2307.11079","title":"3D-IDS: Doubly Disentangled Dynamic Intrusion Detection","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2307.14151","title":"Learning Disentangled Discrete Representations","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2409.14851","title":"Disentanglement with Factor Quantized Variational Autoencoders","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2409.18017","title":"Transferring disentangled representations: bridging the gap between synthetic and real images","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2501.19182","title":"A Compressive-Expressive Communication Framework for Compositional Representations","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2510.21402","title":"Disentangled Representation Learning via Modular Compositional Bias","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2106.05842","title":"Causality in Neural Networks -- An Extended Abstract","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2110.04572","title":"X-model: Improving Data Efficiency in Deep Learning with A Minimax Model","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2204.00386","title":"Autoencoder for Synthetic to Real Generalization: From Simple to More Complex Scenes","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2209.06827","title":"Weakly Supervised Invariant Representation Learning Via Disentangling Known and Unknown Nuisance Factors","created":"2022-09-15","cited_by_count":0,"area":null},{"id":"2303.00128","title":"Representation Disentaglement via Regularization by Causal Identification","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2305.09092","title":"ProtoVAE: Prototypical Networks for Unsupervised Disentanglement","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2305.18273","title":"Pix2Repair: Implicit Shape Restoration from Images","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2310.09278","title":"Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning","created":"2023-10-13","cited_by_count":0,"area":null},{"id":"2408.07016","title":"Rethinking Disentanglement under Dependent Factors of Variation","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2408.17363","title":"Look, Learn and Leverage (L$^3$): Mitigating Visual-Domain Shift and Discovering Intrinsic Relations via Symbolic Alignment","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2502.05037","title":"Leveraging a Simulator for Learning Causal Representations from Post-Treatment Covariates for CATE","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2510.16039","title":"Vector Quantization in the Brain: Grid-like Codes in World Models","created":"2025-10-16","cited_by_count":0,"area":"wm"},{"id":"2601.21688","title":"XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.09277","title":"Mutual Information Collapse Explains Disentanglement Failure in $\\beta$-VAEs","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.24278","title":"Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.11790","title":"Disentangled Representation Learning through Unsupervised Symmetry Group Discovery","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.17568","title":"Diverse Dictionary Learning","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.20549","title":"MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.09725","title":"Disentanglement with Holographic Reduced Representations","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.20526","title":"DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.05325","title":"CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.34078","title":"WhiteCon: Semi-Supervised Domain Adaptation Regression Through Whitening Transform and Dual Consistency","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}