{"total":122,"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":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160,"area":null},{"id":"2209.11924","title":"Interventional Causal Representation Learning","created":"2022-09-24","cited_by_count":142,"area":null},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133,"area":null},{"id":"2204.00673","title":"Learnable latent embeddings for joint behavioral and neural analysis","created":"2022-04-01","cited_by_count":117,"area":null},{"id":"2306.00542","title":"Nonparametric Identifiability of Causal Representations from Unknown Interventions","created":"2023-06-01","cited_by_count":106,"area":null},{"id":"2110.05428","title":"Learning Temporally Causal Latent Processes from General Temporal Data","created":"2021-10-11","cited_by_count":98,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2311.04056","title":"Multi-View Causal Representation Learning with Partial Observability","created":"2023-11-07","cited_by_count":74,"area":null},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2206.10044","title":"Identifiability of deep generative models without auxiliary information","created":"2022-06-20","cited_by_count":70,"area":null},{"id":"2206.01101","title":"Weakly Supervised Representation Learning with Sparse Perturbations","created":"2022-06-02","cited_by_count":65,"area":null},{"id":"2106.09620","title":"Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA","created":"2021-06-17","cited_by_count":64,"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":"2210.13647","title":"Temporally Disentangled Representation Learning","created":"2022-10-24","cited_by_count":61,"area":null},{"id":"2303.09166","title":"Identifiability Results for Multimodal Contrastive Learning","created":"2023-03-16","cited_by_count":61,"area":null},{"id":"2302.02672","title":"Identifiability of latent-variable and structural-equation models: from linear to nonlinear","created":"2023-02-06","cited_by_count":58,"area":null},{"id":"2307.02598","title":"Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation","created":"2023-07-05","cited_by_count":58,"area":null},{"id":"2206.06169","title":"Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems","created":"2022-06-13","cited_by_count":51,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"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":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45,"area":null},{"id":"2211.14666","title":"Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning","created":"2022-11-26","cited_by_count":44,"area":null},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","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":"2306.09643","title":"BISCUIT: Causal Representation Learning from Binary Interactions","created":"2023-06-16","cited_by_count":38,"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":"2310.04723","title":"Subspace Identification for Multi-Source Domain Adaptation","created":"2023-10-07","cited_by_count":37,"area":null},{"id":"2507.00583","title":"AI-Generated Video Detection via Perceptual Straightening","created":"2025-07-01","cited_by_count":34,"area":null},{"id":"2206.00801","title":"Indeterminacy in Generative Models: Characterization and Strong Identifiability","created":"2022-06-02","cited_by_count":33,"area":null},{"id":"2310.15709","title":"Causal Representation Learning Made Identifiable by Grouping of Observational Variables","created":"2023-10-24","cited_by_count":32,"area":null},{"id":"2409.02772","title":"Unifying Causal Representation Learning with the Invariance Principle","created":"2024-09-04","cited_by_count":31,"area":null},{"id":"2410.21869","title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","created":"2024-10-29","cited_by_count":31,"area":null},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2106.15610","title":"An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild","created":"2021-06-29","cited_by_count":30,"area":null},{"id":"2110.15796","title":"Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning","created":"2021-10-29","cited_by_count":30,"area":null},{"id":"2605.26379","title":"When Does LeJEPA Learn a World Model?","created":"2026-05-25","cited_by_count":30,"area":"wm"},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2206.02416","title":"Embrace the Gap: VAEs Perform Independent Mechanism Analysis","created":"2022-06-06","cited_by_count":28,"area":null},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2306.06561","title":"Learning World Models with Identifiable Factorization","created":"2023-06-11","cited_by_count":23,"area":"wm"},{"id":"2401.14535","title":"CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process","created":"2024-01-25","cited_by_count":23,"area":null},{"id":"2405.13888","title":"Marrying Causal Representation Learning with Dynamical Systems for Science","created":"2024-05-22","cited_by_count":23,"area":null},{"id":"2301.05169","title":"Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning","created":"2023-01-12","cited_by_count":22,"area":null},{"id":"2310.18615","title":"Temporally Disentangled Representation Learning under Unknown Nonstationarity","created":"2023-10-28","cited_by_count":22,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20,"area":null},{"id":"2511.05541","title":"Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability","created":"2025-10-30","cited_by_count":18,"area":"mechinterp"},{"id":"2410.11767","title":"Analyzing (In)Abilities of SAEs via Formal Languages","created":"2024-10-15","cited_by_count":17,"area":"mechinterp"},{"id":"2205.12755","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","created":"2022-05-25","cited_by_count":16,"area":null},{"id":"2405.15325","title":"On the Identification of Temporally Causal Representation with Instantaneous Dependence","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2406.14302","title":"Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning","created":"2024-06-20","cited_by_count":16,"area":null},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2210.05972","title":"Unsupervised Learning of Equivariant Structure from Sequences","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2306.06510","title":"Partial Identifiability for Domain Adaptation","created":"2023-06-10","cited_by_count":14,"area":null},{"id":"2202.04828","title":"Learning Latent Causal Dynamics","created":"2022-02-10","cited_by_count":13,"area":null},{"id":"2311.04774","title":"Towards a Unified Framework of Contrastive Learning for Disentangled Representations","created":"2023-11-08","cited_by_count":13,"area":null},{"id":"2409.03142","title":"Causal Temporal Representation Learning with Nonstationary Sparse Transition","created":"2024-09-05","cited_by_count":13,"area":null},{"id":"2102.05185","title":"Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement","created":"2021-02-09","cited_by_count":12,"area":null},{"id":"2206.04756","title":"An Empirical Study on Disentanglement of Negative-free Contrastive Learning","created":"2022-06-09","cited_by_count":12,"area":null},{"id":"2406.13371","title":"Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2406.19298","title":"Compositional Image Decomposition with Diffusion Models","created":"2024-06-27","cited_by_count":12,"area":"diffusion"},{"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":"2309.13167","title":"Flow Factorized Representation Learning","created":"2023-09-22","cited_by_count":11,"area":null},{"id":"2301.12351","title":"Emerging Synergies in Causality and Deep Generative Models: A Survey","created":"2023-01-29","cited_by_count":10,"area":null},{"id":"2209.07326","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","created":"2022-09-15","cited_by_count":9,"area":null},{"id":"2305.15925","title":"On the Identifiability of Switching Dynamical Systems","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2310.11431","title":"Identifying Interpretable Visual Features in Artificial and Biological Neural Systems","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2311.18048","title":"An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis","created":"2023-11-29","cited_by_count":9,"area":null},{"id":"2504.13101","title":"Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2510.18310","title":"Towards Identifiability of Hierarchical Temporal Causal Representation Learning","created":"2025-10-21","cited_by_count":9,"area":null},{"id":"2112.14754","title":"Disentanglement and Generalization Under Correlation Shifts","created":"2021-12-29","cited_by_count":8,"area":null},{"id":"2501.12500","title":"Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis","created":"2025-01-21","cited_by_count":7,"area":null},{"id":"2505.12745","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2102.06822","title":"Demystifying Inductive Biases for $\\beta$-VAE Based Architectures","created":"2021-02-12","cited_by_count":5,"area":null},{"id":"2305.08164","title":"Latent Processes Identification From Multi-View Time Series","created":"2023-05-14","cited_by_count":5,"area":null},{"id":"2410.07013","title":"Causal Representation Learning in Temporal Data via Single-Parent Decoding","created":"2024-10-09","cited_by_count":5,"area":null},{"id":"2302.10890","title":"Learning Interpretable Low-dimensional Representation via Physical Symmetry","created":"2023-02-05","cited_by_count":4,"area":null},{"id":"2311.16849","title":"Identifiable Feature Learning for Spatial Data with Nonlinear ICA","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2403.03698","title":"Towards Controllable Time Series Generation","created":"2024-03-06","cited_by_count":4,"area":null},{"id":"2410.06232","title":"Range, not Independence, Drives Modularity in Biologically Inspired Representations","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2410.22472","title":"Learning Identifiable Factorized Causal Representations of Cellular Responses","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2503.00639","title":"Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2505.08361","title":"Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning","created":"2025-05-13","cited_by_count":4,"area":"deeprl"},{"id":"2510.17040","title":"Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability","created":"2025-10-19","cited_by_count":4,"area":null},{"id":"2207.03866","title":"Pixel-level Correspondence for Self-Supervised Learning from Video","created":"2022-07-08","cited_by_count":3,"area":null},{"id":"2210.03155","title":"Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles","created":"2022-10-06","cited_by_count":3,"area":null},{"id":"2306.16334","title":"On the Identifiability of Quantized Factors","created":"2023-06-28","cited_by_count":3,"area":null},{"id":"2307.00558","title":"Conditionally Invariant Representation Learning for Disentangling Cellular Heterogeneity","created":"2023-07-02","cited_by_count":3,"area":null},{"id":"2509.03738","title":"Mechanistic Interpretability with Sparse Autoencoder Neural Operators","created":"2025-09-03","cited_by_count":3,"area":"mechinterp"},{"id":"2509.22196","title":"Mechanistic Independence: A Principle for Identifiable Disentangled Representations","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2510.02484","title":"From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning","created":"2025-10-02","cited_by_count":3,"area":"deeprl"},{"id":"2510.26782","title":"Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models","created":"2025-10-30","cited_by_count":3,"area":"wm"},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2209.14745","title":"A Multiagent Framework for the Asynchronous and Collaborative Extension of Multitask ML Systems","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2304.02335","title":"Correcting Flaws in Common Disentanglement Metrics","created":"2023-04-05","cited_by_count":2,"area":null},{"id":"2405.20482","title":"Sparsity regularization via tree-structured environments for disentangled representations","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2410.05564","title":"Unsupervised Representation Learning from Sparse Transformation Analysis","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2508.09721","title":"Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA","created":"2025-08-13","cited_by_count":2,"area":null}],"next_cursor":"100"}