{"total":86,"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":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"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":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97,"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":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2206.01101","title":"Weakly Supervised Representation Learning with Sparse Perturbations","created":"2022-06-02","cited_by_count":65,"area":null},{"id":"2303.09166","title":"Identifiability Results for Multimodal Contrastive Learning","created":"2023-03-16","cited_by_count":61,"area":null},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"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":"2305.17225","title":"Causal Component Analysis","created":"2023-05-26","cited_by_count":56,"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":"2102.12353","title":"Nonlinear Invariant Risk Minimization: A Causal Approach","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41,"area":null},{"id":"2407.00143","title":"InfoNCE: Identifying the Gap Between Theory and Practice","created":"2024-06-28","cited_by_count":40,"area":null},{"id":"2110.04121","title":"On the Limitations of Multimodal VAEs","created":"2021-10-08","cited_by_count":38,"area":null},{"id":"2106.07115","title":"Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2110.12091","title":"Contrastively Disentangled Sequential Variational Autoencoder","created":"2021-10-22","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":"2206.02416","title":"Embrace the Gap: VAEs Perform Independent Mechanism Analysis","created":"2022-06-06","cited_by_count":28,"area":null},{"id":"2310.02854","title":"Multi-Domain Causal Representation Learning via Weak Distributional Invariances","created":"2023-10-04","cited_by_count":23,"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":"2106.05238","title":"I Don't Need u: Identifiable Non-Linear ICA Without Side Information","created":"2021-06-09","cited_by_count":21,"area":null},{"id":"2311.08815","title":"Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations","created":"2023-11-15","cited_by_count":17,"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":"2306.01424","title":"Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14,"area":null},{"id":"2507.22264","title":"SmartCLIP: Modular Vision-language Alignment with Identification Guarantees","created":"2025-07-29","cited_by_count":14,"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":"2402.15309","title":"Counterfactual Generation with Identifiability Guarantees","created":"2024-02-23","cited_by_count":13,"area":null},{"id":"2411.06518","title":"Causal Representation Learning from Multimodal Biomedical Observations","created":"2024-11-10","cited_by_count":13,"area":null},{"id":"2502.11245","title":"Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens","created":"2025-02-16","cited_by_count":13,"area":null},{"id":"2402.06223","title":"Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2204.00492","title":"Provable concept learning for interpretable predictions using variational autoencoders","created":"2022-04-01","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":"2106.09070","title":"Identifiability-Guaranteed Simplex-Structured Post-Nonlinear Mixture Learning via Autoencoder","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2206.06593","title":"On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis","created":"2022-06-14","cited_by_count":7,"area":null},{"id":"2210.02083","title":"Multi-View Independent Component Analysis with Shared and Individual Sources","created":"2022-10-05","cited_by_count":7,"area":null},{"id":"2312.13438","title":"Independent Mechanism Analysis and the Manifold Hypothesis","created":"2023-12-20","cited_by_count":7,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2404.01595","title":"Propensity Score Alignment of Unpaired Multimodal Data","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2207.06137","title":"Probing the Robustness of Independent Mechanism Analysis for Representation Learning","created":"2022-07-13","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":"2502.20099","title":"Sanity Checking Causal Representation Learning on a Simple Real-World System","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2101.02083","title":"Representation learning for maximization of MI, nonlinear ICA and nonlinear subspaces with robust density ratio estimation","created":"2021-01-06","cited_by_count":4,"area":null},{"id":"2405.16083","title":"From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals","created":"2024-05-25","cited_by_count":4,"area":null},{"id":"2506.03784","title":"When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2507.14748","title":"Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning","created":"2025-07-19","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":"2110.05887","title":"Discovery of Single Independent Latent Variable","created":"2021-10-12","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":"2409.19422","title":"Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures","created":"2024-09-28","cited_by_count":3,"area":null},{"id":"2502.12603","title":"Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2502.13757","title":"Identifying Metric Structures of Deep Latent Variable Models","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2509.22196","title":"Mechanistic Independence: A Principle for Identifiable Disentangled Representations","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2202.06844","title":"On Pitfalls of Identifiability in Unsupervised Learning. A Note on: \"Desiderata for Representation Learning: A Causal Perspective\"","created":"2022-02-14","cited_by_count":2,"area":null},{"id":"2210.07532","title":"Provable Subspace Identification Under Post-Nonlinear Mixtures","created":"2022-10-14","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":"2411.03755","title":"Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent Dimensions","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2508.03102","title":"Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.18281","title":"Online Time Series Forecasting with Theoretical Guarantees","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2502.16637","title":"Time Series Domain Adaptation via Latent Invariant Causal Mechanism","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2503.10834","title":"On the Identifiability of Causal Abstractions","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2505.07180","title":"Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2602.24275","title":"Hierarchical Action Learning for Weakly-Supervised Action Segmentation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2405.19760","title":"Identifiability of a statistical model with two latent vectors: Importance of the dimensionality relation and application to graph embedding","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2410.18539","title":"Interpretable Representation Learning from Videos using Nonlinear Priors","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2506.07806","title":"Identifiable Object Representations under Spatial Ambiguities","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2507.16467","title":"Estimating Treatment Effects with Independent Component Analysis","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2510.13583","title":"On the Identifiability of Causal Graphs with the Invariance Principle","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2602.15438","title":"Logit Distance Bounds Representational Similarity","created":"2026-02-17","cited_by_count":0,"area":"distill"},{"id":"2602.23785","title":"Provable Subspace Identification of Nonlinear Multi-view CCA","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.13589","title":"Causal Learning with the Invariance Principle","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.00858","title":"MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.23182","title":"Beyond ICA: Identifiability by Symmetry Breaking","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.02015","title":"How Output Format Confounds Data Quality and Capability in Instruction Tuning","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.11959","title":"Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.37789","title":"Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}