{"total":312,"rows":[{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172,"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":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144,"area":null},{"id":"2209.11924","title":"Interventional Causal Representation Learning","created":"2022-09-24","cited_by_count":142,"area":null},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140,"area":null},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133,"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":"2202.14037","title":"Understanding Contrastive Learning Requires Incorporating Inductive Biases","created":"2022-02-28","cited_by_count":96,"area":null},{"id":"2310.09336","title":"Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task","created":"2023-10-13","cited_by_count":93,"area":"diffusion"},{"id":"2306.02235","title":"Learning Linear Causal Representations from Interventions under General Nonlinear Mixing","created":"2023-06-04","cited_by_count":92,"area":null},{"id":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90,"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":"2201.04439","title":"Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases","created":"2022-01-12","cited_by_count":72,"area":null},{"id":"2206.01101","title":"Weakly Supervised Representation Learning with Sparse Perturbations","created":"2022-06-02","cited_by_count":65,"area":null},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64,"area":null},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63,"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":"2302.03693","title":"Concept Algebra for (Score-Based) Text-Controlled Generative Models","created":"2023-02-07","cited_by_count":59,"area":"diffusion"},{"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":"2305.17225","title":"Causal Component Analysis","created":"2023-05-26","cited_by_count":56,"area":null},{"id":"2206.02013","title":"Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis","created":"2022-06-04","cited_by_count":55,"area":null},{"id":"2110.10804","title":"Identifiable Deep Generative Models via Sparse Decoding","created":"2021-10-20","cited_by_count":54,"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":"2306.05415","title":"Causal normalizing flows: from theory to practice","created":"2023-06-08","cited_by_count":51,"area":"lr"},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2301.08230","title":"Score-based Causal Representation Learning with Interventions","created":"2023-01-19","cited_by_count":49,"area":null},{"id":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2205.11506","title":"Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering","created":"2022-05-23","cited_by_count":45,"area":null},{"id":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45,"area":null},{"id":"2201.10000","title":"Neural Manifold Clustering and Embedding","created":"2022-01-24","cited_by_count":44,"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":"2302.10283","title":"Self-supervised learning of Split Invariant Equivariant representations","created":"2023-02-14","cited_by_count":44,"area":null},{"id":"2207.03162","title":"Harnessing Out-Of-Distribution Examples via Augmenting Content and Style","created":"2022-07-07","cited_by_count":43,"area":null},{"id":"2303.10112","title":"Causal Discovery from Temporal Data: An Overview and New Perspectives","created":"2023-03-17","cited_by_count":43,"area":null},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41,"area":null},{"id":"2204.00607","title":"From Statistical to Causal Learning","created":"2022-04-01","cited_by_count":40,"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":"2205.01789","title":"Do More Negative Samples Necessarily Hurt in Contrastive Learning?","created":"2022-05-03","cited_by_count":39,"area":null},{"id":"2306.04898","title":"Understanding Masked Autoencoders via Hierarchical Latent Variable Models","created":"2023-06-08","cited_by_count":39,"area":null},{"id":"2110.04121","title":"On the Limitations of Multimodal VAEs","created":"2021-10-08","cited_by_count":38,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","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":"2302.07920","title":"InfoNCE Loss Provably Learns Cluster-Preserving Representations","created":"2023-02-15","cited_by_count":37,"area":null},{"id":"2306.11078","title":"Beyond Normal: On the Evaluation of Mutual Information Estimators","created":"2023-06-19","cited_by_count":37,"area":null},{"id":"2212.11491","title":"Understanding and Improving the Role of Projection Head in Self-Supervised Learning","created":"2022-12-22","cited_by_count":36,"area":null},{"id":"2403.08335","title":"A Sparsity Principle for Partially Observable Causal Representation Learning","created":"2024-03-13","cited_by_count":35,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2208.14153","title":"Identifying Weight-Variant Latent Causal Models","created":"2022-08-30","cited_by_count":34,"area":null},{"id":"2209.06235","title":"Improving Self-Supervised Learning by Characterizing Idealized Representations","created":"2022-09-13","cited_by_count":34,"area":null},{"id":"2303.01274","title":"Measuring axiomatic soundness of counterfactual image models","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2310.15450","title":"General Identifiability and Achievability for Causal Representation Learning","created":"2023-10-24","cited_by_count":34,"area":null},{"id":"2311.00866","title":"Generalizing Nonlinear ICA Beyond Structural Sparsity","created":"2023-11-01","cited_by_count":34,"area":null},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","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":"2510.20733","title":"Thought Communication in Multiagent Collaboration","created":"2025-10-23","cited_by_count":30,"area":"lr"},{"id":"2605.26379","title":"When Does LeJEPA Learn a World Model?","created":"2026-05-25","cited_by_count":30,"area":"wm"},{"id":"2207.07732","title":"Partial Disentanglement via Mechanism Sparsity","created":"2022-07-15","cited_by_count":29,"area":null},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29,"area":null},{"id":"2202.12230","title":"Sample Efficiency of Data Augmentation Consistency Regularization","created":"2022-02-24","cited_by_count":28,"area":null},{"id":"2306.07916","title":"Identification of Nonlinear Latent Hierarchical Models","created":"2023-06-13","cited_by_count":27,"area":null},{"id":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26,"area":null},{"id":"2110.02501","title":"On the Surrogate Gap between Contrastive and Supervised Losses","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2111.03220","title":"Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices","created":"2021-11-05","cited_by_count":25,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2306.06561","title":"Learning World Models with Identifiable Factorization","created":"2023-06-11","cited_by_count":23,"area":"wm"},{"id":"2310.02854","title":"Multi-Domain Causal Representation Learning via Weak Distributional Invariances","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2310.15580","title":"Identifiable Latent Polynomial Causal Models Through the Lens of Change","created":"2023-10-24","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":"2309.07742","title":"Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning","created":"2023-09-14","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":"2206.09979","title":"Mitigating Data Heterogeneity in Federated Learning with Data Augmentation","created":"2022-06-20","cited_by_count":21,"area":null},{"id":"2301.08164","title":"DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies","created":"2023-01-19","cited_by_count":21,"area":null},{"id":"2307.09933","title":"Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features","created":"2023-07-19","cited_by_count":21,"area":null},{"id":"2205.02049","title":"Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images","created":"2022-05-04","cited_by_count":20,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2403.09683","title":"Counterfactual Image Editing","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"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":"2210.00638","title":"What shapes the loss landscape of self-supervised learning?","created":"2022-10-02","cited_by_count":19,"area":null},{"id":"2207.12067","title":"Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitions","created":"2022-07-25","cited_by_count":18,"area":null},{"id":"2311.02695","title":"Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions","created":"2023-11-05","cited_by_count":18,"area":null},{"id":"2412.01953","title":"The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications","created":"2024-12-02","cited_by_count":18,"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":"2406.00519","title":"Learning Discrete Concepts in Latent Hierarchical Models","created":"2024-06-01","cited_by_count":17,"area":null},{"id":"2406.09294","title":"You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2111.11398","title":"Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks","created":"2021-11-22","cited_by_count":15,"area":null},{"id":"2210.05972","title":"Unsupervised Learning of Equivariant Structure from Sequences","created":"2022-10-12","cited_by_count":15,"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":"2311.12267","title":"Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity","created":"2023-11-21","cited_by_count":15,"area":null},{"id":"2312.00379","title":"Optimal Sample Complexity of Contrastive Learning","created":"2023-12-01","cited_by_count":15,"area":null},{"id":"2204.04606","title":"Towards efficient representation identification in supervised learning","created":"2022-04-10","cited_by_count":14,"area":null},{"id":"2306.01213","title":"Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2306.06510","title":"Partial Identifiability for Domain Adaptation","created":"2023-06-10","cited_by_count":14,"area":null},{"id":"2406.05937","title":"Linear Causal Representation Learning from Unknown Multi-node Interventions","created":"2024-06-09","cited_by_count":14,"area":null}],"next_cursor":"100"}