{"total":247,"rows":[{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"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":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2106.00750","title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","created":"2021-06-01","cited_by_count":224,"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":"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":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97,"area":null},{"id":"2202.04770","title":"Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion","created":"2022-02-08","cited_by_count":96,"area":null},{"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":"2206.07751","title":"On the Identifiability of Nonlinear ICA: Sparsity and Beyond","created":"2022-06-15","cited_by_count":85,"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":"2302.02515","title":"Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey","created":"2023-02-06","cited_by_count":68,"area":null},{"id":"2402.05052","title":"Causal Representation Learning from Multiple Distributions: A General Setting","created":"2024-02-07","cited_by_count":68,"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":"2305.17225","title":"Causal Component Analysis","created":"2023-05-26","cited_by_count":56,"area":null},{"id":"2203.09270","title":"Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series","created":"2022-03-17","cited_by_count":54,"area":null},{"id":"2208.06406","title":"Function Classes for Identifiable Nonlinear Independent Component Analysis","created":"2022-08-12","cited_by_count":53,"area":null},{"id":"2303.11911","title":"Time Series Contrastive Learning with Information-Aware Augmentations","created":"2023-03-21","cited_by_count":52,"area":null},{"id":"2305.10716","title":"A Survey on Time-Series Pre-Trained Models","created":"2023-05-18","cited_by_count":52,"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":"2205.09928","title":"Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer","created":"2022-05-20","cited_by_count":47,"area":null},{"id":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46,"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":"2303.10112","title":"Causal Discovery from Temporal Data: An Overview and New Perspectives","created":"2023-03-17","cited_by_count":43,"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":"2306.09643","title":"BISCUIT: Causal Representation Learning from Binary Interactions","created":"2023-06-16","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":"2310.04723","title":"Subspace Identification for Multi-Source Domain Adaptation","created":"2023-10-07","cited_by_count":37,"area":null},{"id":"2109.08908","title":"Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals","created":"2021-09-18","cited_by_count":35,"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":"2110.12091","title":"Contrastively Disentangled Sequential Variational Autoencoder","created":"2021-10-22","cited_by_count":34,"area":null},{"id":"2208.14153","title":"Identifying Weight-Variant Latent Causal Models","created":"2022-08-30","cited_by_count":34,"area":null},{"id":"2211.03553","title":"Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling","created":"2022-11-07","cited_by_count":34,"area":null},{"id":"2306.02899","title":"Learning nonparametric latent causal graphs with unknown interventions","created":"2023-06-05","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":"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":"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":"2106.09913","title":"Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments","created":"2021-06-18","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":"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":"2206.02416","title":"Embrace the Gap: VAEs Perform Independent Mechanism Analysis","created":"2022-06-06","cited_by_count":28,"area":null},{"id":"2305.14133","title":"Conditional Mutual Information for Disentangled Representations in Reinforcement Learning","created":"2023-05-23","cited_by_count":27,"area":null},{"id":"2202.14019","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","created":"2022-02-28","cited_by_count":25,"area":null},{"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":"2310.18615","title":"Temporally Disentangled Representation Learning under Unknown Nonstationarity","created":"2023-10-28","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":"2310.04295","title":"Identifying Representations for Intervention Extrapolation","created":"2023-10-06","cited_by_count":21,"area":null},{"id":"2310.19054","title":"Object-centric architectures enable efficient causal representation learning","created":"2023-10-29","cited_by_count":21,"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":"2103.01638","title":"Learning disentangled representations via product manifold projection","created":"2021-03-02","cited_by_count":20,"area":null},{"id":"2207.05480","title":"Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning","created":"2022-07-12","cited_by_count":19,"area":null},{"id":"2203.11370","title":"Language modeling via stochastic processes","created":"2022-03-21","cited_by_count":18,"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":"2202.02262","title":"Decoupling Local and Global Representations of Time Series","created":"2022-02-04","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":"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":"2602.24012","title":"InfoNCE Induces Gaussian Distribution","created":"2026-02-27","cited_by_count":16,"area":null},{"id":"2110.11271","title":"Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation","created":"2021-10-21","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":"2308.10603","title":"A step towards understanding why classification helps regression","created":"2023-08-21","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":"2306.06510","title":"Partial Identifiability for Domain Adaptation","created":"2023-06-10","cited_by_count":14,"area":null},{"id":"2308.01578","title":"Unsupervised Representation Learning for Time Series: A Review","created":"2023-08-03","cited_by_count":14,"area":null},{"id":"2310.18904","title":"Identifiable Contrastive Learning with Automatic Feature Importance Discovery","created":"2023-10-29","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":"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":"2411.06518","title":"Causal Representation Learning from Multimodal Biomedical Observations","created":"2024-11-10","cited_by_count":13,"area":null},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2504.11609","title":"Towards Interpretable Deep Generative Models via Causal Representation Learning","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2110.06257","title":"Causal Discovery from Conditionally Stationary Time Series","created":"2021-10-12","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":"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":"2101.06662","title":"Intact-VAE: Estimating Treatment Effects under Unobserved Confounding","created":"2021-01-17","cited_by_count":10,"area":null},{"id":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10,"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":"2302.09795","title":"Simple Disentanglement of Style and Content in Visual Representations","created":"2023-02-20","cited_by_count":10,"area":null}],"next_cursor":"100"}