{"total":105,"rows":[{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"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":"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":"2204.00673","title":"Learnable latent embeddings for joint behavioral and neural analysis","created":"2022-04-01","cited_by_count":117,"area":null},{"id":"2110.14739","title":"Generalized Shape Metrics on Neural Representations","created":"2021-10-27","cited_by_count":112,"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":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104,"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":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86,"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":"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":"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":"2407.00143","title":"InfoNCE: Identifying the Gap Between Theory and Practice","created":"2024-06-28","cited_by_count":40,"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":"2402.14167","title":"T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching","created":"2024-02-21","cited_by_count":33,"area":"diffusion"},{"id":"2302.00993","title":"Unpaired Multi-Domain Causal Representation Learning","created":"2023-02-02","cited_by_count":32,"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":"2605.26379","title":"When Does LeJEPA Learn a World Model?","created":"2026-05-25","cited_by_count":30,"area":"wm"},{"id":"2402.04875","title":"On Provable Length and Compositional Generalization","created":"2024-02-07","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":"2310.05264","title":"The Emergence of Reproducibility and Generalizability in Diffusion Models","created":"2023-10-08","cited_by_count":21,"area":"diffusion"},{"id":"2311.02695","title":"Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions","created":"2023-11-05","cited_by_count":18,"area":null},{"id":"2602.24012","title":"InfoNCE Induces Gaussian Distribution","created":"2026-02-27","cited_by_count":16,"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":"2204.04606","title":"Towards efficient representation identification in supervised learning","created":"2022-04-10","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":"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":"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":"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":"2406.13371","title":"Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2411.14633","title":"Evaluating Representational Similarity Measures from the Lens of Functional Correspondence","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2506.17093","title":"Identifiability of Deep Polynomial Neural Networks","created":"2025-06-20","cited_by_count":12,"area":null},{"id":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","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":"2410.03006","title":"Formation of Representations in Neural Networks","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2506.07883","title":"Diffusion Counterfactual Generation with Semantic Abduction","created":"2025-06-09","cited_by_count":10,"area":"diffusion"},{"id":"2410.14673","title":"Self-supervised contrastive learning performs non-linear system identification","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2409.07594","title":"Automated Discovery of Pairwise Interactions from Unstructured Data","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2302.07778","title":"Measuring the Instability of Fine-Tuning","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2503.05283","title":"Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2506.13831","title":"Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation","created":"2025-06-16","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":"2603.28744","title":"Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation","created":"2026-03-30","cited_by_count":6,"area":"mechinterp"},{"id":"2305.11957","title":"Towards understanding neural collapse in supervised contrastive learning with the information bottleneck method","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2312.03580","title":"Invariance & Causal Representation Learning: Prospects and Limitations","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2109.15062","title":"Towards Principled Causal Effect Estimation by Deep Identifiable Models","created":"2021-09-30","cited_by_count":4,"area":null},{"id":"2307.08913","title":"Towards the Sparseness of Projection Head in Self-Supervised Learning","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2407.11249","title":"Disentangling Representations through Multi-task Learning","created":"2024-07-15","cited_by_count":4,"area":"wm"},{"id":"2506.01599","title":"Connecting Neural Models Latent Geometries with Relative Geodesic Representations","created":"2025-06-02","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":"2603.18908","title":"Ventriloquist LLMs: Linear Alignment of Late-Stage Representations","created":"2026-03-19","cited_by_count":4,"area":null},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2605.03517","title":"Understanding Self-Supervised Learning via Latent Distribution Matching","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2106.07822","title":"Canonical Face Embeddings","created":"2021-06-15","cited_by_count":3,"area":null},{"id":"2211.10558","title":"Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds","created":"2022-11-19","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":"2405.15289","title":"Learning Invariant Causal Mechanism from Vision-Language Models","created":"2024-05-24","cited_by_count":3,"area":"mllm"},{"id":"2412.00761","title":"Learning to Forget using Hypernetworks","created":"2024-12-01","cited_by_count":3,"area":"safety"},{"id":"2505.12868","title":"Causality-Inspired Robustness for Nonlinear Models via Representation Learning","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","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":"2405.20482","title":"Sparsity regularization via tree-structured environments for disentangled representations","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2502.12977","title":"Time-series attribution maps with regularized contrastive learning","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2510.21706","title":"Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2606.01092","title":"A Fiber Criterion for Representation Identifiability in Supervised Learning","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2306.14861","title":"Leveraging Task Structures for Improved Identifiability in Neural Network Representations","created":"2023-06-26","cited_by_count":1,"area":null},{"id":"2307.11332","title":"Beyond Convergence: Identifiability of Machine Learning and Deep Learning Models","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2402.18718","title":"Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2406.14183","title":"Latent Functional Maps: a spectral framework for representation alignment","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.17308","title":"Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2602.02726","title":"Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery","created":"2026-02-02","cited_by_count":1,"area":"mechinterp"},{"id":"2603.29488","title":"What Cosine Similarity of Label Representations Can and Cannot Tell us","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.24936","title":"A Unifying Framework for Unsupervised Concept Extraction","created":"2026-04-27","cited_by_count":1,"area":"mechinterp"},{"id":"2605.04115","title":"Learning reveals invisible structure in low-rank RNNs","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2608.10566","title":"Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.21656","title":"Beyond Gaussian Worlds: Latent Geometry Matters for JEPAs","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2609.38998","title":"Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2111.02732","title":"When Neural Networks Using Different Sensors Create Similar Features","created":"2021-11-04","cited_by_count":0,"area":null},{"id":"2406.04916","title":"Combinatorial Complex Score-based Diffusion Modelling through Stochastic Differential Equations","created":"2024-06-07","cited_by_count":0,"area":"diffusion"},{"id":"2502.01803","title":"Discovering Chunks in Neural Embeddings for Interpretability","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2503.11964","title":"Entropy-regularized Gradient Estimators for Approximate Bayesian Inference","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2506.18011","title":"Probing the Embedding Space of Transformers via Minimal Token Perturbations","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2601.11618","title":"Architecture Before the Formula: Training-Dependent Computational Semantics in Transformers","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2601.20420","title":"Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs","created":"2026-01-28","cited_by_count":0,"area":"mechinterp"},{"id":"2602.15438","title":"Logit Distance Bounds Representational Similarity","created":"2026-02-17","cited_by_count":0,"area":"distill"},{"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":"2605.22532","title":"Relational Linear Properties in Language Models: An Empirical Investigation","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.25620","title":"Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations","created":"2026-05-25","cited_by_count":0,"area":"wm"},{"id":"2605.31438","title":"Flow map learning in nonlinear vector autoregressive models: influence of the feature-library structure on the training error","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.18305","title":"The Information Shadow: Measuring Structural Limits on What Language Models Can Learn","created":"2026-07-17","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":"2608.06516","title":"CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.27020","title":"Representation Measurements Under Function-Preserving Reparameterizations","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":"100"}