{"total":296,"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":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2308.07863","title":"StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models","created":"2023-08-15","cited_by_count":155,"area":"diffusion"},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95,"area":null},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80,"area":null},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77,"area":"diffusion"},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"id":"2106.06169","title":"BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data","created":"2021-06-11","cited_by_count":75,"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":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2112.01983","title":"CoNeRF: Controllable Neural Radiance Fields","created":"2021-12-03","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":"2302.03693","title":"Concept Algebra for (Score-Based) Text-Controlled Generative Models","created":"2023-02-07","cited_by_count":59,"area":"diffusion"},{"id":"2204.11371","title":"Learning Symmetric Embeddings for Equivariant World Models","created":"2022-04-24","cited_by_count":54,"area":"wm"},{"id":"2208.06406","title":"Function Classes for Identifiable Nonlinear Independent Component Analysis","created":"2022-08-12","cited_by_count":53,"area":null},{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51,"area":"mechinterp"},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"area":null},{"id":"2408.17052","title":"Can We Leave Deepfake Data Behind in Training Deepfake Detector?","created":"2024-08-30","cited_by_count":49,"area":null},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48,"area":"mllm"},{"id":"2108.06685","title":"Vector-Decomposed Disentanglement for Domain-Invariant Object Detection","created":"2021-08-15","cited_by_count":47,"area":null},{"id":"2110.15255","title":"Self-Supervised Learning Disentangled Group Representation as Feature","created":"2021-10-28","cited_by_count":47,"area":null},{"id":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2102.05109","title":"CDPAM: Contrastive learning for perceptual audio similarity","created":"2021-02-09","cited_by_count":42,"area":null},{"id":"2111.14820","title":"Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective","created":"2021-11-29","cited_by_count":40,"area":null},{"id":"2202.07559","title":"Unsupervised Learning of Group Invariant and Equivariant Representations","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2107.11055","title":"Transporting Causal Mechanisms for Unsupervised Domain Adaptation","created":"2021-07-23","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":"2106.03630","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","created":"2021-06-07","cited_by_count":36,"area":null},{"id":"2401.11430","title":"Exploring Diffusion Time-steps for Unsupervised Representation Learning","created":"2024-01-21","cited_by_count":36,"area":null},{"id":"2110.15245","title":"From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence","created":"2021-10-28","cited_by_count":35,"area":null},{"id":"2202.02016","title":"Identifiability of Label Noise Transition Matrix","created":"2022-02-04","cited_by_count":34,"area":null},{"id":"2505.07538","title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning","created":"2025-05-12","cited_by_count":33,"area":"lr"},{"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":"2110.15796","title":"Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning","created":"2021-10-29","cited_by_count":30,"area":null},{"id":"2301.13721","title":"DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models","created":"2023-01-31","cited_by_count":30,"area":"diffusion"},{"id":"2106.00694","title":"Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators","created":"2021-06-01","cited_by_count":29,"area":null},{"id":"2310.00105","title":"Latent Space Symmetry Discovery","created":"2023-09-29","cited_by_count":29,"area":null},{"id":"2106.03375","title":"Commutative Lie Group VAE for Disentanglement Learning","created":"2021-06-07","cited_by_count":27,"area":null},{"id":"2111.01365","title":"Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics","created":"2021-11-02","cited_by_count":27,"area":"offlinerl"},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2402.09712","title":"Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement","created":"2024-02-15","cited_by_count":27,"area":"diffusion"},{"id":"2203.09250","title":"Symmetry-Based Representations for Artificial and Biological General Intelligence","created":"2022-03-17","cited_by_count":26,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2212.01354","title":"Designing Ecosystems of Intelligence from First Principles","created":"2022-12-02","cited_by_count":23,"area":null},{"id":"2102.10303","title":"Towards Building A Group-based Unsupervised Representation Disentanglement Framework","created":"2021-02-20","cited_by_count":22,"area":null},{"id":"2204.13661","title":"Toward Compositional Generalization in Object-Oriented World Modeling","created":"2022-04-28","cited_by_count":22,"area":"wm"},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","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":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20,"area":null},{"id":"2312.05719","title":"DVANet: Disentangling View and Action Features for Multi-View Action Recognition","created":"2023-12-10","cited_by_count":19,"area":null},{"id":"2111.02338","title":"Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity","created":"2021-11-03","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":"2307.05134","title":"TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation","created":"2023-07-11","cited_by_count":18,"area":null},{"id":"2102.01264","title":"Evaluating the Interpretability of Generative Models by Interactive Reconstruction","created":"2021-02-02","cited_by_count":17,"area":null},{"id":"2207.03116","title":"Equivariant Representation Learning via Class-Pose Decomposition","created":"2022-07-07","cited_by_count":17,"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":"2104.07155","title":"Disentangling Representations of Text by Masking Transformers","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2310.18777","title":"Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings","created":"2023-10-28","cited_by_count":15,"area":null},{"id":"2504.19774","title":"If Concept Bottlenecks are the Question, are Foundation Models the Answer?","created":"2025-04-28","cited_by_count":15,"area":null},{"id":"2102.06204","title":"Disentangled Representations from Non-Disentangled Models","created":"2021-02-11","cited_by_count":13,"area":null},{"id":"2201.11259","title":"Controlling Directions Orthogonal to a Classifier","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2205.13700","title":"ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting","created":"2022-05-27","cited_by_count":13,"area":null},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2102.03169","title":"Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems","created":"2021-02-04","cited_by_count":12,"area":null},{"id":"2107.12549","title":"DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation","created":"2021-07-27","cited_by_count":12,"area":null},{"id":"2305.18484","title":"Neural Fourier Transform: A General Approach to Equivariant Representation Learning","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2309.12742","title":"Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation","created":"2023-09-22","cited_by_count":12,"area":null},{"id":"2403.03375","title":"Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations","created":"2024-03-05","cited_by_count":12,"area":null},{"id":"2406.17583","title":"Towards Compositional Interpretability for XAI","created":"2024-06-25","cited_by_count":12,"area":null},{"id":"2106.13746","title":"On Incorporating Inductive Biases into VAEs","created":"2021-06-25","cited_by_count":11,"area":null},{"id":"2108.05805","title":"Reimagining an autonomous vehicle","created":"2021-08-12","cited_by_count":11,"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":"2206.11939","title":"Measuring Representational Robustness of Neural Networks Through Shared Invariances","created":"2022-06-23","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":"2403.02649","title":"Few-shot Learner Parameterization by Diffusion Time-steps","created":"2024-03-05","cited_by_count":11,"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},{"id":"2308.03312","title":"Exploiting Code Symmetries for Learning Program Semantics","created":"2023-08-07","cited_by_count":10,"area":null},{"id":"2403.01946","title":"A Generative Model of Symmetry Transformations","created":"2024-03-04","cited_by_count":10,"area":null},{"id":"2412.11521","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","created":"2024-12-16","cited_by_count":10,"area":null},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2108.13753","title":"Disentanglement Analysis with Partial Information Decomposition","created":"2021-08-31","cited_by_count":9,"area":null},{"id":"2203.11132","title":"Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2211.14961","title":"Linear Classification of Neural Manifolds with Correlated Variability","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2312.05840","title":"Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey","created":"2023-12-10","cited_by_count":9,"area":null},{"id":"2402.02346","title":"Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback","created":"2024-02-04","cited_by_count":9,"area":"diffusion"},{"id":"2402.16770","title":"Neural population geometry and optimal coding of tasks with shared latent structure","created":"2024-02-26","cited_by_count":9,"area":null},{"id":"2405.20905","title":"VENI, VINDy, VICI: a generative reduced-order modeling framework with uncertainty quantification","created":"2024-05-31","cited_by_count":9,"area":null},{"id":"2406.02696","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","created":"2024-06-04","cited_by_count":9,"area":"deeprl"},{"id":"2503.20771","title":"Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Data","created":"2025-03-26","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":"2210.11470","title":"i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2302.10701","title":"Scalable Infomin Learning","created":"2023-02-21","cited_by_count":8,"area":null}],"next_cursor":"100"}