{"total":941,"rows":[{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"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":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305,"area":null},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221,"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":"2103.02582","title":"D'ya like DAGs? A Survey on Structure Learning and Causal Discovery","created":"2021-03-03","cited_by_count":211,"area":null},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171,"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":"2308.07863","title":"StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models","created":"2023-08-15","cited_by_count":155,"area":"diffusion"},{"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":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136,"area":"alignment"},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2101.06046","title":"Counterfactual Generative Networks","created":"2021-01-15","cited_by_count":111,"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":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95,"area":null},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93,"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":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86,"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":"2103.05045","title":"Size-Invariant Graph Representations for Graph Classification Extrapolations","created":"2021-03-08","cited_by_count":84,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77,"area":"diffusion"},{"id":"2109.03795","title":"Desiderata for Representation Learning: A Causal Perspective","created":"2021-09-08","cited_by_count":76,"area":null},{"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":"2311.04056","title":"Multi-View Causal Representation Learning with Partial Observability","created":"2023-11-07","cited_by_count":74,"area":null},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73,"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":"2403.18818","title":"ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion","created":"2024-03-27","cited_by_count":71,"area":"diffusion"},{"id":"2106.00672","title":"What Matters for Adversarial Imitation Learning?","created":"2021-06-01","cited_by_count":70,"area":"offlinerl"},{"id":"2206.10044","title":"Identifiability of deep generative models without auxiliary information","created":"2022-06-20","cited_by_count":70,"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":"2309.05569","title":"ITI-GEN: Inclusive Text-to-Image Generation","created":"2023-09-11","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":"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":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59,"area":null},{"id":"2203.05818","title":"ZIN: When and How to Learn Invariance Without Environment Partition?","created":"2022-03-11","cited_by_count":58,"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":"2105.14257","title":"Diffusion-Based Representation Learning","created":"2021-05-29","cited_by_count":57,"area":null},{"id":"2103.10226","title":"Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations","created":"2021-03-18","cited_by_count":56,"area":null},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56,"area":null},{"id":"2105.06422","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","created":"2021-05-13","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":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"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":"2306.15764","title":"High Fidelity Image Counterfactuals with Probabilistic Causal Models","created":"2023-06-27","cited_by_count":53,"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":"2306.08757","title":"InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models","created":"2023-06-14","cited_by_count":50,"area":"diffusion"},{"id":"2301.08230","title":"Score-based Causal Representation Learning with Interventions","created":"2023-01-19","cited_by_count":49,"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":"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":"2104.14556","title":"Discover the Unknown Biased Attribute of an Image Classifier","created":"2021-04-29","cited_by_count":46,"area":null},{"id":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2103.14651","title":"Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice","created":"2021-03-27","cited_by_count":45,"area":null},{"id":"2109.01514","title":"Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows","created":"2021-09-03","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":"2103.15627","title":"Learning Generative Models of Textured 3D Meshes from Real-World Images","created":"2021-03-29","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":"2302.02228","title":"Counterfactual Identifiability of Bijective Causal Models","created":"2023-02-04","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":"2203.15756","title":"Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data","created":"2022-03-29","cited_by_count":42,"area":null},{"id":"2210.00482","title":"Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language","created":"2022-10-02","cited_by_count":42,"area":null},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41,"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":"2204.00607","title":"From Statistical to Causal Learning","created":"2022-04-01","cited_by_count":40,"area":null},{"id":"2305.18378","title":"Disentanglement via Latent Quantization","created":"2023-05-28","cited_by_count":40,"area":null},{"id":"2102.01331","title":"Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder","created":"2021-02-02","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":"2102.10271","title":"Meta-Learning Dynamics Forecasting Using Task Inference","created":"2021-02-20","cited_by_count":38,"area":null},{"id":"2107.11055","title":"Transporting Causal Mechanisms for Unsupervised Domain Adaptation","created":"2021-07-23","cited_by_count":38,"area":null},{"id":"2110.04121","title":"On the Limitations of Multimodal VAEs","created":"2021-10-08","cited_by_count":38,"area":null},{"id":"2311.02794","title":"Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder","created":"2023-11-05","cited_by_count":38,"area":null},{"id":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37,"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":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","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":"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":"2106.13292","title":"Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation","created":"2021-06-24","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":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2108.07668","title":"Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation","created":"2021-08-17","cited_by_count":35,"area":null},{"id":"2205.02837","title":"BlobGAN: Spatially Disentangled Scene Representations","created":"2022-05-05","cited_by_count":35,"area":null}],"next_cursor":"100"}