{"total":94,"rows":[{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2206.04046","title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","created":"2022-06-08","cited_by_count":85,"area":"moe"},{"id":"2209.08590","title":"RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection","created":"2022-09-18","cited_by_count":52,"area":null},{"id":"2204.10268","title":"Out-of-distribution generalization for learning quantum dynamics","created":"2022-04-21","cited_by_count":49,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"area":null},{"id":"2201.12919","title":"Provable Domain Generalization via Invariant-Feature Subspace Recovery","created":"2022-01-30","cited_by_count":32,"area":null},{"id":"2402.00957","title":"Credal Learning Theory","created":"2024-02-01","cited_by_count":31,"area":null},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30,"area":null},{"id":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2301.13323","title":"Fairness and Accuracy under Domain Generalization","created":"2023-01-30","cited_by_count":24,"area":null},{"id":"2402.02949","title":"Kernel PCA for Out-of-Distribution Detection","created":"2024-02-05","cited_by_count":24,"area":null},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2311.08503","title":"MADG: Margin-based Adversarial Learning for Domain Generalization","created":"2023-11-14","cited_by_count":22,"area":null},{"id":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","cited_by_count":21,"area":null},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16,"area":"mechinterp"},{"id":"2209.15177","title":"Domain Generalization -- A Causal Perspective","created":"2022-09-30","cited_by_count":14,"area":null},{"id":"2507.21160","title":"Handling Out-of-Distribution Data: A Survey","created":"2025-07-25","cited_by_count":14,"area":null},{"id":"2310.09586","title":"Causality and Independence Enhancement for Biased Node Classification","created":"2023-10-14","cited_by_count":13,"area":null},{"id":"2402.07785","title":"HYPO: Hyperspherical Out-of-Distribution Generalization","created":"2024-02-12","cited_by_count":13,"area":null},{"id":"2210.09236","title":"ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2206.14917","title":"Towards out of distribution generalization for problems in mechanics","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2305.11052","title":"BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval","created":"2023-05-18","cited_by_count":11,"area":null},{"id":"2403.06392","title":"Towards Robust Out-of-Distribution Generalization Bounds via Sharpness","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2410.20380","title":"FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion","created":"2024-10-27","cited_by_count":11,"area":null},{"id":"2502.08991","title":"Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2303.01092","title":"ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations","created":"2023-03-02","cited_by_count":10,"area":null},{"id":"2310.14227","title":"Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective","created":"2023-10-22","cited_by_count":10,"area":null},{"id":"2311.14315","title":"Robust Domain Misinformation Detection via Multi-modal Feature Alignment","created":"2023-11-24","cited_by_count":10,"area":null},{"id":"2202.06208","title":"Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transport","created":"2022-02-13","cited_by_count":9,"area":null},{"id":"2412.14097","title":"Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2502.10706","title":"Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling","created":"2025-02-15","cited_by_count":9,"area":null},{"id":"2502.19167","title":"Generalizable deep learning for photoplethysmography-based blood pressure estimation -- A Benchmarking Study","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2204.13779","title":"Formulating Robustness Against Unforeseen Attacks","created":"2022-04-28","cited_by_count":8,"area":null},{"id":"2304.13976","title":"Moderately Distributional Exploration for Domain Generalization","created":"2023-04-27","cited_by_count":8,"area":null},{"id":"2207.06687","title":"Breaking Correlation Shift via Conditional Invariant Regularizer","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2209.00652","title":"Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solution","created":"2022-09-01","cited_by_count":6,"area":null},{"id":"2408.07772","title":"Out-of-Distribution Learning with Human Feedback","created":"2024-08-14","cited_by_count":6,"area":"alignment"},{"id":"2505.24731","title":"Circuit Stability Characterizes Language Model Generalization","created":"2025-05-30","cited_by_count":6,"area":"mechinterp"},{"id":"2403.13850","title":"Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2505.21422","title":"When Shift Happens - Confounding Is to Blame","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2207.09638","title":"Doge Tickets: Uncovering Domain-general Language Models by Playing Lottery Tickets","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2211.11243","title":"Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2402.05916","title":"GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2409.19431","title":"Generalization and Robustness of the Tilted Empirical Risk","created":"2024-09-28","cited_by_count":4,"area":null},{"id":"2410.08255","title":"Investigating Representation Universality: Case Study on Genealogical Representations","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2510.18052","title":"Measure-Theoretic Anti-Causal Representation Learning","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2112.10844","title":"Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift","created":"2021-12-20","cited_by_count":3,"area":null},{"id":"2206.02990","title":"Enhancing Distributional Stability among Sub-populations","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2312.16815","title":"Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studies","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2407.07544","title":"Disentangling Masked Autoencoders for Unsupervised Domain Generalization","created":"2024-07-10","cited_by_count":3,"area":null},{"id":"2412.05169","title":"Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2108.12992","title":"SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2302.09815","title":"On the Stability and Generalization of Triplet Learning","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2304.00629","title":"A principled approach to model validation in domain generalization","created":"2023-04-02","cited_by_count":2,"area":null},{"id":"2408.11237","title":"Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2410.08898","title":"Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2410.20295","title":"DeCaf: A Causal Decoupling Framework for OOD Generalization on Node Classification","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2411.15626","title":"Aligning Generalisation Between Humans and Machines","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2505.01130","title":"Risk Analysis and Design Against Adversarial Actions","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2512.00778","title":"What Is Preference Optimization Doing, and Why?","created":"2025-11-30","cited_by_count":2,"area":"alignment"},{"id":"2209.07699","title":"Graph Contrastive Learning with Cross-view Reconstruction","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2310.03738","title":"Robust Novelty Detection through Style-Conscious Feature Ranking","created":"2023-10-05","cited_by_count":1,"area":null},{"id":"2311.00966","title":"Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2311.13959","title":"RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2405.03052","title":"A View on Out-of-Distribution Identification from a Statistical Testing Theory Perspective","created":"2024-05-05","cited_by_count":1,"area":null},{"id":"2501.10202","title":"Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach","created":"2025-01-17","cited_by_count":1,"area":null},{"id":"2503.02961","title":"Koopman-Based Generalization of Deep Reinforcement Learning With Application to Wireless Communications","created":"2025-03-04","cited_by_count":1,"area":"deeprl"},{"id":"2506.20025","title":"Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2506.20575","title":"Exploring Graph-Transformer Out-of-Distribution Generalization Abilities","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2508.01525","title":"MiraGe: Multimodal Discriminative Representation Learning for Generalizable AI-Generated Image Detection","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2510.19330","title":"Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.19700","title":"Generalizable Multimodal Large Language Model Editing via Invariant Trajectory Learning","created":"2026-01-27","cited_by_count":1,"area":"mllm"},{"id":"2208.07798","title":"Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization","created":"2022-08-16","cited_by_count":0,"area":null},{"id":"2211.14594","title":"Direct-Effect Risk Minimization for Domain Generalization","created":"2022-11-26","cited_by_count":0,"area":null},{"id":"2301.06454","title":"PlasmoFAB: A Benchmark to Foster Machine Learning for Plasmodium falciparum Protein Antigen Candidate Prediction","created":"2023-01-16","cited_by_count":0,"area":null},{"id":"2306.00879","title":"Domain Generalization for Domain-Linked Classes","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2306.09177","title":"Dis-AE: Multi-domain & Multi-task Generalisation on Real-World Clinical Data","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2307.10997","title":"DREAM: Domain-free Reverse Engineering Attributes of Black-box Model","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2309.12301","title":"Environment-biased Feature Ranking for Novelty Detection Robustness","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2405.19461","title":"Clustering-Based Validation Splits for Model Selection under Domain Shift","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2405.19703","title":"Towards a Better Evaluation of Out-of-Domain Generalization","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2505.11760","title":"Topology-Aware Knowledge Propagation in Decentralized Learning","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.03674","title":"Out-of-Distribution Graph Models Merging","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.12829","title":"General and Estimable Learning Bound Unifying Covariate and Concept Shifts","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2507.19372","title":"Learning neuro-symbolic convergent term rewriting systems","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2512.09067","title":"Contrast transfer functions help quantify neural network out-of-distribution generalization in HRTEM","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2602.00002","title":"Disentangled Interest Network for Out-of-Distribution CTR Prediction","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.17088","title":"MeGU: Machine-Guided Unlearning with Target Feature Disentanglement","created":"2026-02-19","cited_by_count":0,"area":"safety"},{"id":"2603.07388","title":"Sparsity and Out-of-Distribution Generalization","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.23514","title":"Probabilistic Graphical Model using Graph Neural Networks for Bayesian Inversion of Discrete Structural Component States","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.06368","title":"eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2609.31996","title":"Can Circuit Alignment Predict OOD Generalization?","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}