OOD Generalization

OOD: Out-of-Distribution

Ask about this topic

Overview

Out-of-distribution generalization asks whether models learn patterns that transfer beyond the data they were trained on, such as to new hospitals, locations, time periods, molecular structures, or task compositions. Common approaches include causal and invariant representation learning, domain-generalization methods such as GroupDRO, targeted data augmentation, and physics-informed or compositional models that encode structure. Other strategies adapt models at test time or use prompts, retrieval, uncertainty estimates, and validation proxies to select or adjust predictions under shift. Across vision, language, graphs, science, and robotics, strong in-distribution scores and larger pretraining sets often fail to ensure transfer, leaving realistic shift evaluation and the trade-off between adaptation and preserving useful prior knowledge as central challenges.

Latest papers

CardsList

399 papers45 papers in the last four weeks, up 29% on the four weeks before. 0.3% of all new papers.

  1. Reaction precedents extend retrosynthetic prediction beyond training coverage

    Oct 29, 2026Jiaxing Sun, Xuli Shen, Jiang Wu +17RetrosynthesisChemical Reaction Prediction

    Shanghai Artificial Intelligence Laboratory · Fudan University · Peking University +5

  2. Implicit Reasoning in Transformers: Bridging the Compositionality Gap in GPT-2-like Models

    Oct 28, 2026Davide Venuto, Leonardo VenutoCompositional GeneralizationOOD Generalization

    Technical University of Denmark (DTU), Lyngby, Denmark · Independent Researcher, Heidelberg, Germany

  3. In-Context Learning for Multi-Fidelity Multiscale Model Closure and Cross-Operator Out-Of-Distribution Generalization

    Oct 28, 2026Xinyuan Li, Matthew Zahr, Panos Stinis +1Multifidelity ModelingPDE Operator Learning

    Department of Applied and Computational Mathematics and Statistics, University of Notre Dame, Notre Dame, IN 46556, USA. · Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN 46556, United States. · Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, Richland, WA 99354, USA.

  4. Efficacy of Monocular Depth Estimation in Lunar Environments

    Oct 27, 2026Michael W. Lanighan, Kenji Brameld, Seth GeeMonocular Depth Estimation3D Reconstruction

    TRACLabs Inc., 1331 Gemini Street; Houston, TX 77058.

  5. LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach

    Oct 27, 2026Sølve Langseth, Kristoffer Herland Hellton, Hugo L. HammerOOD GeneralizationTabular Prediction

    Department of Computer Science, Oslo Metropolitan University, Oslo, Norway · Department of Holistic Systems, SimulaMet, Oslo, Norway · Department of Plastic and Reconstructive Surgery, Oslo University Hospital, Oslo, Norway

  6. PRISM: Pathology Reliability In Scarce-label Medicine. A Tile-level Benchmark of Pathology Foundation Models

    Oct 27, 2026Alicem KoyunComputational PathologyPathology Foundation Models

    Westcliff University

  7. What Remains OOD? OODConceptBench for Open-World Concept Recognition in Vision-Language Models

    Oct 24, 2026Zhiran Luo, Zhiyong Yang, Zitai Wang +3VLM EvaluationOOD Generalization

    School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China +2

  8. Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules

    Oct 23, 2026M. Harper Langston, Pierre-David Letourneau, Dalton Jones +7Learning to OptimizeOOD Generalization

    Qualcomm AI Research

  9. SKG in Practice: OOD Generalization Cases Across FourDomains

    Oct 23, 2026Jian An, Chaoshi Wu, Xinpan LuoScientific MLOOD Generalization

  10. Escaping the Phylogenetic Trap: Persistent Homology Enables Cross-Species Ion Channel Classification via Multimodal Graph Neural Networks

    Oct 21, 2026Arezoo Bybordi, Favour Achimba, Mariam Gelashvili +4OOD GeneralizationProtein Representation Learning

    The Graduate Center, City University of New York · Hunter College, City University of New York · Tandon School of Engineering, New York University +3

  11. Implicit Feature Reweighting for Label-Free Graph Generalization

    Oct 21, 2026Tianjun Yao, Chen Xi, Xinyang Li +1OOD GeneralizationGraph Representation Learning

    Shenzhen Loop Area Institute · Guangzhou University · North China Electric Power University +1

  12. Causal world models under physical parameter shifts

    Oct 21, 2026Chu Lin, Yi SunCausal World ModelsWorld Models for Robotics

    Department of Computer Science, The City College of New York, New York, NY 10031, USA · Department of Electrical Engineering, The City College of New York, New York, NY 10031, USA

  13. TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization

    Oct 20, 2026Chengtao Jian, Kai YangLLM AlignmentDirect Preference Optimization

    School of Computer Science and Technology, Tongji University, Shanghai, China · Shenzhen Loop Area Institute, Shenzhen, China · Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China

  14. Language Guidance for Supervised Vision Training: An Empirical Study of Generalization

    Oct 19, 2026Shruthi Gowda, Nikita Jain, Elahe Arani +1OOD GeneralizationShortcut Learning

    Eindhoven University of Technology

  15. CoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Cooperative Forecasting

    Oct 19, 2026Zehao Wang, Jianpeng Yao, Yuping Wang +9Social Robot NavigationMulti-Robot Systems

    Georgia Institute of Technology · University of California, Riverside · University of Michigan, Ann Arbor +3

  16. On Data Scaling in Tabular ML: More Data, Better Generalization?

    Oct 19, 2026Ivan Rubachev, Nikita Lazarev, Artem BabenkoTabular MLTabular Foundation Models

    Yandex · HSE University

  17. Cognitively Decoupled Meta-Induction for Out-of-Distribution Generalization

    Oct 19, 2026Yuqian Wang, Yuanzheng Wang, Chaojun Xiao +7Inductive Reasoning in Language ModelsOOD Generalization

    Beijing Institute of Technology · University of Chinese Academy of Sciences · Department of Computer Science and Technology, Tsinghua University +4

  18. PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization

    Oct 19, 2026Xinyi Chen, Jiahuan Pang, Titus Chima +2Molecular Property PredictionSelf-Supervised Pre-Training

    Global College, Shanghai Jiao Tong University, Shanghai, China. · Digital Innovation Research Center, Duke Kunshan University, Kunshan, Jiangsu, China. · Zu Chongzhi Center, Duke Kunshan University, Kunshan, Jiangsu, China. +1

  19. CFC26: Building Evaluations for Deployment in Sonar-Based Fish Counting

    Oct 15, 2026Madison Van Horn, Suzanne Stathatos, Sevan Brodjian +6Object CountingWildlife Monitoring

    California Institute of Technology · Massachusetts Institute of Technology · California Institute of Technology Volunteer

  20. Predicting Unseen Scientific Interactions: Conditional Flow Models Hallucinate Non-Additive Effects

    Oct 14, 2026Sam Gijsen, Moritz Seiler, Kerstin RitterConditional Generative ModelingFeature Interaction Modeling

  21. Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

    Oct 14, 2026Christos Panourgias, Roberto Stanzione, Adrien Petralia +2Model SelectionTime-Series Anomaly Detection

    Université Paris Cité, LIPADE · École Normale Supérieure, Inria

  22. Who's Behind the Text? Robust Model Authorship Attribution

    Oct 14, 2026Minseok Ko, Hyunseok Lee, Woomin Song +3Authorship AttributionOOD Generalization

    Korea Advanced Institute of Science and Technology (KAIST)

  23. Geometric Calibration of Supervised Fine-Tuning

    Oct 13, 2026Jianzhu Bao, Jia-Chen Gu, Qingyuan Liu +4LLM Fine-TuningSupervised Fine-Tuning

    Nanyang Technological University · University of California, Los Angeles

  24. SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models

    Oct 13, 2026Jerrold Huang, Junwei Quan, Saiyue Lyu +2Agent Skill Security AuditingAI Agent Security Benchmarks

    University of Toronto · University of British Columbia · Rutgers University

  25. What Do Deepfake Audio Detectors Hear? From Self-Supervised Models to Audio LLMs

    Oct 13, 2026Wanying Ge, Xin Wang, Junichi YamagishiAudio Deepfake DetectionExplainable Deepfake Detection

    National Institute of Informatics, Chiyoda-ku, Tokyo 101-8430, Japan

  26. Comprehensive Workflow for Uncertainty-Aware Ionic Liquid Solvent Discovery

    Oct 12, 2026Alexander Lobo, Urvi Awasthi, Leonid ZhukovMaterials Property PredictionMaterials Science

    BCG X AI Science Institute

  27. RINO: Renormalization Group Distillation with No Labels

    Oct 11, 2026Zichun Hao, Raghav Kansal, Abhijith Gandrakota +6Self-Supervised LearningHigh-Energy Physics

    Division of Physics, Mathematics and Astronomy, California Institute of Technology, Pasadena, CA 91125 · Physics Division, Fermi National Accelerator Laboratory, Batavia, IL 60510

  28. Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning

    Oct 11, 2026Chang-Hoon Jeong, Kisung Shin, Hanwool Sul +1Meta-Reinforcement LearningOOD Generalization

    Dept. of Computer Science and Engineering, Seoul National University · Interdisciplinary Program in Artificial Intelligence, Seoul National University

  29. Predicting how model propensities generalize out of distribution

    Oct 10, 2026June Hunter, Lily Wen, Owen Terry +3OOD GeneralizationLanguage Model Generalization

  30. In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation

    Oct 9, 2026Matteo Rufolo, Dario Piga, Filippo Pura +1System IdentificationIn-Context Learning

    SUPSI, IDSIA - Dalle Molle Institute for Artificial Intelligence, Lugano, Switzerland · USI, Faculty of Informatics, Lugano, Switzerland