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. Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications

    Mar 17, 2026Debdas Paul, Elisa Ferrari, Irene Gravili +1OOD GeneralizationDebiased ML

    Leibniz Institute on Aging — Fritz Lipmann Institute (FLI), Beutenbergstr. 11, Jena, 100190, Germany.

  2. Synergizing Deep Learning and Biological Heuristics for Extreme Long-Tail White Blood Cell Classification

    Mar 17, 2026Duc T. Nguyen, Hoang-Long Nguyen, Huy-Hieu PhamWhite Blood Cell ClassificationMedical Image Classification

    College of Engineering & Computer Science, VinUniversity, Hanoi, Vietnam · VinUni-Illinois Smart Health Center, VinUniversity, Hanoi, Vietnam · The Computer Vision and Medical AI Lab, VinUniversity, Hanoi, Vietnam

  3. Low-Field Magnetic Resonance Image Quality Enhancement using Undersampled k-Space and Out-of-Distribution Generalisation

    Mar 14, 2026Daniel Tweneboah Anyimadu, Mohammed M. Abdelsamea, Ahmed Karam EldalyMagnetic Resonance ImagingAccelerated MRI Reconstruction

    Department of Computer Science, University of Exeter, Exeter, United Kingdom · UCL Hawkes Institute, Department of Computer Science, University College London, London, United Kingdom

  4. Towards Generalizable Deepfake Detection via Real Distribution Bias Correction

    Mar 14, 2026Ming-Hui Liu, Harry Cheng, Xin Luo +2Feature WhiteningDeepfake Detection

    School of Software, Shandong University, Jinan 250101, China · School of Computing, National University of Singapore, Singapore · School of Software, Shandong University, Jinan 250100, China

  5. Manifold-Orthogonal Dual-spectrum Extrapolation for Parameterized Physics-Informed Neural Networks

    Mar 14, 2026Zhangyong Liang, Huanhuan GaoPDE Operator LearningPhysics-Informed ML

  6. EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages

    Mar 10, 2026Aman Sharma, Paras ChopraLLM EvaluationLLM Code Generation

    Lossfunk

  7. Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness

    Mar 9, 2026Yehonatan Elisha, Oren Barkan, Noam KoenigsteinSpurious Correlation RobustnessVision Transformer

    Tel Aviv University · The Open University

  8. SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning

    Mar 9, 2026Yuxiang Zhang, Enyan DaiGraph Neural NetworksSpurious Correlation Robustness

    The Hong Kong University of Science and Technology (Guangzhou)

  9. Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment

    Mar 8, 2026Binxia Xu, Xiaoliang Luo, Luke Dickens +1OOD Generalization

    School of Data Science, Fudan University, Shanghai · Independent Researcher, London · Department of Information Studies, University College London, London +1

  10. Sparsity and Out-of-Distribution Generalization

    Mar 8, 2026Scott Aaronson, Lin Lin Lee, Jiawei LiOOD GeneralizationGeneralization Bounds

    UT Austin

  11. Learning Clinical Representations Under Systematic Distribution Shift

    Mar 7, 2026Yuanyun Zhang, Shi LiOOD GeneralizationInvariant Representation Learning

    Columbia University

  12. Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models

    Mar 6, 2026Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin +2Vision-Language GroundingVLM Robustness

    The KOW Company · University of Dhaka · American International University - Bangladesh (AIUB)

  13. Layer by layer, module by module: Choose both for optimal OOD probing of ViT

    Mar 5, 2026Ambroise Odonnat, Vasilii Feofanov, Laetitia Chapel +2Vision TransformerOOD Generalization

    Noah’s Ark Lab, Inria · L’Institut Agro, IRISA · Univ. Rennes 2, IRISA +1

  14. Distribution-Conditioned Transport

    Mar 5, 2026Nic Fishman, Gokul Gowri, Paolo L. B. Fischer +3OOD Generalization

    Harvard University · MIT · Beth Israel Deaconess Medical Center +2

  15. Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading

    Mar 4, 2026Mahindra Rautela, Alexander Most, Siddharth Mansingh +9PDE Foundation ModelsOOD Generalization

    AOT-IC Group, Los Alamos National Laboratory, Los Alamos, New Mexico, US, 87545 · CAI Division, Los Alamos National Laboratory, Los Alamos, New Mexico, US, 87545 · EES Divison, Los Alamos National Laboratory, Los Alamos, New Mexico, US, 87545 +2

  16. Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects

    Mar 4, 2026Ji-Lun Peng, Yun-Nung ChenPersonality Modeling in Language ModelsOOD Generalization

    National Taiwan University, Taipei, Taiwan · Academia Sinica, Taipei, Taiwan

  17. Extending Neural Operators: Robust Handling of Functions Beyond the Training Set

    Mar 4, 2026Blaine Quackenbush, Paul J. AtzbergerNeural OperatorsOOD Generalization

    Department of Mathematics, University of California Santa Barbara (UCSB). · Department of Mathematics, Department of Mechanical Engineering, University of California Santa Barbara (UCSB)

  18. Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs

    Mar 3, 2026Mingyu Jin, Yutong Yin, Jingcheng Niu +7OOD GeneralizationRepresentation Geometry in Language Models

    Rutgers University · Northwestern University · UKP Lab, TU Darmstadt +3

  19. Scale-invariant Gaussian derivative residual networks

    Mar 3, 2026Andrzej Perzanowski, Tony LindebergOOD GeneralizationEquivariant Neural Networks

    Computational Brain Science Lab, Department of Computational Science and Technology, KTH Royal Institute of Technology, SE-100 44 Stockholm, Sweden.

  20. Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation

    Mar 3, 2026Chonghua Lv, Dong Zhao, Shuang Wang +4Domain Generalization for Semantic SegmentationKnowledge Distillation

    School of Artificial Intelligence, Xidian University, China · Department of Information Engineering and Computer Science, University of Trento, Italy · Department of Automation, Tsinghua University, China +1

  21. Diagnosing Generalization Failures from Representational Geometry Markers

    Mar 2, 2026Chi-Ning Chou, Artem Kirsanov, Yao-Yuan Yang +1Neural Network GeneralizationOOD Generalization

    Flatiron Institute · Harvard University · Google DeepMind

  22. Towards OOD Generalization in Dynamic Graphs via Causal Invariant Learning

    Mar 2, 2026Xinxun Zhang, Pengfei Jiao, Mengzhou Gao +2OOD GeneralizationDynamic Graph Learning

    School of Cyberspace, Hangzhou Dianzi University, China · State Key Laboratory of AI Safety, Beijing · School of Computer Science, Wuhan University, China +1

  23. HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts

    Mar 2, 2026Wenxuan Huang, Mingyu Tsoi, Yanhao Huang +10Single-Cell Perturbation ModelingOOD Generalization

    Fudan University · Shanghai Artificial Intelligence Laboratory · The Hong Kong University of Science and Technology +4

  24. Improving Full Waveform Inversion in Large Model Era

    Feb 27, 2026Yinan Feng, Peng Jin, Yuzhe Guo +2Inverse ProblemsOOD Generalization

    School of Data Science and Society University of North Carolina at Chapel Hill Chapel Hill, NC, USA · The Pennsylvania State University State College, PA, USA · Google DeepMind

  25. UPath: Universal Planner Across Topological Heterogeneity For Grid-Based Pathfinding

    Feb 27, 2026Aleksandr Ananikian, Daniil Drozdov, Konstantin YakovlevMotion PlanningOOD Generalization

    Saint-Petersburg University

  26. Reasoning-Driven Multimodal LLM for Domain Generalization

    Feb 27, 2026Zhipeng Xu, Zilong Wang, Xinyang Jiang +3Domain GeneralizationMultimodal Domain Generalization

    Xidian University · Microsoft Research Asia · National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application

  27. Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration

    Feb 26, 2026Xiaole Tang, Xiaoyi He, Jiayi Xu +2All-in-One Image RestorationOOD Generalization

    School of Mathematics and Statistics, Xi’an Jiaotong University, Shaanxi, P.R. China.

  28. On Sample-Efficient Generalized Planning via Learned Transition Models

    Feb 26, 2026Nitin Gupta, Vishal Pallagani, John A. Aydin +1Model-Based PlanningOOD Generalization

    University of South Carolina

  29. Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking

    Feb 25, 2026Yuheng Li, Weitong Chen, Chengcheng Zhu +4Robust WatermarkingMeta-Learning

    Yangzhou University · Nanjing University · Shandong University +2

  30. Tool Use Reduces Depth-Induced Collapse in OOD Reasoning

    Feb 24, 2026David Koplow, Tomer Galanti, Tomaso PoggioOOD GeneralizationLLM Tool Use

    Massachusetts Institute of Technology · Texas A&M University