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. SimLBR: Learning to Detect Fake Images by Learning to Detect Real Images

    Feb 23, 2026Aayush Dhakal, Subash Khanal, Srikumar Sastry +4AI-Generated Image DetectionOOD Generalization

    Washington University in St. Louis · Oak Ridge National Laboratory

  2. Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings

    Feb 23, 2026Lotta Mäkinen, Jorge Loría, Samuel KaskiMeta-LearningOOD Generalization

    Department of Computer Science, Aalto University, Espoo, Finland · ELLIS Institute Finland, Espoo, Finland · Department of Computer Science, University of Manchester, United Kingdom

  3. VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention

    Feb 23, 2026Jingbo Zhou, Jun Xia, Siyuan Li +11Graph TransformerNode Classification

    Zhejiang University Hangzhou, Zhejiang, China · Westlake University Hangzhou, Zhejiang, China · Hong Kong University of Science and Technology (Guangzhou) Guangzhou, Guangdong, China +4

  4. Spiking Graph Predictive Coding for Reliable OOD Generalization

    Feb 22, 2026Jing Ren, Jiapeng Du, Bowen Li +6OOD GeneralizationGraph Neural Networks

    RMIT University, Melbourne, Australia · University of Auckland, Auckland, New Zealand · CSIRO’s Data61, Melbourne, Australia +1

  5. Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition

    Feb 22, 2026Alexandros Haliassos, Rodrigo Mira, Stavros PetridisConnectionist Temporal ClassificationAutomatic Speech Recognition

    NatWest AI Research · Imperial College London

  6. WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation

    Feb 21, 2026Bo Liang, Chen Gong, Haobo Wang +8Human Pose EstimationOOD Generalization

    School of Computer Science, Peking University · University of Electronic Science and Technology of China · University of Pittsburgh +2

  7. Latent Equivariant Operators for Robust Object Recognition: Promises and Challenges

    Feb 20, 2026Minh Dinh, Stéphane DenyEquivariant Neural NetworksImage Classification

    Department of Computer Science, Dartmouth College, Hanover, NH 03755, USA · Departments of Computer Science & Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland

  8. A Deep Surrogate Model for Robust and Generalizable Long-Term Blast Wave Prediction

    Feb 20, 2026Danning Jing, Xinhai Chen, Xifeng Pu +5Neural Surrogate ModelingSpatiotemporal Forecasting

    National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha 410073, China · Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073, China · College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China +2

  9. Rethinking Beam Management: Generalization Limits Under Hardware Heterogeneity

    Feb 20, 2026Nikita Zeulin, Olga Galinina, Ibrahim Kilinc +2Wireless CommunicationsOOD Generalization

    Tampere University, Tampere, Finland · University of California San Diego, CA, USA

  10. OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models

    Feb 20, 2026Ling Lin, Yang Bai, Heng Su +5VLM EvaluationVLM Robustness

    School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230000, China · Suzhou Institute for Advanced Research, USTC, Suzhou 215123, China · Institute of High Performance Computing (IHPC), A*STAR, Singapore +1

  11. Causal Neighbourhood Learning for Invariant Graph Representations

    Feb 20, 2026Simi Job, Xiaohui Tao, Taotao Cai +2Graph Representation LearningCausal Representation Learning

    School of Science, Engineering and Digital Technologies, University of Southern Queensland, Australia. · School of Data Science, Lingnan University, Hong Kong.

  12. Anti-causal domain generalization: Leveraging unlabeled data

    Feb 19, 2026Sorawit Saengkyongam, Juan L. Gamella, Andrew C. Miller +3Domain GeneralizationOOD Generalization

    Apple · ETH Zürich

  13. Omitted Variable Bias in Language Models Under Distribution Shift

    Feb 18, 2026Victoria Lin, Louis-Philippe Morency, Eli Ben-MichaelOOD GeneralizationGeneralization Bounds

    Carnegie Mellon University, Pittsburgh, PA, USA

  14. Parameter-free representations outperform single-cell foundation models on downstream benchmarks

    Feb 18, 2026Huan Souza, Pankaj MehtaSingle-Cell RNA SequencingLinear Representation Hypothesis

    Department of Physics, Boston University, Boston, MA, 02215, USA · Faculty of Computing and Data Science, Boston University, Boston, MA, 02215, USA

  15. Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics

    Feb 17, 2026Anna Zimmel, Paul Setinek, Gianluca Galletti +2Test-Time AdaptationOOD Generalization

    ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz, Austria · Emmi AI GmbH, Linz, Austria

  16. On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks

    Feb 17, 2026Yannic Neuhaus, Nicolas Flammarion, Matthias Hein +1OOD GeneralizationMultimodal Reasoning

    Tübingen AI Center – University of Tübingen · EPFL · ELLIS Institute Finland – Aalto University

  17. Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledge

    Feb 16, 2026Siying Ma, Mehrdad M. Zadeh, Mauricio Soroco +3PDE Surrogate ModelingNeural Operators

    Simon Fraser University · Georgia Institute of Technology

  18. A Constrained Optimization Perspective of Unrolled Transformers

    Jan 24, 2026Javier Porras-Valenzuela, Samar Hadou, Alejandro RibeiroDeep Learning OptimizationTransformer

    Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, United States of America.

  19. 6 Fingers, 1 Kidney: Natural Adversarial Medical Images Reveal Critical Weaknesses of Vision-Language Models

    Dec 3, 2025Leon Mayer, Piotr Kalinowski, Caroline Ebersbach +6VLM EvaluationVLM Robustness

    German Cancer Research Center (DKFZ) Heidelberg, Division of Intelligent Medical Systems, Germany. · Medical Faculty, Heidelberg University, Germany. · Faculty of Mathematics and Computer Science, Heidelberg University, Germany. +9

  20. PISA: Prioritized Invariant Subgraph Aggregation for Out-of-Distribution Generalization on Graphs

    Nov 27, 2025Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli +1OOD GeneralizationInvariant Representation Learning

    Sapienza University of Rome · Université Côte d’Azur, CNRS, Inria, I3S

  21. Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation

    Nov 15, 2025Yannan Chen, Ruoyu Chen, Wei Wang +6Adversarial RobustnessOOD Generalization

    School of Cyber Science and Technology, Sun Yat-Sen University, Guangdong Province, China · Institute of Perception, PC Laboratory, Guangdong Province, China · University of Chinese Academy of Sciences, Beijing, China +3

  22. D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Frequency and Pixel Spaces

    Nov 14, 2025Ruoqi Wang, Haitao Wang, Shaojie Guo +1Unsupervised Domain AdaptationData Augmentation

    HKUST(GZ) · SYSU · ECNU +1

  23. Robust and Efficient Finetuning of Vision Foundation Models via Implicit Ensembling

    Oct 8, 2025Masih Aminbeidokhti, Heitor Rapela Medeiros, Eric Granger +1Vision Foundation Model AdaptationOOD Generalization

  24. Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes

    Oct 5, 2025Xiangjun Mi, Frank MuellerQuantum LDPC CodesQuantum Error Correction Decoding

    North Carolina State University, Raleigh, NC 27695, USA

  25. How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off

    Oct 1, 2025Waïss Azizian, Ali HasanLanguage Model PretrainingOOD Generalization

    Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LJK, 38000 Grenoble, France · Work done during an internship at Morgan Stanley Machine Learning Research. · Machine Learning Research, Morgan Stanley, New York, USA

  26. Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge

    Sep 29, 2025Pengxiao Lin, Zheng-An Chen, Zhi-Qin John XuTransformer InterpretabilityOOD Generalization

    School of Mathematical Sciences, Shanghai Jiao Tong University · Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University · Shanghai Seres Information Technology Co., Ltd, Shanghai 200040, China.

  27. CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalization

    Sep 18, 2025Min Zhang, Yuyin Wang, Zhongxiang Dai +4VLM AdaptationDomain Generalization

    East China Normal University · Xidian University · Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security +3

  28. When is Fine-Tuning Scalable? Certified Recovery from Noisy Data and Linear-Cost Fine-Tuning on Structured Task Shifts

    Aug 31, 2025Anastasis Kratsios, Tin Sum Cheng, Bum Jun Kim +1Fine-TuningOOD Generalization

    Department of Mathematics, McMaster University, Canada · Department of Mathematics and Computer Science, University of Basel, Switzerland · Department of Statistical Sciences, University of Toronto, Canada +1

  29. DE-VAE: Revealing Uncertainty in Parametric and Inverse Projections with Variational Autoencoders using Differential Entropy

    Aug 16, 2025Frederik L. Dennig, Daniel A. KeimVariational AutoencodersUncertainty Quantification

    University of Konstanz

  30. Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark

    Aug 8, 2025Ngoc N. Tran, Anwar Said, Waseem Abbas +2Distribution Shift RobustnessGraph Representation Learning

    Vanderbilt University, USA · Highmark Health, USA · University of Texas at Dallas, USA