OOD Generalization

OOD: Out-of-Distribution

Follow this topic Ask about this topic

Momentum

29 papers in the last four weeks, up 263% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 261

All topics

EarthShift: a benchmark for measuring robustness to real-world distribution shifts in Earth observation
May 28, 2026Kelsey Doerksen, Hannah KernerDistribution Shift Robustness Geospatial Foundation Models
School of Computing and Augmented Intelligence Arizona State University
Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts
May 28, 2026Mengdi Chu, Yang Liu, Ayan Biswas +1Distribution Shift Robustness Neural Network Generalization
The Ohio State University · Los Alamos National Laboratory
Toward Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data
May 28, 2026Caio Petrucci, Leo Sampaio Ferraz Ribeiro, Sandra AvilaZero-Shot Learning OOD Generalization
1Instituto de Computac¸˜ao, Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil · 2Instituto de Ciˆencias Matem´aticas e de Computac¸˜ao, Universidade de S˜ao Paulo (USP), S˜ao Carlos, Brazil
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
May 27, 2026Jiapeng Zhu, Jianxiang Yu, Yibo Zhao +5Agentic RL OOD Generalization
1East China Normal University, 2Meituan Longcat Team · 1East China Normal University · 2Meituan Longcat Team
SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling
May 27, 2026Quanen Sun, Changxin Tian, Ke Shi +6LLM Evaluation Language Model Scaling Laws
Ant Group
The Role of Causal Features in Strategic Classification for Robustness and Alignment
May 26, 2026Antonio Gois, Sophia Gunluk, Nir Rosenfeld +3Strategic Classification OOD Generalization
Mila & Universit´e de Montr´eal · Faculty of Computer Science, Technion - Israel Institute of Technology · Canada CIFAR AI Chair +1
Causal Representation Learning for Generalisable Recommendation
May 26, 2026Yorgos Felekis, Michael O'Riordan, Oriol Corcoll +1Disentangled Representation Learning Causal Representation Learning
University of Warwick · Spotify · Spotify & University College London
Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining
May 26, 2026Biao Ouyang, Tengxue Zhang, Zhihao Zhuang +3Time-Series Causal Discovery OOD Generalization
East China Normal University
Conformalised imprecise inference for robust extrapolation under limited data
May 25, 2026Yu Chen, Scott FersonDistribution Shift Robustness Uncertainty Quantification
Institute for Risk and Uncertainty · University of Liverpool · Liverpool
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
May 25, 2026Khoi Le, Tri Cao, Phong Nguyen +5Pairwise Preference Learning Reward Modeling
National University of Singapore · VinUniversity · Nanyang Technological University
UAV-OVO: Out-of-Viewpoint Generalization in UAV Action Recognition
May 25, 2026Yu Xia, Zhengbo Zhang, Shuaihu Zhang +1Test-Time Adaptation OOD Generalization
Wuhan University · Singapore University of Technology and Design
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
May 25, 2026Bo Lv, Jingbo SunOOD Generalization Question Decomposition
Tencent Hunyuan · University of Chinese Academy of Sciences
Abduction-Deduction Entanglement: Domain Generalization via Representation Transplants
May 24, 2026Kasra Jalaldoust, Elias BareinboumDomain Generalization OOD Generalization
Department of Computer Science Columbia University New York, NY 10027, USA
ROAR: Retrieval Opportunity-Aware Refinement for Zero-Shot Time Series Forecasting
May 24, 2026Jinjin Chi, Lei Feng, Yiming Wang +4Zero-Shot Time Series Forecasting Time Series Forecasting
College of Computer Science and Technology, Jilin University, Changchun, China · College of Computing and Data Science, Nanyang Technological University, Singapore
ChainzRule: Sample-Efficient, Robust Deep Learning Across Tabular, NLP, and Vision Tasks
May 23, 2026Rowan MartnishnPolynomial Neural Networks Neural Network Robustness
Sentivity AI
Revitalizing Dense Material Segmentation: Stabilized Vision Transformers and the Generalization Paradox
May 22, 2026Allan Kazakov, Duygu Cakir, Hilal Kurt İrfanoğlu +1Image Segmentation Vision Transformer
Bahcesehir University, Istanbul, Turkey · Poder Bilişim Teknolojileri Sanayi ve Ticaret A.Ş., Istanbul, Turkey · Galatasaray University, Istanbul, Turkey
Understanding Goal Generalisation in Sequential Reinforcement Learning
May 22, 2026Jason Ross Brown, Edward James YoungReinforcement Learning OOD Generalization
University of Cambridge Cambridge, United Kingdom · University of Cambridge & Geodesic Research Cambridge, United Kingdom
No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation
May 21, 2026Bradley Stanley-Clamp, Anson Lei, Hannah M. Christensen +1Distribution Shift Robustness Climate Science
Applied AI Lab · University of Oxford, UK · Atmospheric, Oceanic and Planetary Physics
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
May 21, 2026Sungjun Lim, Heedong Kim, Andrew Lee +1Distribution Shift Robustness OOD Generalization
aYonsei University · bHarvard University
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
May 20, 2026Lucheng Fu, Ye Yu, Yiyang Wang +4Neural Network Generalization Large Language Model-Guided Optimization
Georgia Institute of Technology · University of Illinois Urbana-Champaign
A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
May 19, 2026Yuyang Zhang, Yifu Zhang, Xuehai Zhou +1Transformer Expressivity OOD Generalization
McGill University · Mila - Quebec AI Institute · Université de Montréal
FLUXtrapolation: A benchmark on extrapolating ecosystem fluxes
May 19, 2026Anya Fries, Jacob A Nelson, Martin Jung +2Distribution Shift Robustness OOD Generalization
Seminar for Statistics, ETH Zürich Zürich, Switzerland · Max Planck Institute for Biogeochemistry Jena, Germany
Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection
May 19, 2026Fatemeh Pesaran Zadeh, Seyeon Choi, Xing Han Lù +2OOD Generalization Training Data Selection
Seoul National University · McGill University · Mila – Quebec AI Institute +1
Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning
May 19, 2026Nasehatul Mustakim, Lucas LehnertPartially Observable RL OOD Generalization
Department of Computer Science University of Saskatchewan Saskatoon, Saskatchewan, Canada
PACE-FNO: Physics-Aligned Canonical Equivariance for Fourier Neural Operators
May 18, 2026Jiaxiao Xu, Changhong Mou, Yeyu Zhang +1Fourier Neural Operator OOD Generalization
Shanghai University of Finance and Economics · Utah State University · University of Edinburgh
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
May 16, 2026Yangyou Liu, Zezhi Shao, Xinyu Chen +3OOD Generalization Time Series Generation
College of Computer Science, Sichuan University, Chengdu, China · Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · Institute of Artificial Intelligence, University of Central Florida, Orlando, USA +1
A numerical study into neural network surrogate model performance for uncertainty propagation
May 15, 2026Noah Wade, Kirubel TeferraNeural Surrogate Modeling Uncertainty Quantification
ASEE Postdoctoral Associate, U.S. Naval Research Laboratory, Washington, DC, 20375, USA · U.S. Naval Research Laboratory, Washington, 20375, DC, USA
XSearch: Explainable Code Search via Concept-to-Code Alignment
May 15, 2026Yiming Liu, Ruofan Liu, Yun Lin +7OOD Generalization Information Retrieval
Shanghai Jiao Tong University, China · Shanghai Innovation Institute, China · National University of Singapore, Singapore +3
Continual Learning of Domain-Invariant Representations
May 15, 2026Pascal Janetzky, Tobias Schlagenhauf, Stefan FeuerriegelOOD Generalization Cross-Domain Generalization
LMU Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany · Bosch Center for Artificial Intelligence, Renningen, Germany +1
Learning Direct Control Policies with Flow Matching for Autonomous Driving
May 14, 2026Marcello Ceresini, Federico Pirazzoli, Andrea Bertogalli +5Flow Matching End-to-End Autonomous Driving
1Università degli Studi di Parma · 2Alma Mater Studiorum - Università di Bologna · 3VisLab (an Ambarella Inc. company)

May 28, 2026, cs.CVJ/K move · Enter open · S save

EarthShift: a benchmark for measuring robustness to real-world distribution shifts in Earth observation

Kelsey Doerksen, Hannah Kerner

School of Computing and Augmented Intelligence Arizona State University

Distribution Shift Robustness Geospatial Foundation Models OOD Generalization Remote Sensing Remote Sensing Benchmarks

Open paper AskPDF arXiv

Current Earth observation benchmarks focus on measuring performance on diverse tasks and applications, typically measuring generalization in-distribution. But when models are deployed, they must generalize to myriad out-of-distribution scenarios, such as new time periods, geographies, scales, and sensors. We introduce EarthShift: the first public testbed for benchmarking robustness across multiple realistic distribution shifts encountered in remote sensing. EarthShift enables users to measure distributional robustness by comparing performance in- and out-of-distribution using datasets from paired datasets from different sources, temporal windows, geographic locations, and sensors. Our experiments on 8 geospatial foundation models (GFMs) and 11 tasks covering 5 shift types show that GFMs consistently perform 15-20% worse out-of-distribution on average regardless of model architecture, size, pre-training or fine-tuning strategy. We show that GFM robustness is similar to that of generic vision foundation models, and even fully-supervised models. This highlights a need for future research to strive for improvements in distributional robustness, not just performance, which can be benchmarked using EarthShift. We release our code and datasets to provide a testbed to guide future work to create foundation models that are robust and reliable in real-world applications. Code and data for EarthShift are available at: https://earthshift.github.io

Momentum

Related topics

Latest papers 261