OOD Generalization

OOD: Out-of-Distribution

Follow this topic Ask about this topic

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

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

Feb 23, 2026

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

The rapid advancement of generative models has made the detection of AI-generated images a critical challenge for both research and society. Recent works have shown that most state-of-the-art fake image detection methods overfit to their training data and catastrophically fail when evaluated on curated hard test sets with strong distribution shifts. In this work, we argue that it is more principled to learn a tight decision boundary around the real image distribution and treat the fake category as a sink class. To this end, we propose SimLBR, a simple and efficient framework for fake image detection using Latent Blending Regularization (LBR). Our method significantly improves cross-generator generalization, achieving up to +24.85% accuracy and +69.62% recall on the challenging Chameleon benchmark. SimLBR is also highly efficient, training orders of magnitude faster than existing approaches. Furthermore, we emphasize the need for reliability-oriented evaluation in fake image detection, introducing risk-adjusted metrics and worst-case estimates to better assess model robustness. All code and models will be released on HuggingFace and GitHub.

Aayush Dhakal, Subash Khanal, Srikumar Sastry +4

Washington University in St. Louis · Oak Ridge National Laboratory

AI-Generated Image Detection OOD Generalization One-Class Classification

Feb 23, 2026

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

Meta-learning methods perform well on new within-distribution tasks but often fail when adapting to out-of-distribution target tasks, where transfer from source tasks can induce negative transfer. We propose a causally-aware Bayesian meta-learning method, by conditioning task-specific priors on precomputed latent causal task embeddings, enabling transfer based on mechanistic similarity rather than spurious correlations. Our approach explicitly considers realistic deployment settings where access to target-task data is limited, and adaptation relies on noisy (expert-provided) pairwise judgments of causal similarity between source and target tasks. We provide a theoretical analysis showing that conditioning on causal embeddings controls prior mismatch and mitigates negative transfer under task shift. Empirically, we demonstrate reductions in negative transfer and improved out-of-distribution adaptation in both controlled simulations and a large-scale real-world clinical prediction setting for cross-disease transfer, where causal embeddings align with underlying clinical mechanisms.

Lotta Mäkinen, Jorge Loría, Samuel Kaski

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

Meta-Learning OOD Generalization Cross-Domain Transfer Learning

Feb 23, 2026

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

Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges: (1) most models suffer from exponentially increasing computational complexity, making it difficult to scale to large graphs; (2) attention mechanisms based on node-level operations limit the flexibility of the model and result in poor generalization performance in out-of-distribution (OOD) scenarios. To address these issues, we propose VecFormer (the Vector Quantized Graph Transformer), an efficient and highly generalizable model for node classification, particularly under OOD settings. VecFormer adopts a two-stage training paradigm. In the first stage, two codebooks are used to reconstruct the node features and the graph structure, aiming to learn the rich semantic Graph Codes. In the second stage, attention mechanisms are performed at the Graph Token level based on the transformed cross codebook, reducing computational complexity while enhancing the model's generalization capability. Extensive experiments on datasets of various sizes demonstrate that VecFormer outperforms the existing Graph Transformer in both performance and speed.

Jingbo Zhou, Jun Xia, Siyuan Li +11

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

Graph Transformer Node Classification OOD Generalization

Feb 22, 2026

Spiking Graph Predictive Coding for Reliable OOD Generalization

Graphs provide a powerful basis for modeling Web-based relational data, with expressive GNNs to support the effective learning in dynamic web environments. However, real-world deployment is hindered by pervasive out-of-distribution (OOD) shifts, where evolving user activity and changing content semantics alter feature distributions and labeling criteria. These shifts often lead to unstable or overconfident predictions, undermining the trustworthiness required for Web4Good applications. Achieving reliable OOD generalization demands principled and interpretable uncertainty estimation; however, existing methods are largely post-hoc, insensitive to distribution shifts, and unable to explain where uncertainty arises especially in high-stakes settings. To address these limitations, we introduce SpIking GrapH predicTive coding (SIGHT), an uncertainty-aware plug-in graph learning module for reliable OOD Generalization. SIGHT performs iterative, error-driven correction over spiking graph states, enabling models to expose internal mismatch signals that reveal where predictions become unreliable. Across multiple graph benchmarks and diverse OOD scenarios, SIGHT consistently enhances predictive accuracy, uncertainty estimation, and interpretability when integrated with GNNs.

Jing Ren, Jiapeng Du, Bowen Li +6

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

OOD Generalization Graph Neural Networks Spiking Neural Networks

Feb 22, 2026

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

Unified Speech Recognition (USR) has emerged as a semi-supervised framework for training a single model for audio, visual, and audiovisual speech recognition, achieving state-of-the-art results on in-distribution benchmarks. However, its reliance on autoregressive pseudo-labelling makes training expensive, while its decoupled supervision of CTC and attention branches increases susceptibility to self-reinforcing errors, particularly under distribution shifts involving longer sequences, noise, or unseen domains. We propose CTC-driven teacher forcing, where greedily decoded CTC pseudo-labels are fed into the decoder to generate attention targets in a single forward pass. Although these can be globally incoherent, in the pseudo-labelling setting they enable efficient and effective knowledge transfer. Because CTC and CTC-driven attention pseudo-labels have the same length, the decoder can predict both simultaneously, benefiting from the robustness of CTC and the expressiveness of attention without costly beam search. We further propose mixed sampling to mitigate the exposure bias of the decoder relying solely on CTC inputs. The resulting method, USR 2.0, halves training time, improves robustness to out-of-distribution inputs, and achieves state-of-the-art results on LRS3, LRS2, and WildVSR, surpassing USR and modality-specific self-supervised baselines.

Alexandros Haliassos, Rodrigo Mira, Stavros Petridis

NatWest AI Research · Imperial College London

Connectionist Temporal Classification Automatic Speech Recognition Audio-Visual Speech Recognition Pseudo-Labeling OOD Generalization

Feb 21, 2026

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

Millimeter-wave Human Pose Estimation (mmWave HPE) promises privacy but suffers from poor generalization under distribution shifts. We demonstrate that brute-force data scaling is ineffective for out-of-distribution (OOD) robustness; efficiency and coverage are the true bottlenecks. To address this, we introduce WiCompass, a coverage-aware data-collection framework. WiCompass leverages large-scale motion-capture corpora to build a universal pose space ``oracle'' that quantifies dataset redundancy and identifies underrepresented motions. Guided by this oracle, WiCompass employs a closed-loop policy to prioritize collecting informative missing samples. Experiments show that WiCompass consistently improves OOD accuracy at matched budgets and exhibits superior scaling behavior compared to conventional collection strategies. By shifting focus from brute-force scaling to coverage-aware data acquisition, this work offers a practical path toward robust mmWave sensing.

Bo Liang, Chen Gong, Haobo Wang +8

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

Human Pose Estimation OOD Generalization mmWave Radar Sensing Data-Efficient Learning

Feb 20, 2026

Latent Equivariant Operators for Robust Object Recognition: Promises and Challenges

Despite the successes of deep learning in computer vision, difficulties persist in recognizing objects that have undergone group-symmetric transformations rarely seen during training

\unicode{x2013}

for example objects seen in unusual poses, scales, positions, or combinations thereof. Equivariant neural networks are a solution to the problem of generalizing across symmetric transformations, but require knowledge of transformations a priori. An alternative family of architectures proposes to learn equivariant operators in a latent space, from examples of symmetric transformations. Here, using simple datasets of rotated and translated noisy MNIST, we illustrate how such architectures can successfully be harnessed for out-of-distribution classification, thus overcoming the limitations of both traditional and equivariant networks. While conceptually enticing, we discuss challenges ahead on the path of scaling these architectures to more complex datasets. Our code is available at https://github.com/BRAIN-Aalto/equivariant_operator.

Minh Dinh, Stéphane Deny

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

Equivariant Neural Networks Image Classification Operator Learning OOD Generalization

Feb 20, 2026

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

Accurately modeling the spatio-temporal dynamics of blast wave propagation remains a longstanding challenge due to its highly nonlinear behavior, sharp gradients, and burdensome computational cost. While machine learning-based surrogate models offer fast inference as a promising alternative, they suffer from degraded accuracy, particularly evaluated on complex urban layouts or out-of-distribution scenarios. Moreover, autoregressive prediction strategies in such models are prone to error accumulation over long forecasting horizons, limiting their robustness for extended-time simulations. To address these limitations, we propose RGD-Blast, a robust and generalizable deep surrogate model for high-fidelity, long-term blast wave forecasting. RGD-Blast incorporates a multi-scale module to capture both global flow patterns and local boundary interactions, effectively mitigating error accumulation during autoregressive prediction. We introduce a dynamic-static feature coupling mechanism that fuses time-varying pressure fields with static source and layout features, thereby enhancing out-of-distribution generalization. Experiments demonstrate that RGD-Blast achieves a two-order-of-magnitude speedup over traditional numerical methods while maintaining comparable accuracy. In generalization tests on unseen building layouts, the model achieves an average RMSE below 0.01 and an R2 exceeding 0.89 over 280 consecutive time steps. Additional evaluations under varying blast source locations and explosive charge weights further validate its generalization, substantially advancing the state of the art in long-term blast wave modeling.

Danning Jing, Xinhai Chen, Xifeng Pu +5

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

Neural Surrogate Modeling Spatiotemporal Forecasting PDE Surrogate Modeling Computational Fluid Dynamics OOD Generalization

Feb 20, 2026

Rethinking Beam Management: Generalization Limits Under Hardware Heterogeneity

Hardware heterogeneity across diverse user devices poses new challenges for beam-based communication in 5G and beyond. This heterogeneity limits the applicability of machine learning (ML)-based algorithms. This article highlights the critical need to treat hardware heterogeneity as a first-class design concern in ML-aided beam management. We analyze key failure modes in the presence of heterogeneity and present case studies demonstrating their performance impact. Finally, we discuss potential strategies to improve generalization in beam management.

Nikita Zeulin, Olga Galinina, Ibrahim Kilinc +2

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

Wireless Communications OOD Generalization Wireless Resource Allocation

Feb 20, 2026

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

Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID). However, in real-world scenarios, it is often impractical to expect that all data processed by an AI system satisfy this assumption. Furthermore, failure to appropriately handle out-of-distribution (OOD) objects may introduce safety risks in real-world applications (e.g., autonomous driving or medical assistance). Unfortunately, current research has not yet provided valid benchmarks that can comprehensively assess the performance of VLMs in response to OOD data. Therefore, we propose OODBench, a predominantly automated method with minimal human verification, for constructing new benchmarks and evaluating the ability of VLMs to process OOD data. OODBench contains 40K instance-level OOD instance-category pairs, and we show that current VLMs still exhibit notable performance degradation on OODBench, even when the underlying image categories are common. In addition, we propose a reliable automated assessment metric that employs a Basic-to-Advanced Progression of prompted questions to assess the impact of OOD data on questions of varying difficulty more fully. Lastly, we summarize substantial findings and insights to facilitate future research in the acquisition and evaluation of OOD data.

Ling Lin, Yang Bai, Heng Su +5

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

VLM Evaluation VLM Robustness OOD Generalization Large Vision-Language Models

Feb 20, 2026

Causal Neighbourhood Learning for Invariant Graph Representations

Graph data often contain noisy and spurious correlations that mask the true causal relationships, which are essential for enabling graph models to make predictions based on the underlying causal structure of the data. Dependence on spurious connections makes it challenging for traditional Graph Neural Networks (GNNs) to generalize effectively across different graphs. Furthermore, traditional aggregation methods tend to amplify these spurious patterns, limiting model robustness under distribution shifts. To address these issues, we propose Causal Neighbourhood Learning with Graph Neural Networks (CNL-GNN), a novel framework that performs causal interventions on graph structure. CNL-GNN effectively identifies and preserves causally relevant connections and reduces spurious influences through the generation of counterfactual neighbourhoods and adaptive edge perturbation guided by learnable importance masking and an attention-based mechanism. In addition, by combining structural-level interventions with the disentanglement of causal features from confounding factors, the model learns invariant node representations that are robust and generalize well across different graph structures. Our approach improves causal graph learning beyond traditional feature-based methods, resulting in a robust classification model. Extensive experiments on four publicly available datasets, including multiple domain variants of one dataset, demonstrate that CNL-GNN outperforms state-of-the-art GNN models.

Simi Job, Xiaohui Tao, Taotao Cai +2

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

Graph Representation Learning Causal Representation Learning OOD Generalization Graph Structure Learning Causal Inference

Feb 19, 2026

Anti-causal domain generalization: Leveraging unlabeled data

The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training environments, limiting their applicability when labeled data are scarce. In this work, we study domain generalization in an anti-causal setting, where the outcome causes the observed covariates. Under this structure, environment perturbations that affect the covariates do not propagate to the outcome, which motivates regularizing the model's sensitivity to these perturbations. Crucially, estimating these perturbation directions does not require labels, enabling us to leverage unlabeled data from multiple environments. We propose two methods that penalize the model's sensitivity to variations in the mean and covariance of the covariates across environments, respectively, and prove that these methods have worst-case optimality guarantees under certain classes of environments. Finally, we demonstrate the empirical performance of our approach on a controlled physical system and a physiological signal dataset.

Sorawit Saengkyongam, Juan L. Gamella, Andrew C. Miller +3

Apple · ETH Zürich

Domain Generalization OOD Generalization

Feb 18, 2026

Omitted Variable Bias in Language Models Under Distribution Shift

Despite their impressive performance on a wide variety of tasks, modern language models remain susceptible to distribution shifts, exhibiting brittle behavior when evaluated on data that differs in distribution from their training data. In this paper, we describe how distribution shifts in language models can be separated into observable and unobservable components, and we discuss how established approaches for dealing with distribution shift address only the former. Importantly, we identify that the resulting omitted variable bias from unobserved variables can compromise both evaluation and optimization in language models. To address this challenge, we introduce a framework that maps the strength of the omitted variables to bounds on the worst-case generalization performance of language models under distribution shift. In empirical experiments, we show that using these bounds directly in language model evaluation and optimization provides more principled measures of out-of-distribution performance, improves true out-of-distribution performance relative to standard distribution shift adjustment methods, and further enables inference about the strength of the omitted variables when target distribution labels are available.

Victoria Lin, Louis-Philippe Morency, Eli Ben-Michael

Carnegie Mellon University, Pittsburgh, PA, USA

OOD Generalization Generalization Bounds Model Misspecification

Feb 18, 2026

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

Single-cell RNA sequencing (scRNA-seq) data exhibit strong and reproducible statistical structure. This has motivated the development of large-scale foundation models, such as TranscriptFormer, that use transformer-based architectures to learn a generative model for gene expression by embedding genes into a latent vector space. These embeddings have been used to obtain state-of-the-art (SOTA) performance on downstream tasks such as cell-type classification, disease-state prediction, and cross-species learning. Here, we ask whether similar performance can be achieved without utilizing computationally intensive deep learning-based representations. Using simple, interpretable pipelines that rely on careful normalization and linear methods, we obtain SOTA or near SOTA performance across multiple benchmarks commonly used to evaluate single-cell foundation models, including outperforming foundation models on out-of-distribution tasks involving novel cell types and organisms absent from the training data. Our findings highlight the need for rigorous benchmarking and suggest that the biology of cell identity can be captured by simple linear representations of single cell gene expression data.

Huan Souza, Pankaj Mehta

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

Single-Cell RNA Sequencing Linear Representation Hypothesis OOD Generalization

Feb 17, 2026

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

Machine learning surrogates are increasingly used in engineering to accelerate costly simulations, yet distribution shifts between training and deployment often cause severe performance degradation (e.g., unseen geometries or configurations). Test-Time Adaptation (TTA) can mitigate such shifts, but existing methods are largely developed for lower-dimensional classification with structured outputs and visually aligned input-output relationships, making them unstable for the high-dimensional, unstructured and regression problems common in simulation. We address this challenge by proposing a TTA framework based on storing maximally informative (D-optimal) statistics, which jointly enables stable adaptation and principled parameter selection at test time. When applied to pretrained simulation surrogates, our method yields up to 7% out-of-distribution improvements at negligible computational cost. To the best of our knowledge, this is the first systematic demonstration of effective TTA for high-dimensional simulation regression and generative design optimization, validated on the SIMSHIFT and EngiBench benchmarks.

Anna Zimmel, Paul Setinek, Gianluca Galletti +2

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

Test-Time Adaptation OOD Generalization Distribution Shift Surrogate Modeling

Feb 17, 2026

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

Integrating reasoning in large language models and large vision-language models has recently led to significant improvement of their capabilities. However, the generalization of reasoning models is still vaguely defined and poorly understood. In this work, we present an evaluation framework to rigorously examine how well chain-of-thought (CoT) approaches generalize on a simple planning task. Specifically, we consider a grid-based navigation task in which a model is provided with a map and must output a sequence of moves that guides a player from a start position to a goal while avoiding obstacles. The versatility of the task and its data allows us to fine-tune model variants using different input representations (visual and textual) and CoT reasoning strategies, and systematically evaluate them under both in-distribution (ID) and out-of-distribution (OOD) test conditions. Our experiments show that, while CoT reasoning improves in-distribution generalization across all representations, out-of-distribution generalization (e.g., to larger maps) remains very limited in most cases when controlling for trivial matches with the ID data. Surprisingly, we find that reasoning traces which combine multiple text formats yield the best (and non-trivial) OOD generalization. Finally, purely text-based models consistently outperform those utilizing image-based inputs, including a recently proposed approach relying on latent space reasoning.

Yannic Neuhaus, Nicolas Flammarion, Matthias Hein +1

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

OOD Generalization Multimodal Reasoning VLM Reasoning Multimodal CoT Reasoning

Feb 16, 2026

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

Recent advances in scientific machine learning (SciML) have enabled neural operators (NOs) to serve as powerful surrogates for modeling the dynamic evolution of physical systems governed by partial differential equations (PDEs). While existing approaches focus primarily on learning simulations from the target PDE, they often overlook more fundamental physical principles underlying these equations. Inspired by how numerical solvers are compatible with simulations of different settings of PDEs, we propose a multiphysics training framework that jointly learns from both the original PDEs and their simplified basic forms. Our framework enhances data efficiency, reduces predictive errors, and improves out-of-distribution (OOD) generalization, particularly in scenarios involving shifts of physical parameters and synthetic-to-real transfer. Our method is architecture-agnostic and demonstrates consistent improvements in normalized root mean square error (nRMSE) across a wide range of 1D/2D/3D PDE problems. Through extensive experiments, we show that explicit incorporation of fundamental physics knowledge significantly strengthens the generalization ability of neural operators. We will release models and codes at https://sites.google.com/view/sciml-fundemental-pde.

Siying Ma, Mehrdad M. Zadeh, Mauricio Soroco +3

Simon Fraser University · Georgia Institute of Technology

PDE Surrogate Modeling Neural Operators Physics-Informed Neural Operators Data-Efficient Learning OOD Generalization

Jan 24, 2026

A Constrained Optimization Perspective of Unrolled Transformers

We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints on the objective function and replace standard empirical risk minimization (ERM) with a primal-dual training scheme. This approach yields models whose intermediate representations decrease the loss monotonically in expectation across layers. We apply our method to both unrolled transformer architectures and conventional pretrained transformers on tasks of video denoising and text classification. Across these settings, we observe constrained transformers achieve stronger robustness to perturbations and maintain higher out-of-distribution generalization, while preserving in-distribution performance.

Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro

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

Deep Learning Optimization Transformer OOD Generalization Constrained Optimization

Dec 3, 2025

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

Vision-language models (VLMs) are increasingly integrated into clinical workflows. However, existing benchmarks primarily assess performance on common anatomical presentations and fail to capture the challenges posed by rare variants. To address this gap, we introduce AdversarialAnatomyBench, the first benchmark comprising naturally occurring rare anatomical variants across diverse imaging modalities and anatomical regions. We call such variants that violate learned priors about "typical" human anatomy natural adversarial anatomy. Benchmarking 25 state-of-the-art VLMs with AdversarialAnatomyBench yielded three key insights. First, when queried with basic medical perception tasks, mean accuracy dropped from 71% on typical to 28% on atypical anatomy. Even the best-performing models, GPT-5, Gemini 2.5 Pro, and Llama 4 Maverick, showed performance drops of 41-51%. Second, model errors closely mirrored expected anatomical biases. Third, neither model scaling nor interventions, including bias-aware prompting and test-time reasoning, resolved these issues. These findings highlight a critical limitation in current VLMs: their poor generalization to rare anatomical presentations. AdversarialAnatomyBench provides a foundation for systematically measuring and mitigating anatomical bias in multimodal medical artificial intelligence (AI) systems.

Leon Mayer, Piotr Kalinowski, Caroline Ebersbach +6

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

VLM Evaluation VLM Robustness Healthcare OOD Generalization Medical VLMs Medical Image Benchmarks

Nov 27, 2025

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

Invariant learning on graphs aims to build predictors that rely on causal substructures rather than on environment-specific shortcuts. Current methods extract either a single invariant subgraph (CIGA) or, more recently, a set of diverse invariant subgraphs (SuGAr). We observe that the second half of the multi-subgraph pipeline, "how the extracted subgraphs are combined" has gone essentially unexamined; existing methods average branch predictions uniformly or select one greedily. We show that this is precisely where accuracy is lost. A minimum-variance combination argument establishes that uniform averaging is optimal only when every branch carries the same total error covariance with the ensemble---a knife edge balance that second order exchangeability guarantees and that the diversity regularizer used to obtain multiple subgraphs is explicitly designed to break. We then show that invariance is closed under post composition; because the branches are frozen and read the graph only through their invariant subgraphs, any measurable aggregator of their outputs remains invariant, and the aggregate's environment gap is bounded by the branches' residual invariance violation uniformly over aggregators. Learning the combination rule by plain empirical risk minimization is therefore safe, and aggregator capacity trades off against estimation error rather than robustness. PISA instantiates this with a lightweight instance-conditional MLP over stacked branch logits, trained on frozen branches at negligible cost. Across 15 synthetic and real benchmarks, PISA improves the average over the strongest prior method by 2.96 points on synthetic shifts and 1.74 points on realistic shifts, with per-dataset gains up to 5.90 points, and nearly doubles SuGAr's improvement over ERM on the six DrugOOD tasks (from +2.76 to +5.07 ROC-AUC).

Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli +1

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

OOD Generalization Invariant Representation Learning Ensemble Learning

Nov 15, 2025

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

Current visual models often make predictions based on a limited set of discriminative visual cues. As a result, they may become unreliable when the distribution shifts or when these cues are missing. Faithful attribution methods can reveal such problematic reliance through localized explanations, but they are typically used post hoc and are not fed back into the model. To address this limitation, we propose Subset-Selected Counterfactual Augmentation (SS-CA), a training strategy that masks decision-relevant regions to construct counterfactual samples and guide the model toward more robust decision boundaries. Specifically, we extend LIMA, a subset-selection-based faithful attribution method, to Counterfactual LIMA to identify regions whose removal shifts the model toward a competing class. SS-CA then selects near-boundary masks that reduce the logit gap while preserving the original semantics, and applies an adaptive counterfactual filling strategy to replace the masked regions without introducing external semantics. Feeding these counterfactual samples back into training encourages the model to exploit the remaining informative evidence and shifts the decision boundary toward a more robust one. Extensive experiments across five ImageNet variants show that SS-CA effectively improves ID accuracy, OOD generalization, and perturbation robustness, achieving gains of 5.70%/18.04% on ImageNet-1k/ImageNet-R with CLIP ViT/32b, 9.52%/11.33% on ImageNet-R/ImageNet-S on TinyImageNet-200 with ResNet-101, and about 4% under Gaussian Noise corruption. The code will be released soon.

Yannan Chen, Ruoyu Chen, Wei Wang +6

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

Adversarial Robustness OOD Generalization Counterfactual Data Augmentation Counterfactual Learning

Nov 14, 2025

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

Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision, especially in unsupervised domain adaptation scenarios, where shifts in image background, style, and acquisition instruments often degrade model performance. Generic augmentations show inconsistent gains under such shifts, whereas dataset-specific augmentations require expert knowledge and prior analysis. Moreover, prior studies show that neural networks adapt poorly to domain shifts because they exhibit a learning bias to domain-specific frequency components. Perturbing frequency values can mitigate such bias but overlooks pixel-level details, leading to suboptimal performance. To address these limitations, we propose D-GAP, a Dataset-agnostic and Gradient-guided augmentation method for the Amplitude spectrum (in frequency space) and the Pixel values. Unlike conventional handcrafted augmentations, D-GAP computes sensitivity maps in the frequency space from task gradients, which reflect how strongly the deep models respond to different frequency components, and uses the maps to adaptively interpolate amplitudes between source and target samples. We further propose a dual-space augmentation that jointly controls spectral bias and spatial fidelity by introducing a complementary pixel-space blending branch. This way, D-GAP turns augmentation from fixed, random, or manually designed perturbation into a model-response-adaptive intervention. Extensive experimental results show that the proposed method consistently outperforms both generic and dataset-specific domain adaptation methods, improving average OOD performance by +5.3% on four real-world datasets and +1.9% on three benchmark datasets. Code is available at https://github.com/RapidsAtHKUST/D-GAP.

Ruoqi Wang, Haitao Wang, Shaojie Guo +1

HKUST(GZ) · SYSU · ECNU +1

Unsupervised Domain Adaptation Data Augmentation OOD Generalization

Oct 8, 2025

Robust and Efficient Finetuning of Vision Foundation Models via Implicit Ensembling

Robust finetuning of foundation models seeks to improve out-of-distribution (OOD) generalization during in-distribution (ID) adaptation. We revisit Mixout, a stochastic regularizer that intermittently replaces finetuned parameters with a reference anchor, and study its effectiveness for robust finetuning of vision foundation models. We reinterpret Mixout as a single-run, weight-sharing implicit ensemble and analyze its expected OOD error through a bias-variance-covariance-locality (BVCL) lens. This perspective reveals three key factors that govern the ID-OOD trade-off: the choice of masking anchor, the mask resampling frequency, and mask sparsity. Guided by this analysis, we propose GMixout, which generalizes Mixout in three ways. First, it explicitly controls the masking period through a resampling-frequency hyperparameter. Second, it replaces the fixed pretrained anchor with an exponential moving average snapshot that adapts throughout training. Third, it uses sparse kernels to update only a small subset of parameters at each iteration, introducing no inference-time overhead and enabling large-model finetuning on consumer-grade GPUs. Experiments across five vision benchmarks show that GMixout consistently outperforms Mixout, Model Soups, and strong parameter-efficient finetuning baselines under both covariate shift and class imbalance.

Masih Aminbeidokhti, Heitor Rapela Medeiros, Eric Granger +1

Vision Foundation Model Adaptation OOD Generalization Ensemble Learning Parameter-Efficient Fine-Tuning

Oct 5, 2025

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

Quantum error correction (QEC) is essential for scalable quantum computing, yet decoding errors via conventional algorithms result in limited accuracy (i.e., suppression of logical errors) and high overheads, both of which can be alleviated by inference-based decoders. To date, such machine-learning (ML) decoders lack two key properties crucial for practical fault tolerance: reliable uncertainty quantification and robust generalization to previously unseen QEC codes. To address this gap, we propose a Quantum Bayesian graph Attention decoder (QuBA) that enables expressive error-pattern recognition alongside calibrated uncertainty estimates. Building on QuBA, we further develop a multi-phase training framework with enhanced cross-domain robustness enabling decoding beyond the training set called Sequential Aggregate Generalization under Uncertainty (SAGU). Experiments on bivariate bicycle (BB) codes and their coprime variants demonstrate that (i)QuBA consistently outperforms the classical baseline belief propagation (BP), achieving up to a two orders of magnitude reduction in logical error rate (LER) under confident-decision bounds on the coprime BB code

[[154,6,16]]

; (ii) SAGU achieves decoding performance comparable to or even outperforming QuBA's domain-specific training approach.

Xiangjun Mi, Frank Mueller

North Carolina State University, Raleigh, NC 27695, USA

Quantum LDPC Codes Quantum Error Correction Decoding OOD Generalization Uncertainty Quantification Graph Neural Networks

Oct 1, 2025

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

The factors driving the performance of in-context learning (ICL) in large language models (LLMs) remain poorly understood despite ICL's surprising effectiveness, enabling models to adapt to new tasks from only a handful of examples. To clarify and improve these capabilities, we characterize how the statistical properties of the pretraining distribution (e.g., tail behavior, coverage) shape ICL. We develop a theoretical framework that encompasses generalization and task selection and show how distributional properties govern sample efficiency, task retrieval, and robustness. To this end, we generalize existing concentration results to heavy-tailed priors and dependent sequences, better reflecting the structure of LLM pretraining data. Our framework reveals a fundamental design trade-off: heavy-tailed pretraining distributions facilitate robust task selection under distribution shifts but are detrimental to generalization, especially in low-data regimes. We then empirically evaluate our predictions by studying how ICL performance varies with the pretraining distribution on challenging tasks such as stochastic differential equations and stochastic processes with memory. Together, these findings suggest that controlling key statistical properties of the pretraining distribution is essential for building ICL-capable and reliable LLMs.

Waïss Azizian, Ali Hasan

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

Language Model Pretraining OOD Generalization In-Context Learning Heavy-Tailed Distributions

Sep 29, 2025

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

Large Language Models (LLMs) excel at multi-hop reasoning in distribution, yet fail on unseen compositions, a phenomenon known as the curse of two-hop reasoning. In this work, we argue that this phenomenon can be attributed to a missing supervision on the bridge entity. We formalize this gap by introducing identity bridge, a minimal supervision that enforces a identity mapping on bridge tokens. Under this supervision, even a one-layer transformer with uniform attention (Emb-MLP) can achieve out-of-distribution (OOD) two-hop generalization. We provide a theoretical analysis demonstrating that identity bridge induces an implicit regularization effect, leading the model to establish a direct subject-to-answer association. From an empirical perspective, the performance of standard GPT-2 models aligns closely with simple Emb--MLP models across varying levels of problem complexity. Finally, analyses of fine-tuned mainstream LLMs indicate that correct two-hop predictions consistently coincide with the establishment of a subject-to-answer relationship, extending our findings to realistic settings.

Pengxiao Lin, Zheng-An Chen, Zhi-Qin John Xu

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.

Transformer Interpretability OOD Generalization Multi-Hop Reasoning Compositional Generalization

Sep 18, 2025

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

Recent advances in pre-training vision-language models (VLMs), e.g., contrastive language-image pre-training (CLIP) methods, have shown great potential in learning out-of-distribution (OOD) representations. Despite showing competitive performance, the prompt-based CLIP methods still suffer from: i) inaccurate text descriptions, which leads to degraded accuracy and robustness, and poses a challenge for zero-shot CLIP methods. ii) limited vision-language embedding alignment, which is one important factor affecting generalization performance. To tackle the above issues, this paper proposes a novel Conditional Domain prompt Learning (CoDoL) method, which utilizes readily-available domain information to form prompts and contributes to improved vision-language embedding alignment, which we identify as one factor underlying the observed OOD generalization gains. To capture both instance-specific and domain-specific information, we further propose a lightweight Domain Meta Network (DMN) to generate input-conditional tokens for images in each domain. Extensive experiments on four OOD benchmarks (PACS, VLCS, OfficeHome, and DigitDG) validate the effectiveness of our proposed CoDoL method in terms of empirically improves vision-language embedding alignment across four DG benchmarks, which we present as a contributing factor (rather than the sole cause) of the observed OOD gains.

Min Zhang, Yuyin Wang, Zhongxiang Dai +4

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

VLM Adaptation Domain Generalization OOD Generalization Vision-Language Alignment Visual Prompt Learning

Aug 31, 2025

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

Transformers often transfer across related tasks with little fine-tuning; we study this question in noisy nonparametric regression for continuous maps

f,g:[0,1]^d\to\mathbb{R}^D

, representing the source and shifted tasks, using a single-query, single-head transformer

\mathcal{T}(\cdot)=V\operatorname{Softmax}(-α(\cdot,K))

with

\ell^{\infty}

-based alignment scores

α

. Rather than assume that gradient-based training reaches an empirical risk minimizer, we give a model-specific two-stage procedure certifying source-task recovery and out-of-distribution (OOD) adaptation. With high probability, the resulting attention head recovers

f

to arbitrary accuracy

\varepsilon>0

in every fixed

L^p([0,1]^d)

norm,

1\le p<\infty

, from noisy observations. For Lipschitz targets, its rate is minimax-optimal up to logarithmic factors without assuming oracle access to an asymptotic ERM. If

D=1

and

f

is Pfaffian than the values matrix factors into

AC

with

A

scaling at-most linearly

\mathcal{O}(\varepsilon^{-1})

in the reciprocal approximation error

\varepsilon>0

. Importantly, our training procedure encodes all our identified (potentially) shared geometric structure from

f

only into the values matrix factor

C

and the keys matrix

K

allowing for rapid access, and all

f

-specific structure only into

A

. Our main result concerns the OOD phase; where we identify geometric structures, which if shared by the source

f

and OOD

g

task; then only only the values matrix factor

A

needs to be fine-tuned to guarantee an

L^p

-recovery of

g

. Critically, fine-tuning only

A

is a convex problem which involving an at-most linear number of parameters

\mathcal{O}(\varepsilon^{-1})

; dramatically cutting down on the worst-case scaling of

\mathcal{O}(\varepsilon^{-\mathbf{d}})

unavoidable in the source-training phase.

Anastasis Kratsios, Tin Sum Cheng, Bum Jun Kim +1

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

Fine-Tuning OOD Generalization Transformer Parameter-Efficient Fine-Tuning Nonparametric Regression

Aug 16, 2025

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

Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projections make it possible to embed new, unseen samples without recalculating the entire projection, while invertible projections allow the synthesis of new data instances. However, existing methods perform poorly when dealing with out-of-distribution samples in either the data or embedding space. Thus, we propose DE-VAE, an uncertainty-aware variational AE using differential entropy (DE) to improve the learned parametric and invertible projections. Given a fixed projection, we train DE-VAE to learn a mapping into 2D space and an inverse mapping back to the original space. We conduct quantitative and qualitative evaluations on four well-known datasets, using UMAP and t-SNE as baseline projection methods. Our findings show that DE-VAE can create parametric and inverse projections with comparable accuracy to other current AE-based approaches while enabling the analysis of embedding uncertainty.

Frederik L. Dennig, Daniel A. Keim

University of Konstanz

Variational Autoencoders Uncertainty Quantification OOD Generalization Inverse Dimensionality Reduction Dimensionality Reduction

Aug 8, 2025

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

While graph-based Android malware classifiers report strong benchmark accuracy of over 94%, their performance sharply decreases up to 45% when exposed to previously unseen variants of known malware families. In this work, we systematically investigate this critical yet overlooked challenge for real-world deployment by introducing a benchmarking suite designed to simulate two prevalent scenarios: MalNet-Tiny-Common for covariate shift, and MalNet-Tiny-Distinct for domain shift. We further identify an inherent limitation of existing benchmarks where input representation is limited to structure-only function call graphs, discarding the semantic signals needed for robust cross-distribution reasoning. To verify this, we propose a semantic enrichment framework that extends raw graph topology with function-level attributes, combining lightweight metadata with LLM-based code embeddings. Empirical evaluations confirm the effectiveness of our data-centric methodology, with which classification performs better under distribution shift compared to model-based approaches, and consistently further enhances robustness when used in conjunction. We release our precomputed datasets alongside an extensible pipeline implementation, laying the groundwork for more resilient malware detection systems in evolving threat environments.

Ngoc N. Tran, Anwar Said, Waseem Abbas +2

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

Distribution Shift Robustness Graph Representation Learning OOD Generalization Android Malware Detection Malware Classification Graph Classification+1