OOD Generalization

OOD: Out-of-Distribution

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
View on map

Latest papers 261

All topics
CardsList
Jun 30, 2026cs.CV

Additive Causal Construction for Transferable and Reconfigurable Cross-System Learning in Multi-Source Image Fusion

In multi-source image fusion scenarios, heterogeneous inputs are typically driven by distinct generative mechanisms and can be viewed as a composition of multiple causal systems. However, cross-system discrepancy (CSD) and cross-system entanglement (CSE) commonly arise during the fusion process, often leading to significant performance degradation under out-of-distribution (OOD) predictions. To address the CSD and CSE issues, we propose the additive causal construction (ACC) framework, which characterizes information fusion at two levels: firstly, it establishes causal "anchors" shared among multiple systems through intervention consistency to enable causal graph transferability (CGT); and secondly, it formalizes the fusion process as causal construction and models the reliability of constructed paths through uncertainty quantification to ensure causal graph reconfigurability (CGR). Building upon this, we revisit the traditional causal representation learning (CRL) with ACC and propose ACC-CRL as a learnable instantiation of the framework. The method explores joint causal content representations across systems via content-mechanism decoupling, and performs response alignment under shared anchors to mitigate CSD. Furthermore, it incorporates structural uncertainty to adaptively regulate the fusion process, thereby suppressing unstable CSE. We conduct systematic experiments on synthetic data (ColorMNIST) and real-world multi-center medical imaging tasks (microvascular invasion (MVI) prediction). The results demonstrate that the proposed method significantly improves OOD generalization while maintaining in-distribution (ID) performance, validating the effectiveness and robustness of the ACC-CRL strategy based on mechanism alignment and uncertainty modeling in open environments.

Zhizhong Fu, Wei Zhou, Zhaoyang Jiang +5

School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China. · Department of Radiology, Huzhou Maternity & Child Health Care Hospital, Huzhou 313000, China. · Department of Radiology, Huzhou Maternity & Child Health Care Hospital Affiliated to Huzhou Normal University,Huzhou 313000,China. +3

Multi-Source Image FusionCausal Representation LearningOOD GeneralizationCausal Structure LearningCross-Domain Transfer Learning
AskPDF
Jun 30, 2026cs.CV

Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit

AI-generated video detection benchmarks such as GenVidBench and AIGVDBench are the de facto leaderboards, yet most evaluation protocols leave uncontrolled confounds that can inflate reported generalization. As an existence proof, a three-feature clip-length classifier reaches a leave-one-generator-out (LOGO) AUC of 0.998 on GenVidBench under unaudited evaluation, while measuring nothing about motion. A 20-paper survey finds none applying all six standard controls that would catch this, so we combine them into an audited protocol and apply it to six representative feature sources (three published detectors and three repurposed signal sources), re-running it cross-dataset on AIGVDBench. The audit both debunks and certifies: the trivial classifier collapses to near chance (0.529), a CLIP baseline is caught carrying dataset identity, and the 2025 forensic detector WaveRep clears the floor at out-of-distribution LOGO AUC 0.996 with chance-level real-vs-real coherence. At a deployable FPR of 0.1%, multiple high-AUC methods fall to single-digit recall and the leaderboard order changes, so we recommend an audited tuple (AUC, above-floor margin, operating-point recall, and calibration) over a single number. As a white-box positive control, we add TemporalSpec (codec motion vectors); via cross-substrate feature fusion (XSFF), a second substrate adds genuine complementarity that survives the audit. We release VidAudit, to our knowledge the largest unified and audited detector collection for this task, providing 14 detectors behind one plugin API, a leaderboard, and Croissant metadata, available at https://github.com/KurbanIntelligenceLab/vidaudit. Together, the protocol and toolkit move evaluation from leaderboard rank toward whether a result measures what it claims.

Mert Onur Cakiroglu, Zhihe Lu, Mehmet Dalkilic +1

Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar

Benchmark AuditingOOD GeneralizationDeepfake DetectionGenerative AI Evaluation
AskPDF
Jun 29, 2026cs.LG

Beyond IID: How General Are Tabular Foundation Models, Really?

Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are increasingly evaluating tabular foundation models on diverse datasets and tasks. However, these task- and discipline-specific evaluations remain largely inaccessible to model researchers because benchmark software and evaluation protocols are fragmented. As a result, model researchers rely on standard benchmarks, which are mostly defined for tasks where tabular foundation models already excel. The most challenging scenarios are excluded, limiting meaningful progress in the field by focusing on marginal improvements on IID data rather than on broader, more demanding challenges. To overcome this, we introduce BeyondArena, the first unified holistic benchmark for tabular data that supports diverse task types (IID, temporal, grouped), across sample size and feature dimensionality scales, with diverse feature types (with text, with high cardinality) from a broad range of disciplines. To enable unified benchmarking beyond standard benchmarks, we introduce Data Foundry, a Python framework and metadata schema for curating tabular datasets for predictive machine learning. Our results across 11 models and 142 curated datasets show that existing tabular foundation models excel on tiny- to medium-sized IID data, while traditional tree-based and deep learning models still dominate on non-IID, large, and high-dimensional datasets. BeyondArena guides model research for the most demanding challenges in tabular data, enabling progress towards truly foundational tabular models.

Lennart Purucker, Andrej Tschalzev, Nick Erickson +7

1Prior Labs · University of Mannheim · 4INRIA Saclay +5

Tabular Foundation ModelsOOD GeneralizationTabular MLTabular PredictionCross-Dataset Generalization
AskPDF
Jun 29, 2026cs.LG

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong length generalization beyond the length of training sequences, this behavior is brittle, yielding high out-of-distribution (OOD) variance, even across well-performing in-distribution solutions. We trace this variance to the spurious correlation in simple algorithmic tasks between sequence length and number of loops. Introducing stochasticity into the number of loops during training sharply reduces OOD variance and stabilizes predictions across inference-time loop counts. To improve upon heuristic randomization schemes, we further analyze RL-Halting as a learned stochastic schedule and find that it generally improves the accuracy-stability trade-off. Across binary addition, Dyck-1, Unique Set, and Copy, learned stochastic stopping often improves this trade-off but can also stabilize a suboptimal computation. Our work suggests that "when to stop" should be treated as a training-time design choice, not merely an inference-time computation-allocation rule.

Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger +2

EPFL, Lausanne, Switzerland · Max Planck Institute for Intelligent Systems & ELLIS Institute, Tübingen, Germany

Early StoppingOOD GeneralizationLength GeneralizationRecurrent Transformers
AskPDF
Jun 25, 2026cs.AI

Diagnosing Task Insensitivity in Language Agents

Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key source of this failure as task insensitivity: when faced with similar but distinct tasks, models might apply patterns learned during training and fail to solve the task at hand. We show that models often continue with actions aligned with the original task even when the instruction is semantically corrupted and cannot be directly answered. We further find that, when we replace the task description in a trained prompt with another similar but distinct task, the model may still output the same action. This behavior is accompanied by a consistent training-time attention drift away from task tokens and toward local observations, suggesting an optimization bias toward shortcuts. To mitigate this problem, we propose Task-Perturbed NLL Optimization, a lightweight contrastive regularizer that explicitly encourages action dependence on the task instruction. Extensive evaluations show that our intervention improves task sensitivity and OOD generalization while preserving more stable attention to task tokens.

Jingyu Liu, Xiaopeng Wu, Kehan Chen +2

Gaoling School of Artificial Intelligence Renmin University of China, Beijing, China · Taobao & Tmall Group of Alibaba · Beijing Key Laboratory of Research on Large Models and Intelligent Governance +1

OOD GeneralizationLLM AgentsLanguage Model Robustness
AskPDF
Jun 25, 2026cs.AI

Learning to Recover Task Experts from a Multi-Task Merged Model

Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference. While dynamic merging models aim to bridge this gap, many works rely on the costly storage and loading of redundant expert components at inference. In this work, from the perspective of task expert, we view parameter interference as parameter perturbation introduced to each expert during merging process. We show that such parameter perturbations can be modeled as affine transformation, which can be approximated as additive offsets. Motivated by these, we propose Recover Task eXpert (ReTeX), a framework that predicts those offsets, in order to undo parameter interference and recover task-expert performance from a single merged checkpoint. To recover the appropriate expert when task identity is unknown, we introduce a router-free task identifier based on SVD subspace signatures computed offline before inference. At inference, the identifier selects the task whose subspace yields the smallest projection residual for a given input. As a result, ReTeX recovers over 95% of individual-expert performance in both vision and NLP domains, while significantly improving generalization to unseen tasks. Crucially, we also show that the parameter offset prediction leads to emergent adaptive interpolation of expert knowledge for out-of-distribution (OOD) tasks. ReTeX adaptively interpolates seen expert knowledge to handle unseen tasks. Our code is available at https://github.com/BAIKLAB/ReTeX

Jinwook Jung, Taegyu Kim, Kumju Jo +1

Department of Artificial Intelligence, 2Department of Data Science Hanyang University

OOD GeneralizationMulti-Task LearningModel Merging
AskPDF
Jun 25, 2026cs.LG

Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence

Graph Neural Differential Equations (GNDEs) model continuous-time graph dynamics by parameterizing Neural ODE velocity fields with Graph Neural Networks. Their local, size-independent filters suggest a zero-shot size-transfer principle: train on a small graph and deploy on larger, similar graphs without retraining. We develop a quantitative theory for this principle on sparse random graphs sampled from graphons. We consider Graphon Neural Differential Equations (Graphon-NDEs) and adjoint Graphon-NDEs as the infinite-node limits of the forward and adjoint GNDE systems, and establish well-posedness. For an nn-node random graph with sparsity parameter αnα_n, we prove trajectory-wise convergence of GNDE solutions to Graphon-NDE solutions at rate O((αnn)−1/2)O((α_n n)^{-1/2}), up to logarithmic factors, with high probability. We also establish uniform-in-time convergence bounds for adjoint systems governing hidden-state and parameter gradients. We further study discretize-then-optimize (DTO) and optimize-then-discretize (OTD) training. Under explicit Euler discretization with MM steps, we show that DTO and OTD are asymptotically consistent, with hidden-state and local parameter-gradient discrepancies of orders O(1/M)O(1/M) and O(1/M2)O(1/M^2), respectively, up to sparsity and logarithmic factors. Experiments on HSBM and tent graphons support the theoretical rates, while zero-shot transfer experiments across four graphon classes demonstrate accurate deployment of learned GNDEs on larger independently sampled graphs.

Mingsong Yan, Zhida Wang, Sui Tang

Department of Mathematics, University of California, Santa Barbara, CA.

OOD GeneralizationNeural ODEs
AskPDF
Jun 25, 2026cs.SE

Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs

Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task. Techniques for diagnosing such failures are commonly assessed using within-program cross-validation, which may be inadequate for deployment settings involving previously unseen programs. It is therefore necessary to assess how performance differs across these settings and to identify the causes of any performance gap in established fault diagnosis techniques for DL. We investigate this gap using DynFault, a corpus of 5,542 fault-injected training traces from 38 real-world DL programs. We found a gap of 0.190 in balanced accuracy for existing fault diagnosis techniques between within-program evaluation and holding out whole programs. We also found the gap comes from program-level structure in the features, which led us to examine two runtime feature sets, curvature features and optimizer features, and their behavior on unseen programs. We found that curvature features are useful for instability detection on unseen programs, while optimizer and activation features help only on programs seen during training.

Sigma Jahan

Faculty of Computer Science Dalhousie University, Halifax, Canada

OOD GeneralizationFault Diagnosis
AskPDF
Jun 24, 2026cs.LG

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization

Pre-trained transformers have demonstrated remarkable generalization abilities, at times extending beyond the scope of their training data. Yet, real-world deployments often face unexpected or adversarial data that diverges from training data distributions. Without explicit mechanisms for handling such shifts, model reliability and safety degrade, urging more disciplined study of out-of-distribution (OOD) settings for transformers. By systematic experiments, we present a mechanistic framework for delineating the precise contours of transformer model robustness. We find that OOD inputs, including subtle typos and jailbreak prompts, drive language models to operate on an increased number of fallacious concepts in their internals. We leverage this device to quantify and understand the degree of distributional shift in prompts, enabling a mechanistically grounded fine-tuning strategy to robustify LLMs. Expanding the very notion of OOD from input data to a model's private computational processes, a new transformer diagnostic at inference time is a critical step toward making AI systems safe for deployment across science, business, and government.

Praneet Suresh, Jack Stanley, Sonia Joseph +2

Mila Quebec AI Institute · Meta AI · Sapient Intelligence

Distribution Shift RobustnessTransformer InterpretabilityNeural Network RobustnessOOD GeneralizationAdversarial Robustness of Language Models
AskPDF
Jun 24, 2026cs.CV

TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition

Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generalization. While existing studies pursue this generalization-specialization trade-off with additional regularizations or constraints, we argue that they overlook the deviation of representations beyond the fine-tuning data distribution, resulting in suboptimal adaptation effects. We believe such deviation is inherited from the inconsistency between the fine-tuning and evaluation objectives, where model optimization is restricted to the known training distribution but evaluated on unseen ones. In this paper, we introduce \emph{TACO}, a simple yet effective framework to mitigate the potential negative effects induced by this inconsistency. Our key insight is that adaptation should preserve OOD-relevant alignment beyond the training distribution. To this end, we propose \emph{Relative Structure Distillation}, which regularizes the relative geometry of the representation space and suppresses harmful alignment shift during training. We further decouple the representation space from the optimization space with a lightweight specialization projection, allowing task-specific adaptation without directly overspecializing the representations used at test time. \emph{TACO} establishes state-of-the-art performance on diverse benchmarks under cross-dataset and base-to-novel settings. Code will be released at https://github.com/ZMHH-H/TACO.

Minghao Zhu, Xiao Lin, Mengxian Hu +5

Tongji University, Shanghai, China

VLM AdaptationOOD GeneralizationVideo Action RecognitionVision-Language Alignment
AskPDF
Jun 23, 2026cs.AI

Life After Benchmark Saturation: A Case Study of CORE-Bench

When a benchmark's accuracy saturates, it is often retired and replaced with a more challenging version. We show that this approach privileges accuracy and misses the opportunity to study six other key dimensions of agent performance: construct validity issues such as shortcuts, out-of-distribution generalizability, efficiency, reliability, the relative importance of the model versus the scaffold, and uplift from human-agent collaboration. We use CORE-Bench Hard, a benchmark for computational reproducibility of scientific code, as a case study to demonstrate that measuring agents along these dimensions yields meaningful insights into agent performance even after accuracy saturates. First, we surface threats to construct validity in CORE-Bench Hard that are difficult to anticipate with less capable agents. We introduce an improved benchmark, CORE-Bench v1.1, and an out-of-distribution task suite, CORE-Bench OOD. Second, we find that despite accuracy saturation, CORE-Bench v1.1 remains useful for measuring efficiency, reliability, model performance, and scaffold performance. Finally, we conduct a small-scale randomized experiment to measure uplift from human-agent collaboration on real-world computational reproducibility tasks. We find a statistically significant speedup by about a factor of two -- likely underestimated due to one-fifth of human-only reproductions reaching the time limit before completing -- and describe various other findings. Together, our contributions present a more rigorous alternative to the dominant accuracy-centric evaluation paradigm.

Nitya Nadgir, Sayash Kapoor, Kangheng Liu +11

1Independent · 2Princeton University · 3UC Berkeley +1

OOD GeneralizationAI Agent EvaluationBenchmark ValidityScientific Reproducibility
AskPDF
Jun 23, 2026cs.CL

Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection

Large language models have transformed code generation, raising concerns around authorship, assessment integrity, and software trust. SemEval-2026 Task 13 Subtask A operationalizes detection as binary classification over code snippets, with a particular emphasis on out-of-distribution (OOD) generalization across unseen programming languages and application domains. We propose a SALSA-style formulation, Single-pass Autoregressive LLM Structured Classification, that maps each class to a dedicated output token and trains the model to emit a single-token label in a structured response. Rather than engineering hand-crafted features or decision rules, this formulation delegates the authorship decision to the model. To improve OOD robustness, we combine balanced sampling across languages with parameter-efficient fine-tuning and conservative training (low learning rate, single epoch) to avoid overfitting to the training domain. Our best system achieves OOD F1=0.789F_1 = 0.789 on the official leaderboard, substantially outperforming the CodeBERT baseline (F1=0.305F_1 = 0.305).

Ruslan Berdichevsky, Shai Nahum-Gefen, Elad Ben-Zaken

Dream Security Ltd. Tel Aviv, Israel

OOD GeneralizationCode Language Models
AskPDF
Jun 22, 2026cs.LG

Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate

The task of compositional generation involves using a conditional generative model, trained only on a subset of the possible conditions, to produce samples from compositionally-defined target distributions such as a geometric combination of the source distributions. In this work, we argue that this task is often infeasible for vanilla conditional diffusion models: we conjecture that no inference-time technique can efficiently produce samples from the target distribution in certain well-motivated settings. This idea is supported by theory-guided generalization arguments and carefully-designed experiments on both synthetic and realistic data. In particular, while recent methods such as Feynman-Kac correction reduce inference-time approximation error, our results show that score estimation error has a more catastrophic effect on performance when the target distribution is out-of-distribution with respect to the sources, highlighting the need for a different approach to this task.

Duncan Soiffer, Chandler Squires, Yuan Guan +2

Machine Learning Department, Carnegie Mellon University · Valence Labs · Department of Computer Science, University of Manchester

OOD GeneralizationConditional Diffusion ModelsCompositional Generalization
AskPDF
Jun 22, 2026cs.LG

Topological Out-of-Domain Generalization in Dynamical Systems Reconstruction

Predicting the behavior of dynamical systems (DS) beyond the dynamical and parameter regimes observed in training is a pivotal and essentially unresolved problem in scientific ML. It is central to any good scientific theory, which we expect to be able to make predictions about regimes not covered by currently available data. Recent hierarchical and hyper-network guided approaches for DS reconstruction (DSR) enable training on many DS simultaneously, and revealed that extracted latent features are often related to crucial control parameters of the underlying DS that varied across the training corpus. However, true out-of-domain forecasting abilities of these models, e.g., across tipping points, remain limited, and fine-tuning, or even full model retraining, on time series from the new dynamical regime is usually required. Here, we mathematically analyze the root of these limitations in previous model formulations and identify three core shortcomings rooted in a mismatch between structural assumptions of the reconstruction model and typical properties of physical systems. We propose a combination of remedies for these shortcomings, most importantly feature splitting, and furthermore derive a closed-form bound on the reliable extrapolation range. We demonstrate empirically that our techniques allow for accurate zero-shot prediction into new dynamical regimes, outside the observed training regime, as, e.g., encountered across tipping points.

Georg Trede, Charlotte Ricarda Doll, Elias Weber +1

Dept. of Theoretical Neuroscience, Central Institute of Mental Health, Mannheim, Germany · Faculty of Physics and Astronomy, Heidelberg University, Germany · Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Germany

Dynamical SystemsZero-Shot Time Series ForecastingOOD GeneralizationNonlinear System Identification
AskPDF
Jun 21, 2026cs.RO

FLYNN: Robust Neural Network for Robot Navigation using Fly Brain Topology

While deep learning models achieve state-of-the-art performance in complex tasks, they remain brittle when faced with new environments or sensory deprivation. In contrast, biological systems exhibit remarkable tolerance to these challenges. We address this vulnerability by developing a recurrent neural network (RNN) whose architecture is directly derived from the synaptic-resolution brain connectome of the fruit fly Drosophila melanogaster. We demonstrate the feasibility of training the fly connectome neural network (FLYNN) to perform vision-based navigation in MuJoCo, achieving performance comparable to modern hand-crafted networks of similar parameter counts. Crucially, FLYNN exhibits superior resistance to out-of-distribution (OOD) data and tolerance to sensory loss without further training. It remained functional even under total vision loss while hand-crafted networks largely failed, even when specifically trained with camera dropout. Principal Component Analysis (PCA) of the internal state of FLYNN suggests that it exhibits a particularly high degree of representational modularity, which might be related to its robustness. Our work provides a new direction for designing resilient artificial agents following the topology of biological brains.

Benquan Wang, Jingdao Chen

Department of Computer Science Engineering, Mississippi State University, Mississippi State, MS 39762, USA

Robot NavigationNeural Network RobustnessOOD GeneralizationRecurrent Neural Networks
AskPDF
Jun 19, 2026cs.RO

Inductive Generalization for Robotic Manipulation

Understanding the generalization capabilities of visuomotor policies is essential in the development of capable robotic agents. Generalizable models learn structures that transfer across domains. However, in practice, visuomotor policies test performance by interpolation on known distributions using unstructured domain shifts (e.g. lighting, clutter, diverse objects). We argue that to measure generalization capabilities we must instead test the inductive capacity of policies on progressively harder, out-of-distribution task variants. We call this inductive generalization, drawing directly on how axis-based evaluation has revealed inherent generalization limitations in language models (e.g. sequence length, counting) arXiv:2502.00197 . We provide a reusable and formal evaluation protocol for measuring inductive generalization in any manipulation policy, and establish baselines showing that existing paradigms fail this test; e.g. SoTA Vision-Language-Action models and find that policies that appear to generalize to prior domain shifts (distractors, etc) fail inductive generalization tests. These results expose a class of learning challenges orthogonal to those addressed by data and model scaling in robot learning, yet are imperative to solve in order to realize general purpose robots.

Annabella Macaluso, Haochen Zhang, Ishaan Masilamony +2

Carnegie Mellon University

OOD GeneralizationGeneralization in Robotic ManipulationRobotic Policy EvaluationVisuomotor Policy LearningRobotic ManipulationRobot Manipulation Benchmarks+1
AskPDF
Jun 18, 2026cs.LG

Learning through Internalization

We study internalization processes, by which neural-network-based systems absorb an explicit computational procedure into their own weights, and how they facilitate learning. We investigate how transformers internalize the simulation of semiautomata by internalizing chain-of-thought (CoT) tokens, which classes of semiautomata are harder to internalize, and expose the flip side of internalization, that is, a progressive degradation of out-of-distribution performance. We then provide the first provable analysis of successful internalization: for the task of learning parities, we show that a simplified one-layer transformer provably first learns the target with explicit CoT supervision and then internalizes the autoregressive generation as CoT tokens are progressively removed, learning to directly compute the parity. This task is computationally hard to learn from data without CoT supervision. Finally, we discuss how learning through internalization relates to the \textit{Positive Distribution Shift} phenomenon recently introduced by~\citet{Med+26}.

Nikolaos Tsilivis, Nirmit Joshi, Marko Medvedev +2

New York University · Toyota Technological Institute at Chicago · University of Chicago

TransformerOOD Generalization
AskPDF
Jun 18, 2026cs.AI

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation studies covering new asset classes (including a multi-modal visual extension), alternative orchestrations, retrieval strategies, reasoning modes, infrastructure optimizations, and evaluation-methodology probes. Consolidating those studies with seven prior agent benchmarks, we argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation. Rankings derived from aggregate scores do not transfer to out-of-distribution settings; recent public-to-hidden competition retrospectives provide direct empirical evidence of this rank instability. We propose ranking configurations by predictive validity, the correlation between in-sample and out-of-sample rank, rather than in-sample mean, and report a twelve-tier measurement apparatus that exposes the deployment-relevant dimensions HELM and its agent-era successors collapse. The position is operationalized through three falsifiable out-of-distribution criteria with explicit thresholds; existing evidence partly supports it but is too thin to confirm. We close with a pre-registered pilot design and a field-level vision for what the next generation of agentic benchmarks should report.

Dhaval C. Patel, Kaoutar El Maghraoui, Shuxin Lin +58

OOD GeneralizationLLM Agent EvaluationAI Agent BenchmarksBenchmark Validity
AskPDF
Jun 17, 2026cs.LG

Comparing Linear Probes with Mahalanobis Cosine Similarity

Linear probes are widely used in interpretability research and often compared by cosine similarity. The Mahalanobis cosine similarity (MCS) between two directions, which reweights the inner product by test data covariance, is a natural task-aware refinement. Ying et al. (2026) report that a probe's MCS to a reference probe trained on the out-of-distribution (OOD) data near-perfectly linearly predicts the probe's OOD AUROC (R^2 = 0.98). Here, we extend this empirical finding across models, layers, and concept domains, and prove this general phenomenon in closed form: For balanced classes whose projections are Gaussian, OOD AUROC and MCS to the reference probe are linear because both are sigmoid-shaped functions of the probe's signal-to-noise ratio (SNR) on the test data. The theory also predicts when this linearity fails, which we verify empirically. MCS offers a theoretically grounded and empirically effective alternative to Euclidean cosine similarity for comparing linear probes.

Zhuofan Josh Ying, Peter Hase, Nikolaus Kriegeskorte

Departments of 1Psychology, 2Neuroscience, 3Electrical Engineering · 4Zuckerman Mind Brain Behavior Institute; Columbia University, New York, NY · 5Stanford University, Stanford, CA +1

Linear ProbingMahalanobis DistanceOOD GeneralizationLanguage Model Probing
AskPDF
Jun 17, 2026cs.CV

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic

Open Vocabulary Action Recognition (OVAR) enables the recognition of novel actions by leveraging vision-language representations, overcoming the limitations of traditional closed-set approaches. However, achieving robust performance in real-world scenarios typically requires domain-specific fine-tuning, which is often costly and raises privacy and regulatory concerns. In this work, we propose an alternative paradigm that bypasses target-domain training and recombines knowledge from existing datasets and models. Leveraging model merging and task arithmetic, we extract and combine task vectors from models fine-tuned on diverse public OVAR datasets. We show that, in out-of-distribution settings, the resulting merged model achieves superior zero-shot generalization to the pre-trained base model. Code is available at https://github.com/omaymaMoussadek/robust-ovar

Francesca Morandi, Omayma Moussadek, Federico Venturini +5

University of Modena and Reggio Emilia · University of Pisa · Eni S.p.A.

Zero-Shot LearningOOD GeneralizationVideo Action Recognition
AskPDF
Jun 16, 2026cs.LG

When Dynamics Models Read the Wrong Time Steps: Label-Free Event Credit Re-Anchoring for Robust Global Readouts

Learned dynamics models often answer global physical questions, such as fault severity or impact stiffness, by pooling a per-step feature sequence into one readout vector. This sequence-to-global interface creates an under-studied temporal credit problem: with only trajectory-level supervision, a model can predict accurately in training conditions while reading from abundant smooth correlates rather than the brief physical events that determine the target. We call this failure temporal credit dilution. It is not exposed by the training loss and is not removed by standard physics-informed residuals, because the error lies in where the global readout assigns functional credit. We introduce Credit-in-Event, an interface-level probe for measuring how much pooled credit lands on event steps, and prove in closed form that a pooled linear reader routes credit to a spurious background channel as the event fraction shrinks. We then propose CREST, a training-free and label-free readout that estimates a transient event core from learned features and re-anchors the pooled representation through event-versus-rest contrast. Across simulated gear and impact systems, recurrent and attention encoders, and public bearing vibration data, CREST reduces out-of-distribution error while restoring event credit. Ablations show that stable-step selection and receptive-field shrinking fail, confirming that the gain comes from event-core credit re-anchoring rather than a generic locality or stability prior.

Yifan Wang

Department of Mechanical Engineering, McGill University Montréal, QC H3A 2T7, Canada

Latent Dynamics ModelingOOD GeneralizationTemporal Credit AssignmentFault Diagnosis
AskPDF
Jun 16, 2026cs.CV

Theoretical Grounding of Out-Of-Distribution Detection With Reinforcement Learning Optimizer

Out-of-distribution (OOD) detection in dynamic open-world environments requires a model to continually adapt to evolving data distributions while generalizing to covariate-shifted inputs and rejecting semantic-shifted OOD examples. Most existing OOD detection methods optimize only the current-step objective and do not explicitly account for how post-deployment environment changes affect future OOD behavior. In this paper, we establish a theoretical grounding for dynamic OOD detection using a reinforcement learning (RL)-guided optimizer that explicitly favors updates that reduce the semantic OOD false positive rate over time. We develop a novel augmented optimizer that uses an RL-guided correction term on top of standard gradient descent (GD) and show its improvement over both future-domain generalization and semantic-OOD rejection. We analyze temporal error decomposition in terms of model-change and environment-change generalization errors and develop a new theoretical framework for comparing the generalization errors under both GD and RL-guided optimizers.

Salimeh Sekeh, Xin Zhang

San Diego State University

OOD GeneralizationOOD Detection
AskPDF
Jun 15, 2026cs.AI

Nothing from Something: Can a Language Model Discover 0?

AI systems based on artificial neural networks are being developed with aspirations of pushing the boundary of human mathematical knowledge. A key question for these systems is how much they can reach beyond their training data. Mathematical discovery requires a strong form of out of distribution generalization; the ability to hypothesize genuinely new - and potentially logically more powerful - mathematical structures. It has been hypothesized that language abilities support such generalizations in human cognition. In this work, we use simple arithmetic as a case study for examining how modern AI models could expand their mathematical horizons, evaluating whether these models can independently discover the concept of "zero". We show that (1) language models of a GPT-2 size are unable to perform this generalization at test time regardless of language pretraining, but (2) models can improve substantially after training on tens or hundreds of examples of zero. Additionally, we find that language pretraining reduces the number of required examples by approximately 50%50\%, showing that language abilities can scaffold mathematical discovery in neural models.

Phoebe Zeng, Thomas L. Griffiths, Brenden M. Lake

Department of Computer Science, Princeton University

Numerical Reasoning in Language ModelsLanguage Model PretrainingZero-Shot LearningOOD Generalization
AskPDF
Jun 15, 2026cond-mat.mtrl-sci

Physics-Informed Attention Mechanism and Generalization Capability of Deep Learning-Based Grain Growth Evolution Prediction

Machine Learning (ML) models for grain growth prediction are typically trained on idealized synthetic data, yet practical applications require generalization to conditions outside the training distribution. This study evaluated the Out-Of-Distribution (OOD) generalization capability of the trained model from our previous study across three test cases, including experimental microstructures, microstructures characterized by a bimodal grain size distribution, and abnormal grain growth. To further probe whether physics-informed architectural design could improve robustness under these different conditions, a boundary-masked attention mechanism was proposed specifically for grain growth, constraining attention to grain boundary pixels. Both the baseline and the proposed physics-informed attention model were evaluated without retraining or fine-tuning on the OOD data. Both models successfully generalized to all three test cases, yet the boundary-masked attention mechanism provided substantial improvements, with the most notable gains for microstructures characterized by a bimodal grain size distribution, where Structural Similarity Index Measure (SSIM) improved from \num{0.6221} to \num{0.7609} and mean grain size (R‾\overline{R}) error decreased from \SI{8.75}{\percent} to \SI{3.57}{\percent}. The attention heatmap analysis revealed that the boundary-masked attention model learned to concentrate attention on large grain boundaries in a manner consistent with curvature-driven grain growth physics, emerging from training without being explicitly encoded into the architecture. These results indicate that models trained on synthetic data can generalize to diverse OOD conditions without retraining, and that physics-informed attention may improve accuracy when the boundary morphology matches the training domain.

Pungponhavoan Tep, Marc Bernacki

Mines Paris, PSL University Centre for Material Forming (CEMEF), UMR CNRS 06904 Sophia Antipolis, France

OOD GeneralizationPhysics-Informed ML
AskPDF
Jun 15, 2026cs.LG

A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning

Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributional shifts in the underlying data-generating process. Such shifts may occur between training and evaluation, as in In-Distribution (ID) and Out-of-Distribution (OOD) generalization, or within non-stationary settings where environment dynamics evolve over time. However, the formal relationship between these views remains unclear, and existing work mainly focuses on mitigation rather than the causal origin of shift within the agent-environment interaction. This work develops a unified causal-origin taxonomy that characterizes sources of distributional shift in RL and relates ID/OOD generalization to non-stationary settings. We transfer the classical dataset-shift principle from supervised learning to RL by reformulating distributional shift in terms of the generative interaction process. Using a Partially Observable Markov Decision Process (POMDP), we decompose the interaction into structural components, including the state distribution, observation process, policy, reward, and transition dynamics, together with the shifted-time boundary. The proposed taxonomy distinguishes internal (agent-driven) and external (environment-driven) distributional shifts. The shifted-time boundary perspective further characterizes explicit, implicit, and hybrid shifts. This formulation unifies ID/OOD generalization and non-stationarity as structured changes in the underlying process. We also introduce an evaluation framework for measuring shift impact and adaptation through performance degradation and recovery metrics. By grounding distributional shift in the causal-origin structure of RL, this work supports systematic analysis of robustness under distributional shift.

Ardianto Wibowo, Paulo E Santos, Amer Baghdadi +3

IMT Atlantique, Brest, France · Flinders University, Adelaide, Australia · IRL Crossing, Adelaide, Australia +1

Distribution Shift RobustnessNon-Stationary RLOOD Generalization
AskPDF
Jun 14, 2026cs.CL

In-Domain Supervised Pathology Report Classification: A Reproducible Pipeline from Data Curation to Production-Matched Evaluation

We introduce an in-domain supervised pipeline designed to counter the out-of-distribution performance drop that hampers supervised biomedical NLP models, a problem observed when models trained on pathology reports are moved across cancer registries. Our contribution is a reproducible recipe for training a supervised classifier from routinely collected cancer registry data. It describes how to build the in-domain training set and a production-matched holdout, and to choose operating points that keep the false-negative rate (FNR) very low while keeping reviewer workload manageable. The pipeline standardizes data curation with facility-stratified sampling and separate handling of reports linked to registry cases, and includes a blinded manual audit to estimate positive-case prevalence and label noise. On a 418k-report holdout set, the Kentucky model achieved FNR 0.003 and false-positive rate (FPR) 0.097, improving over the Seattle-trained MOSSAIC OncoID baseline (FNR 0.010, FPR 0.183) and raising F1 from 0.860 to 0.922. In a blinded manual review of 600 reports, estimated positive prevalence declined from 0.500 to 0.398, indicating substantial label noise with errors concentrated in rare primary sites.

Isaac Hands, Bin Huang, Adam Spannaus +4

Department of Computer Science, University of Kentucky, Lexington, KY, USA · UK Markey Cancer Center, Lexington, KY, USA · Kentucky Cancer Registry, Lexington, KY, USA +3

Computational PathologyTraining Data CurationOOD GeneralizationOncologyClinical NLP
AskPDF
Jun 14, 2026cs.CV

Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation

Deep neural networks (DNNs) frequently fail to generalize to out-of-distribution (OOD) medical images because of variations in scanners and acquisition protocols. Retraining DNN models to address these distribution shifts is often impractical due to the high cost of acquiring and annotating new medical datasets. To address this, we introduce VarDeepPCA, a novel lightweight variational DNN framework designed to restore/refine degraded segmentation maps by leveraging intrinsic geometric priors. Unlike existing approaches that require target-domain data or extensive pre-training, our VarDeepPCA explicitly learns a distribution of valid anatomical geometries using only small in-distribution (ID) datasets. Theoretically, our novel variational learning framework leverages a reinterpretation of the softmax mapping to implicitly perform exact distribution modeling, thereby enabling computationally efficient, sampling-free learning and inference. This also enables VarDeepPCA to provide uncertainty estimates associated with its restored segmentation maps. We empirically validate our framework across 4 distinct clinical applications, using 14 publicly available datasets, involving segmentation of the myocardium, neuroretinal rim, prostate, and fetal head. Comparisons against 15 existing methods demonstrate that VarDeepPCA consistently restores segmentation maps produced by the existing methods on OOD data to (i) significantly improve anatomical plausibility of geometries and clinical utility of the segmentations, and (ii) significantly reduce errors, without needing any more training data than that used by existing methods.

Jimut B. Pal, Suyash P. Awate

Centre for Machine Intelligence and Data Science (C-MInDS), Indian Institute of Technology (IIT) Bombay, Mumbai · Computer Science and Engineering (CSE) Department, Indian Institute of Technology (IIT) Bombay, Mumbai

OOD GeneralizationMedical Image SegmentationVariational InferenceSegmentation Uncertainty Estimation
AskPDF
Jun 10, 2026cs.LG

Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter

Machine-learning drug-discovery pipelines increasingly rely on generative models that propose molecules far from the data used to train downstream synthesizability filters. Existing filters (SAScore, SCScore, RAscore, DeepSA) are purely statistical and degrade in exactly this out-of-distribution (OOD) regime. We ask whether cheap, closed-form physical priors, used as auxiliary supervision on a graph neural network (GNN), improve OOD generalization. We add two auxiliary losses to a GINE backbone: a topological complexity regression supervised by the Bertz index, and a strain-energy soft penalty supervised by MMFF94 force-field energy. On a 65,177-molecule corpus (HIV, Tox21, COCONUT) labeled by SAScore thresholds we reproduce a strong in-distribution baseline, then evaluate a 4-way ablation (baseline / +complexity / +strain / +both) on a single-source OOD split (train on drug-like HIV+Tox21, test on COCONUT natural products), repeated over 5 seeds with paired bootstrap confidence intervals. All three physics-aware variants give a small but statistically significant OOD improvement over the baseline (mean OOD AUC 0.9774): +complexity Delta = +0.0060 (95% CI [+0.0023, +0.0102]), +strain Delta = +0.0032 ([+0.0008, +0.0052]), +both Delta = +0.0066 ([+0.0038, +0.0093]); every interval excludes zero, and the combination is best. The variants are indistinguishable in-distribution, so the effect is visible only under OOD evaluation. We are explicit that the effects are modest, and we report a cautionary methodological finding: a single-seed version of this experiment produced a qualitatively different (non-monotone) story that did not survive multi-seed evaluation.

Riya Bisht, Dhruv Agarwal

Graph Neural NetworksOOD GeneralizationPhysics-Informed MLMolecular Property PredictionPhysics-Informed GNNs
AskPDF
Jun 10, 2026cs.LG

Harness In-Context Operator Learning with Chain of Operators

Neural operators approximate mappings between function spaces, but often generalize poorly to other operators and usually require fine-tuning or retraining. In-Context Operator Networks (ICON) addresses this issue by prompting the model with numerical context so that the model learns specific operators from prompts and adapt to different operators without fine-tuning. However, ICON may still fail to generalize to out-of-distribution (OOD) operator tasks. Inpired by the success of harness engineering of Large Language models (LLMs), we introduce Chain of Operators (CHOP), a framework that harness a frozen ICON to OOD operator tasks without updating its parameters. Specifically, CHOP constructs a chain of operators consisting of explicit elementary transformations and the frozen ICON. Experiments on a scalar conservation law and a mean-field control problem show that CHOP reduces relative inference error over direct ICON evaluation, while each operator in the chain remains interpretable and in closed form. A chain constructed on one PDE family further generalizes to a different family, indicating shared mechanisms across harness systems.

Minghui Yang, Ling Guo, Liu Yang

Department of Mathematics, Shanghai Normal University, Shanghai, China · Department of Mathematics, National University of Singapore, Singapore

OOD GeneralizationPDE Operator LearningOperator LearningNeural Operators
AskPDF
Jun 10, 2026cs.SD

Quality Adaptive Angular Margin Learning for Respiratory Sound Classification

We present a quality-adaptive angular-margin learning framework that improves feature generalization by enforcing intra-class compactness and inter-class separability. Our framework, titled QLung, introduces a no-reference audio quality margin derived from spectral entropy and root-mean-square energy, which adaptively scales angular margins based on recording quality. To this end, we propose a log-scaled angular margin that stabilizes training under severe class imbalance. We also use an angular classifier that normalizes features and class weights, ensuring margin penalties are applied consistently on the unit hypersphere. Our approach improves in-distribution performance on the ICBHI dataset by 2.46% over the cross-entropy baseline, and most significantly, achieves the strongest out-of-distribution performance on the SPRSound dataset compared to prior state-of-the-art methods. Code is available at https://github.com/RSC-Toolkit/QLung.

Yoon Tae Kim, Heejoon Koo, Miika Toikkanen +1

RSC LAB, MODULABS, Republic of Korea · Department of Electronic Engineering, Wonkwang University, Republic of Korea · AI Convergence Research Institute, Wonkwang University, Republic of Korea

OOD GeneralizationMetric LearningAudio ClassificationRespiratory Sound Classification
AskPDF