Distribution Shifts

The deployment of data-driven models in 6G wireless networks is increasingly challenged by frequent distribution shifts that degrade performance over time. Unsupervised Domain Adaptation (UDA) offers an alternative approach by adapting the trained model to a shifted domain without requiring labels. However, UDA pipelines are often more complex than single-task training due to additional modules and optimization procedures, raising a practical question: do the benefits of adaptation come at a higher energy cost, and how does this trade-off compare to retraining when labeling effort is also considered? In this work, we investigate the energy consumption of UDA and compare it to single task. We further propose a way to determine the minimum number of target domains for which UDA becomes more energy-efficient than retraining, taking into account the labeling cost. Our results aim to clarify when UDA should be preferred over classical train-from-scratch approaches from an energy and labeling-aware perspective.

Sample reweighting is a major approach to addressing distribution shifts, such as label noise and class imbalance. Meta-Weight-Net (MW-Net) is a promising sample reweighting network that computes weights based on classification loss. Although MW-Net improves prediction performance under a single type of distribution shift using a simple neural network, its performance degrades when facing both label noise and class imbalance, where it is hard to determine appropriate weights solely from classification loss and using a simple network. In this study, we introduce neural architecture search to MW-Net to mitigate such performance degradation. Using the tree-structured Parzen estimator, we explore the optimal number of hidden layers and nodes and select the most suitable intermediate layer in the classification model to serve as the input for MW-Net. Experimental results on the CIFAR-10 and CIFAR-100 datasets that were modified to include both label noise and class imbalance demonstrate the effectiveness of neural architecture search for MW-Net.

Distribution shift between training and deployment is a pervasive challenge for modern AI systems. In many cases, the target marginals of covariates and response are known or specified through population-level observations, boundary conditions, properties of simulator configurations, or alignment-time distributional constraints. Such knowledge may provide valuable side information for regression estimation. We study this problem in the multivariate linear regression setting with a stable conditional mean $E[Y\mid X]$ across source and target, and identify the hybrid-loss estimator, which jointly incorporates both target marginals, as a benchmark target-aware estimator. Its direct computation, however, requires solving a coupled nonlinear optimization that is expensive at scale. Our main contribution is to develop and evaluate two computationally tractable alternatives: a constrained moment-matching estimator and a two-stage estimator that augments ordinary least squares with a calibration step. For all three estimators, we derive and compare closed-form asymptotic mean squared errors, yielding conditions under which the tractable alternatives match or closely approximate the hybrid benchmark, and regimes in which they do not. Monte Carlo experiments across three controlled shift regimes validate the theoretical results, investigate the accuracy-runtime tradeoffs among the three estimators, and translate into guidance on estimator choice. In particular, the two-stage estimator nearly matches the hybrid benchmark in the high signal-to-noise regime at essentially no additional cost, providing theoretical grounding for empirical observations in nonlinear settings.

Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distribution shift. Crucially, these two conditions demand different downstream actions, as ambiguous in-distribution faces should be reported with their ambiguity whereas out-of-distribution inputs should be rejected. However, a single uncertainty score conflates the two. In this study, uncertainty decomposition into aleatoric and epistemic components for FER is investigated, and Uncertainty-Aware Routing (UAR), an inference-time routing mechanism that exploits the separation, is introduced. Specifically, aleatoric and epistemic uncertainties are obtained from a Deep Ensemble of fully fine-tuned DINOv2 models and are each validated against an independent external signal: aleatoric against human annotator disagreement, and epistemic against distribution shift induced by image corruptions. The proposed dual-validation protocol reveals that aleatoric recovers annotator disagreement with Spearman correlation 0.66 (95% CI: 0.64-0.68), and epistemic detects corruption-induced shifts, achieving average AUROC of 0.699 at the highest corruption severity. UAR retains approximately 1.8 times more ambiguous in-distribution faces than single-uncertainty routing at a matched out-of-distribution rejection rate. A strong label-distribution-learning baseline achieves comparable disagreement recovery but cannot separate ambiguity from shift and therefore cannot route, establishing that the value of decomposition lies in the separation enabling interpretable and differentiated action selection.

Machine learning systems deployed in dynamic environments frequently operate under nonstationary data distributions, where controlled distribution shift can progressively degrade predictive performance. However, many widely used tabular benchmark datasets lack explicit temporal structure, limiting reproducible evaluation of drift adaptation methods. This work proposes a cluster-induced distribution shift simulation framework that transforms static tabular datasets into controlled evolving data streams through structured perturbations across featurespace partitions. Using this framework, six adaptation strategies are systematically evaluated: static learning, sliding-window retraining, global ADWIN retraining, cluster-local ADWIN retraining, random subspace drift detection, and feature-partitioned drift detection. Experiments are conducted on five benchmark datasets covering both classification and regression tasks using diverse predictive model families, including linear models, k-Nearest Neighbours, tree ensembles, boosting methods, and adaptive online learners.

Medical time series (MedTS) signals such as electroencephalography (EEG) and electrocardiography (ECG) support many clinical applications. However, substantial subject-level heterogeneity often induces subject-level distribution shift, causing a fixed parameter set to generalize poorly to unseen individuals. Compared with domain adaptation methods that often depend on extra adaptation components or target-batch statistics, Test-Time Training (TTT) provides a more practical solution for sequential clinical data by enabling online adaptation from unlabeled test samples. However, many representative TTT methods require iterative inner-loop optimization, increasing test-time overhead. In this paper, we propose MedTS-TTT, a test-time training framework for medical time series modeling. MedTS-TTT is built upon Closed-Loop Self-Alignment Test-Time Training (CLSA-TTT) and a Gated Convolutional Backbone (GCB). CLSA-TTT constructs a token-level self-supervised target and performs a single-step fast-weight update for intra-layer closed-loop alignment, enabling rapid sample-wise adaptation without iterative inner-loop optimization. GCB combines CLSA-TTT-based fast adaptation and token-level fusion with a gated convolutional branch to balance local dynamic modeling and information-flow control. On 4 public datasets (2 EEG and 2 ECG) with subject-independent splits, MedTS-TTT achieves 11 top-1 rankings out of 12 evaluations across 9 baselines and 3 metrics. The code is publicly available at https://github.com/mingzhi-c/MedTS-TTT.

A fundamental assumption in statistics and machine learning is that ``the future looks like the past,'' formalized as exchangeability: the joint data distribution is order-invariant. In practice, this assumption is often violated due to distribution shifts over time. Early detection of exchangeability violations is crucial to prevent performance degradation and enable timely interventions like model retraining. Conformal test martingales offer a flexible, distribution-free framework for sequential exchangeability testing with guaranteed false-alarm rate control by betting against the uniformity of conformal p-values. While alternatives such as plug-in martingales and mixture-based strategies exist, computationally efficient baselines like the Simple Jumper are limited to detecting mean location shifts. We propose a family of conformal test martingales based on shifted Legendre polynomials that extend the Simple Jumper to higher-order moments. The Simple Legendre Jumper replaces linear betting functions with polynomials of arbitrary degree, enabling rapid detection of variance, skewness, and other higher-order deviations. The Product Legendre Jumper combines multiple polynomial degrees into a single betting function but suffers from exponential state-space growth, termed the jumping tax. To resolve this, we introduce the Variational Legendre Jumper, which employs a mean-field approximation to reduce complexity to constant time per step with minimal power loss, providing an expressive, scalable framework for real-time distribution shift monitoring.

Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for understanding and trusting reported probabilities. Recent work shows that enforcing calibration at the level of individual predictors can improve ensemble accuracy and calibration, with mixture-of-experts (MoE) models showing strong empirical improvements in particular; however, the conditions under which calibration helps MoE are not well understood. In this work, we study how MoE models behave under distribution shift, focusing on how routing mechanisms interact with expert-level calibration. We show that expert calibration is sufficient to ensure calibration of the overall model under a broad class of distribution shifts in hard-routed models, but is insufficient for calibrating soft-routed models. To address this, we propose an adversarial reweighting that penalizes calibration errors of the routed aggregate under distribution shift, and we demonstrate that it improves the accuracy-calibration tradeoff both on average and on difficult subsets of the data, across model classes, prediction tasks, and distribution shifts.

Federated bilevel optimization is widely used for nested learning problems across distributed clients, such as federated hyperparameter tuning and meta-learning under privacy and communication constraints. Most existing formulations assume fixed client data distributions, which can be violated by performativity, where deployed decisions reshape client behavior and data collection, inducing client-specific, decision-dependent distribution shift. We study federated bilevel performative prediction, where both upper-level (UL) and lower-level (LL) objectives are evaluated under client-dependent, decision-dependent distributions. We formalize the federated bilevel performatively stable (FBPS) point under a decoupled-risk perspective and provide sufficient conditions for its existence and uniqueness. We then develop two federated methods to compute the FBPS solution: FBi-RRM, which converges linearly under a contraction condition, and FBi-SGD, a communication-efficient stochastic method based on federated hypergradient estimation with convergence guarantees under diminishing step sizes when sensitivities are sufficiently small. Experiments on strategic regression and meta strategic classification validate the predicted stability thresholds and demonstrate improved meta-generalization over non-performative baselines, and CNN-based classification further demonstrates the practical effectiveness of the proposed methods in nonconvex neural network settings.

Data valuation quantifies the intrinsic quality of individual samples to enable principled data curation, quality control, and robust learning. For time series in critical domains such as healthcare, finance, and industrial monitoring, effective valuation methods are essential yet fundamentally lacking. Existing approaches are either model-dependent, limiting their generalizability, or designed for i.i.d. data and thus fail to capture temporal dependencies, multi-scale patterns, and non-stationary dynamics inherent to sequential data. We introduce TimeLAVA, a learning-agnostic framework that values temporal segments by their marginal contribution to minimizing distributional discrepancy between evaluated and reference data. At its core is a novel Selective Wavelet-based Wasserstein discrepancy combining multi-scale wavelet transforms for temporal localization with unbalanced optimal transport for robustness to distributional shifts. Segment values are efficiently computed via sensitivity analysis without requiring model training and aggregated into point-wise scores. We provide theoretical guarantees linking valuation to model-agnostic generalization and prove bounded sensitivity to outlier contamination. Extensive experiments across anomaly detection, data pruning, and label noise detection demonstrate that TimeLAVA produces significantly more informative value scores than existing methods on diverse real-world datasets.

The quality of recorded data depends on the stability of the sensor system that acquires it. Sensor motion and aging can degrade the performance and stability of downstream data-driven methods. We present a Wasserstein-GAN-inspired approach for unsupervised inference of physically interpretable transformation parameters that map a changed detector response distribution back to a nominal reference distribution. In contrast to standard generative modeling, the generator is used as a learnable calibration transformation whose trainable weights represent the sought parameters, while the critic provides a distributional distance signal via the Wasserstein objective. We validate the approach on a tracking-detector toy model with controlled layer shifts and demonstrate its application on high-granularity Geant4-simulated calorimeter data with cell-wise aging effects. The method recovers aging coefficients for individual cells with correlation to ground truth and improves agreement between calibrated and reference energy-sum distributions, while exhibiting the expected degradation at increasing channel-to-channel noise levels. These results indicate that adversarial distribution matching can serve as a data-driven component of calibration strategies in settings where direct labels for degradation parameters are unavailable.

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.

Subject-driven image customization aims to generate images that not only follow textual instructions but also preserve the identity of a given reference subject. Existing approaches, including test-time fine-tuning, encoder-based methods, and token competition in shared attention spaces, suffer from limited efficiency, misalignment between extracted reference features and the generative process, and interference from irrelevant information. To address these limitations, we formulate the customization task as a distribution shift induced by incorporating reference images into text-to-image generation, and derive a Conditional Attention Distribution Shift formulation grounded in maximum entropy theory. Building on this formulation, we propose CustomShift, a dual-branch architecture based on Stable Diffusion 3. The Reference-Alignment Branch leverages self-attention between reference images and subject names to achieve layer-wise alignment with latent representations, while the Cross-Guidance Branch integrates textual and reference cues to guide generation. Experiments on the DreamBooth and Custom101 benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches, achieving a better balance between semantic fidelity and subject consistency.

Recent vision token pruning methods effectively preserve model performance under moderate token budgets but become unstable under ultra-low token budget. Our analysis shows that as the pruning budget decreases, accuracy degradation is often accompanied by larger feature distribution shifts. Critically, the degree of this distribution shift strongly correlates with performance degradation. To better characterize this phenomenon, we introduce a lightweight distribution consistency metric to estimate the distribution shift between retained and full tokens. Motivated by these observations, we propose a two-stage pruning framework consisting of Anchor-Context Graph Recovery (ACGR) and Text-Aware Token Cluster Selection (TATCS). Specifically, ACGR transfers contextual information before token removal, while TATCS dynamically re-selects representative tokens when severe distribution shift is detected. Extensive experiments demonstrate that our method achieves superior and more stable performance under ultra-low token budget. Notably, it retains 92.1% of the upper-bound average performance on LLaVA-1.5-7B with only 16 visual tokens.

Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts. Yet, its performance often suffers from instability and sensitivity to hyperparameters such as update steps and subspace. We explain this behavior through a decision-theoretic lens, treating TTT as implicit Bayesian inference in the kernel regime. Under a Gaussian process benchmark, we show that TTT reduces prediction error when updates are spectrally matched to the prompt's signal-to-noise ratio and aligned with query-relevant eigen-directions. This perspective underpins the following results: (1) we show when fixed update steps and subspaces fail under distribution shifts, motivating adaptive strategies; (2) we prove that selecting update steps via prompt evidence admits a PAC-Bayes guarantee against overfitting; and (3) we characterize the Bayes-optimal update subspace under a linear-Gaussian correction model, yielding a scoring rule for selecting Transformer blocks and heads. Our theory helps explain the empirical instability of TTT, taking a step toward principled guidance for when, how far, and which directions to adapt.

Early and highly accurate prediction of colorectal polyps, as an important sign of one of the most dangerous types of cancer, will result in saving more lives. Despite the advancements in colorectal polyp classification, many challenges remain in obtaining an automated polyp prediction system that is able to diagnose the difficult-to-predict polyps accompanied by different features in real scenarios, where the model can handle imbalanced data, label distribution shift, and cross-modality generalization successfully. In this study, we propose Polyp-D2ATL, a novel framework accompanied by a specific training strategy, which mitigates these limitations and effectively predicts the different classes of polyps belonging to the NICE classification. Our extensive experiments on the PICCOLO validation and test sets demonstrate that the proposed Polyp-D2ATL significantly outperforms existing state-of-the-art models across various reliable metrics, achieving an accuracy of 82.38%, a Macro-F1 of 77.49%, and a specificity of 87.47% on the validation set, alongside consistent improvements on the held-out test set which demonstrates the generalization capacity and clinical applicability of the proposed approach.

We consider the problem of uncertainty quantification for a pretrained classification model deployed under unknown distribution shift. We propose Audited Conformal Prediction (ACP), a method that leverages a small labeled dataset from the target population to train an auxiliary audit model identifying inputs where the legacy model is likely to fail. By integrating the audit model's outputs into the conformal prediction framework, ACP produces prediction sets that guarantee marginal coverage while achieving substantially higher conditional coverage in practice than existing approaches. We develop and analyze two complementary integration strategies -- one targeting marginal coverage with improved conditional performance, the other providing explicit group-conditional coverage guarantees -- and establish theoretical guarantees for both. Experiments on synthetic and real-world datasets validate the method and illustrate trade-offs between prediction set size and conditional coverage.

Understanding how a prediction model will perform in a new environment before deployment is essential to preventing harm when algorithms inform decision-making. Two common sources of model performance degradation are (i) covariate shift, where the target covariate distribution differs from the source, and (ii) selective labels, where the observability of outcomes depends on historical decisions. We study pre-deployment model evaluation under the joint presence of covariate shift and labeling of outcomes selectively based on observed features. In particular, we present a double machine learning procedure for estimating the target risk of an arbitrary black-box prediction model under a general loss function. We show identification of this estimand under standard assumptions and derive a bias-corrected estimator based on the influence function of the target risk. Finally, we evaluate our estimator through experiments using the eICU electronic health records database, showing that it tracks the true target risk more accurately than methods that address either selective labels or covariate shift alone, as well as baselines that combine standard plug-in approaches.

Transfer learning is usually studied as a consequence of distribution shift. This paper identifies an orthogonal failure mode in which the data distribution is fixed and the loss changes. This setting is called \emph{loss shift}. A loss determines which information in $X$ is Bayes-relevant, and two losses may therefore require different representations even under the same joint law $P(X,Y)$. The idea is formalized using Bayes quotients, which allow losses to be ordered by refinement. In the Bayes-quotient formulation, strict refinement gives an immediate qualitative obstruction. A source-minimal representation for a coarser loss is insufficient for a strictly finer target loss. For finite-output log loss, this obstruction becomes an exact quantitative identity. The excess risk is the conditional information about $Y$ discarded by the representation. Experiments in controlled, learned, synthetic-image, and real-image settings show the predicted effect, i.e., classification-equivalent representations can have different optimal log-loss performance under a fixed data distribution.

Safety classifiers deployed in production operate under a stationarity assumption that fails silently: when input distributions drift, accuracy degrades with no error signal until ground-truth labels arrive. We present an online monitor that detects distributional shift in classifier scores via a sliding-window KS statistic with empirically calibrated alarm thresholds. In a pre-registered factorial evaluation (4 classifiers $\times$ 5 shift conditions $\times$ 20 seeds $\times$ 2 window sizes; 800 cells), the monitor achieves 86.6% valid detection (mean latency 39.5 steps) across synthetic-onset, real-jailbreak, and adversarial regimes; a classifier $\times$ shift interaction ($η^2 = 0.185$) shows that monitoring must be tuned per classifier. Attempting to recover post-detection coverage via weighted conformal prediction exposes a failure mode: density-ratio estimation collapses for generative classifiers because logistic regression separates source from target perfectly in 3584-4096-dimensional embedding space, clipping all importance weights to zero; projecting to $\leq 32$ dimensions restores coverage. We then extend the framework to gradient-based evasion and give the first threat-model characterisation of score-disagreement monitoring as a canary. We falsify three assumptions: that architectural diversity drives the signal (false, $η^2 = 0.011$), that it is generic out-of-distribution detection (false, GCG-specific, $p < 10^{-12}$), and that an adaptive attacker can suppress it (false while the canary is confident). We derive the exact security boundary, a confidence-gated equilibrium at which a monitor-aware attacker stalls at gap $= 1/(2λ)$, and provide a calibration-free scan martingale achieving false-alarm rate $\leq 1\%$ across all classifiers with no per-model tuning.

Conformal predictive systems (CPS) output calibrated bands of CDFs under exchangeability. We extend generalized CPS to non-exchangeable settings by encoding distributional shifts through observation-specific permutation weights. This yields shift-aware predictive systems that remain valid whenever the test point is, conditionally on the unordered sample, a weighted draw from the observed atoms. Since such weights are typically estimated, we introduce weight-uncertainty boxes and construct robust CPS envelopes with finite-sample or asymptotic confidence guarantees. We derive efficient computation for conformity-measure CPS, conformal binning, and conformal isotonic distributional regression. Experiments under covariate shift and feedback-driven biomolecular design show calibrated predictive bands that widen under stronger shifts and tighten as sample size increases.

Graphical User Interfaces (GUIs) serve as the dominant medium for human-computer interaction, yet building GUI agents that generalize across the vast diversity of real-world interface environments, with the same flexibility and robustness that humans naturally exhibit, remains unsolved. Notably, GUI data are inherently non-stationary: the continual emergence of previously unseen interface instances (e.g., novel domains and resolutions) induces persistent distribution shifts, significantly impeding the continual learning of existing GUI agents. Reinforcement fine-tuning (RFT) has attracted considerable attention as a promising approach. Nevertheless, RFT exhibits pronounced instability in its grounding capability, manifested as sharp reward discontinuities and high-variance oscillations. The imbalanced distribution of rollout outcomes introduces substantial noise into advantage estimation, leading to policy overconfidence. The fixed clipping bound suppresses the increase in policy probabilities needed to adapt to new distributions, leading to a collapse in exploration capacity. To address these challenges, we propose GUI-AC, a method that enhances the continual learning capability of GUI agents. GUI-AC introduces grounding certainty to support two core mechanisms: (i) Adaptive Advantage, which down-weights noisy advantage estimates to prevent policy overconfidence; and (ii) Dynamic Clipping, which relaxes the clipping bound to encourage exploration range. Extensive experiments show that these mechanisms jointly improve performance, enabling our method to surpass state-of-the-art baselines. Code is available anonymously at https://github.com/Can-Lin/GUI-AC.

Reinforcement learning (RL) has become a key component of post-training large language models (LLMs). In practice, LLM RL is often off-policy because of training-inference mismatch and policy staleness, making trust-region control essential for stable optimization. Mainstream methods such as PPO and GRPO approximate this control with a ratio-clipping mechanism, but the importance ratio can be a poor proxy for distributional shift in long-tailed vocabularies. Recent work such as DPPO addresses this mismatch by replacing ratio-based clipping with a divergence-based mask, yielding a trust region defined by the sampled token's absolute probability shift. However, DPPO still relies on a hard mask: once a token crosses the trust-region boundary in a harmful direction, its gradient is discarded rather than corrected. To address this, we propose Divergence Regularized Policy Optimization (DRPO), which replaces the hard mask with a smooth advantage-weighted quadratic regularizer on policy shift. DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights that attenuate diverging updates and provide corrective signals beyond the boundary. Experiments across model scales, architectures, and precision settings show that DRPO improves the stability and efficiency of LLM RL training.

Modulation recognition systems rely on heterogeneous signal representations. 2D signal-image modalities such as time-frequency and cyclostationary maps capture structural patterns, while 1D statistical descriptors such as higher-order power spectra encode complementary cues. Under distribution shift, these modalities degrade unevenly, making robust fusion a central challenge for practical deployment. Progress is further limited by the lack of a unified evaluation protocol that systematically separates different shift types. This paper addresses both challenges through a joint benchmark-and-model study in underwater acoustic modulation recognition. UAMR-ShiftBench is the first benchmark to jointly cover in-distribution, low-SNR, unseen-environment, unseen-communication-parameter, and measured sea-trial evaluation under a single matched protocol, with two independent real-world subsets collected during two sea-trial campaigns conducted in March and November in the South China Sea. SCP-TriCA fuses STFT, cyclostationary, and P2/P4 (second- and fourth-order power spectra) modalities hierarchically: the two 2D modalities are first aligned through bidirectional cross-attention, and the 1D statistical modality is then incorporated through a sample-adaptive selective gate. On UAMR-ShiftBench, SCP-TriCA achieves 95.33% in-distribution accuracy and 74.59% simulated OOD average, outperforming the strongest baseline by 5.12 percentage points, and reaches 91.14% and 94.86% on the two sea-trial subsets, exceeding the best baseline by 15.71 and 23.00 percentage points respectively. Ablation results confirm that the gains stem from modality complementarity and the hierarchical fusion design. Code and models are available at https://github.com/ronglaiqian/UAMR-ShiftBench.

Performative prediction studies feedback loops that arise when predictive models are deployed in consequential domains. In these settings, deploying a model can change the population whose patterns the model aims to predict, inducing a distribution shift that is endogenous to the learning system. This perspective departs from classical treatments of distribution shift, where shifts are typically modeled as exogenous changes in the data-generating process. Yet, in practice, distribution shift is rarely one or the other. Predictive models may influence future data through the decisions they support, while the world itself continues to drift for reasons beyond the learner's control. We study partially performative prediction, a framework that captures both endogenous and exogenous sources of distribution shift. The framework generalizes performative prediction by allowing the data distribution to evolve both in response to the deployed model and according to an external, time-varying process. We extend the central notions of performative stability and performative optimality to this setting by defining their online analogues that track the evolving partially performative environment. We analyze practical learning heuristics, including repeated retraining, and characterize when they successfully adapt to partially performative environments.

Performance estimation under distribution shift aims to predict how a model behaves on an unlabeled test set whose distribution differs from the training data, a scenario that requires reliable indicators that can faithfully reflect model behavior without ground-truth labels. Existing approaches rely solely on the outputs of the given model whose biases are amplified once the distribution shifts, weakening the correlation with the true performance. Motivated by this limitation, we propose Fused Reference Alignment Prediction (FRAP), which leverages the complementary strengths of an external foundation model and the base model to construct a more reliable surrogate of the ground-truth labels. FRAP aligns the prediction distribution of the foundation model with that of the base model by applying temperature-scaled calibration that minimizes their divergence. The aligned predictions are fused through confidence-based weighting into a refined reference distribution that integrates robustness from the foundation model and domain-specific expertise from the base model, and performance estimation is obtained by measuring how closely the base model predictions agree with this reference. Extensive experiments across diverse datasets and architectures show that FRAP provides consistent and substantial improvements over representative performance-estimation methods under distribution shift.

Data samples used for training often differ from those encountered during fine-tuning and deployment, and while ML models show promise, their performance remains limited when only small annotated datasets are available. Performance often degrades under distribution shifts caused by diverse sensors, populations, and application settings. Although pre-training helps, models frequently encounter out-of-distribution (OOD) data in real-world settings, leading to reduced robustness. Existing adaptation methods usually assume fixed distribution shifts and struggle when multiple types or severities occur. In particular, they overlook shift severity, for example treating adaptation to a large familiar dataset the same as adaptation to a small dataset with a new task, which limits generalisation. To address this, we propose ADAPTOOD, a novel framework that leverages data uncertainty to quantify distribution shift severity and guide fine-tuning for time series. This uncertainty measures how strongly samples from the target deployment distribution deviate from the pre-training distribution, providing a direct signal of OOD severity. Our framework combines this uncertainty with low-rank model updates and adaptive hyperparameter optimisation to improve adaptation. We show that ADAPTOOD achieves up to 7% higher accuracy and 12.9% higher precision than existing methods in OOD tasks, maintaining strong performance as distribution shift severity increases.

Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment. Statistical tools for detecting training-data membership exist, but have been validated almost exclusively in controlled academic regimes: large, homogeneous pre-training corpora and transparent, single-stage training pipelines. Whether these methods remain reliable in realistic auditing scenarios remains unclear. We identify two under-studied failure modes: distribution shift, which arises when suspect and validation sets violate the IID assumption, and scale constraints, which arise because benchmarks are orders of magnitude smaller than pre-training corpora. We systematically evaluate three leading paradigms, LLM Dataset Inference, Post-Hoc Dataset Inference, and CoDeC, across 25 models from multiple families (including Pythia, OLMo 2, and specialised cultural and medical LLMs) and scales (up to 27B). We then further extend our analysis to frontier industry models. Across 335 evaluations, only 201 yield correct outcomes. LLM Dataset Inference results in false positives under distribution shift, Post-Hoc Dataset Inference is underpowered at benchmark scale, and CoDeC provides only coarse provenance signals that are insufficient to verify individual benchmark splits. Our results reveal a systematic reliability gap between controlled validation and practical benchmark auditing, and show that statistical detection cannot yet replace transparent data provenance. We open-source our benchmark for further research.

Live streaming has emerged as a primary medium for social interaction and digital commerce, yet it is increasingly plagued by sophisticated risks. A fundamental challenge in this domain is \emph{tactical out-of-distribution (OOD) shift}: while malicious actors maintain stable underlying objectives, they continuously redesign narrative packaging to evade detection. Such adversarial shifts expose critical limitations of existing OOD generalization paradigms, whose assumptions are difficult to satisfy in the presence of tightly coupled intent-tactic evolution and ill-defined raw-level counterfactuals. In this paper, we tackle this issue from a \emph{latent causal} perspective and propose \underline{L}atent-\underline{P}redictive \underline{C}ounterfactual \underline{D}ecoupling~(LPCD), a plug-in framework for robust live streaming risk assessment. LPCD enables counterfactual reasoning under adversarial tactical re-packaging by modeling intent and narrative variation at the latent level, and enforces \emph{latent counterfactual consistency} to anchor risk prediction on causally stable malicious intent. At inference time, LPCD applies a lightweight, parameter-free calibration to further mitigate tactic-induced distribution shifts. Extensive experiments on large-scale industrial datasets and online production traffic demonstrate that LPCD consistently outperforms state-of-the-art baselines, validating its effectiveness in moderating evolving adversarial risks in real-world live streaming. The project page is available at https://qiaoyran.github.io/LiveStreamingRiskAssessment/.

Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this work, we show that distribution shifts can cause feature clusters corresponding to distinct classes in the model's representation space to merge, while the decision boundary remains fixed. This induces a systematic skew in the predicted class distribution, referred to as prediction bias. Prediction bias refers to a shift in the predicted class distribution, with some classes overrepresented and others suppressed. We show that entropy minimization amplifies this prediction bias by tightening the existing clusters, reinforcing the incorrect groupings until all predictions collapse to a trivial solution. Next, to demonstrate the significance of prediction bias and mitigate it, we further propose Distribution Shift Bias Reduction (DSBR), a bias-correcting objective that specifically targets this failure mode by equalizing the contribution of each predicted class to the unsupervised entropy minimization loss. To study this failure mode, we design suitable adaptation settings using four medical-imaging datasets and additionally evaluate on ImageNet-C. We find that DSBR consistently stabilizes test-time adaptation, prevents model collapse, and matches or outperforms state-of-the-art methods. Moreover, DSBR operates solely at test-time.

The standard generalization bounds assume that the training and deployment distributions are the same, or are static, and don't consider regime switching environments where the ratio of calm vs crisis states is different. This paper proposes a framework that generalizes regime-aware models by quantifying the extra risk due to regime composition mismatch, when distribution shifts are Markov-switching. We obtain an exact decomposition, separating regime mismatch from regime sensitivity; we extend the bound to beta-mixing data using the effective sample size corrected for the spectral gap; and we show a minimax lower bound for synthetic data and on 25 years of global equity indices. The proposed penalty is an ex post realized generalization gap, whereas the training-only estimator does not show significant correlation: the feature geometry of crises can be detected, but not the temporal arrival. Thus, the framework is not a forecast machine. Forecasting the composition of the future regime is an open question in the rare cases of regime change.

We propose RCEM, a Robust Conversational search EMbedder that is additionally equipped with LLM's query reformulation capability without losing base model's generalization. Unlike prior conversational dense retrieval approaches that learn direct conversation-to-passage matching, RCEM aligns conversations, prepended by special token, to LLM-rewritten queries, while preserving the original embedding space. The unchanged embedding space automatically maps the rewritten-query to the relevant passages. As a result, RCEM (1) reduces overfitting by simplifying the alignment task from long passages to shorter rewritten queries, (2) eliminates the need for conversation-to-passage relevance labels for training, and (3) maintains its original embedding space that allows conversational queries against indexes built by original embedder without rebuilding them. Extensive experiments show that RCEM consistently outperforms prior approaches, achieving up to 30% improvement under distributional shift.

Sequential conformal prediction (CP) provides valid uncertainty quantification under the assumption of residual exchangeability. However, this assumption is often violated in real-world time series due to temporal dependencies and distributional shifts. While recent methods attempt to approximate exchangeability through reweighting, identifying optimal weights remains an open challenge. To address this limitation, we propose DistMatch, a binning-based method that recursively partitions residuals within a binary tree using the Kolmogorov-Smirnov (KS) statistic. We theoretically show that this partitioning induces approximately exchangeable leaves, thereby avoiding the need for reweighting. By applying quantile regression with online updates within each leaf, DistMatch enables locally adaptive inference and improves robustness to distributional shifts. Extensive experiments demonstrate that DistMatch outperforms existing sequential CP methods.

Diffusion models have shown promising performance as data-driven priors for computational imaging, as well as some capacity to detect out-of-distribution (OOD) images. However, existing approaches to OOD detection often require some knowledge of the shifted distribution, fail to detect subtle or localized distribution shifts, and operate on full images, rather than the indirect measurements available in inverse problems. We propose an OOD detection metric based on the Kullback-Leibler divergence between the diffusion prior and the posterior distribution, that (i) does not require any calibration data or knowledge of the shifted distribution, and (ii) can detect whole images as OOD as well as localize OOD patches within an image. Experimentally, we show that this metric can detect subtle yet semantically meaningful distribution shifts, such as the shift from healthy liver CT scans to those with tumors, and generalizes across different types of diffusion models, datasets, and inverse problems. Our code can be found at https://github.com/voilalab/KLIP.

We propose a unified framework for addressing three key challenges of distribution shift: (1) estimating a model's performance on an unlabeled target domain, (2) explaining the shift by identifying the features responsible, and (3) improving the target domain performance. Our method, Entropic Projection Alignment (EPA), aligns the source distribution to the target by matching carefully selected moments while simultaneously minimising the KL divergence from the source. This formulation yields a unique closed-form solution for importance weights, achieving robustness through implicit variance control. Drawing on domain adaptation theory, we establish that moment matching is sufficient for reliable estimation and adaptation, avoiding the need for full density ratio recovery. Extensive experiments, together with strong theoretical guarantees, demonstrate that EPA consistently outperforms state-of-the-art baselines while offering substantial computational efficiency.

Semantic segmentation is crucial for autonomous navigation in off-road environments, enabling precise classification of surroundings to identify traversable regions. However, distinctive factors inherent to off-road conditions, such as source-target domain discrepancies and sensor corruption from rough terrain, can result in distribution shifts that alter the data differently from the trained conditions. This often leads to inaccurate semantic label predictions and subsequent failures in navigation tasks. To address this, we propose ST-Seg, a novel framework that expands the source distribution through style expansion (SE) and texture regularization (TR). Unlike prior methods that implicitly apply generalization within a fixed source distribution, ST-Seg offers an intuitive approach for distribution shift. Specifically, SE broadens domain coverage by generating diverse realistic styles, augmenting the limited style information of the source domain. TR stabilizes local texture representation affected by style-augmented learning through a deep texture manifold. Experiments across various distribution-shifted target domains demonstrate the effectiveness of ST-Seg, with substantial improvements over existing methods. These results highlight the robustness of ST-Seg, enhancing the real-world applicability of semantic segmentation for off-road navigation.

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

Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution. This makes it difficult to determine whether a model has learned generalizable physical dynamics or only performs well under particular settings. We construct a benchmark with 8 physical dynamics, 3 training-data mixtures, and 25 test regimes induced by dynamic-scale and initial-condition complexity shifts, covering in-distribution, distribution-shift, and out-of-distribution settings. We evaluate five physics foundation model architectures and four model variants per architecture (scratch and three pretrained sizes), resulting in 60,000 measurements. Our results show that current physics foundation models behave as conditional rather than universal generalists: their generality depends on the physical regime, temporal scale, initial-condition setting, pretraining, model size, and architecture. Improving the training data distribution only partially mitigates this limitation. Pretraining and scaling are also unable to reliably remove their ability biases. We argue that improving physics foundation models requires moving beyond scaling models or expanding data, toward learning mechanisms that better capture transferable physical knowledge across regimes, temporal scales, and distribution shifts.

Learning-based radio map estimation (RME) plays a critical role in UAV-assisted wireless sensing, enabling tasks such as coverage prediction and network optimization. Most current methods assume an independently and identically distributed (i.i.d.) training and testing setting based on random sampling. However, practical UAV measurements are collected sequentially along feasible trajectories, resulting in highly structured and spatially correlated patterns. This mismatch introduces a sampling distribution shift that increases the intrinsic difficulty of spatial field recovery and compromises the generalization of models trained under i.i.d. assumptions. To mitigate this issue, we propose a trajectory-aware training paradigm based on Stochastic-Triggered Trajectory-Based Sampling (ST-TBS), which preserves trajectory continuity while introducing sampling variability. Moreover, from a statistical perspective, we show that trajectory-based sampling reduces spatial diversity and increases information redundancy compared to random sampling. Extensive experiments on the RadioMapSeer and SpectrumNet datasets demonstrate that models trained with random sampling suffer significant performance degradation under trajectory-based observations, with RMSE increasing from 0.0391 to 0.2632 on SpectrumNet. Conversely, our proposed ST-TBS method effectively reduces the RMSE to 0.0571. These results highlight the necessity of aligning training and deployment sampling distributions for reliable RME.

Predictive models trained on observational data often fail to generalise to the distributions they encounter when deployed, especially when the training data is a product of the system being optimised. Recommender systems are a canonical example: they are trained on interaction logs confounded by the deployed policy, past user behaviour, and platform filtering. As a result, the training distribution differs substantially from the candidate distribution scored at serving time, a gap that makes offline metrics unreliable predictors of online performance. We address the distribution shift problem with a method motivated by causal representation learning (CRL). We propose an information-theoretic disentanglement criterion and prove that its optimum depends only on the causal components of the input. We then derive a tractable variational lower bound that makes the criterion optimisable from finite observational data alone. The scope of our method is narrower than that of much of the CRL literature, in that we target better generalisation under distribution shift, not full identification of all latent causal factors. This narrower target is what makes the method practical, requiring only the existing confounded logs, applying to any standard supervised model, and adding no inference-time cost. Our headline evaluation is an A/B test with millions of users on Spotify, applied to a production ranker for personalised playlist generation. A capacity-matched CRL variant performed on par offline but delivered substantial online gains in listener engagement. Complementary evidence on the public KuaiRand recommendation dataset and a synthetic benchmark with known causal structure shows the same pattern: offline parity with baseline, gains under distribution shift. Across all three settings, adding our causal disentanglement objective yields meaningfully better out-of-distribution generalisation.

A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline logs (Static Context RL) or using a prompt-based simulator (Interactive RL). In this work, we theoretically show that both paradigms are fundamentally limited by context distribution shift--a mismatch between dialogue histories observed during training and those encountered in real conversations. This shift compounds quadratically over turns and severely degrades dialogue quality. Specifically, we attribute this shift to two distinct sources: (i) policy-induced shift, arising from training on static histories rather than self-generated trajectories; and (ii) simulator-induced shift, stemming from discrepancies between simulated and real human behaviors. To address these challenges, we propose Calibrated Interactive RL, a unified framework that couples interactive RL with simulator alignment. By aligning the simulator with human interaction patterns, our approach reduces the sim-to-real gap and mitigates compounding distribution shifts. Experiments across multiple dialogue tasks confirm our theoretical analysis: (i) Interactive RL significantly outperforms the Static Context baseline by mitigating policy distribution shift; and (ii) calibrating simulators with our alignment method further bridges the sim-to-real gap, yielding state-of-the-art downstream performance.

Importance weighting (IW) is a golden solver for joint distribution shift, where the joint distributions differ between the training and test data. To solve this problem, IW estimates test-to-training density ratios as importance weights and reweights the training losses accordingly. Recent advances in dynamic IW (DIW) integrate weight estimation into model training, enabling scalable IW for deep models and achieving strong performance on large modern datasets. Despite its promise, DIW remains limited in two aspects. First, it incurs substantial computational overhead by solving a kernel mean matching (KMM)-induced optimization problem to convergence in every mini-batch. Second, it relies solely on KMM for weight estimation, whereas the IW literature contains diverse estimation methods based on different divergence measures. In this paper, we propose accelerated DIW (ADIW), a unified and efficient IW framework for deep learning under joint distribution shift. ADIW performs a few lightweight projected gradient descent updates that warm-start from previously updated weights, substantially improving efficiency. Moreover, ADIW generalizes DIW into a unified divergence-minimization framework that supports diverse weight-estimation methods in a plug-and-play manner, including those based on the Kullback-Leibler divergence, squared distance, and Wasserstein-1 distance. We establish convergence guarantees for ADIW under mild conditions, and empirical results demonstrate that ADIW achieves state-of-the-art IW performance while being substantially more efficient.

Distribution shift in imitation learning refers to the problem that the agent cannot plan proper actions for a state that has not been visited during the training. This problem can be largely attributed to the inherently narrow state-action coverage provided by expert demonstrations over the full environment. In this paper, we propose a robust offline to adaptive online imitation learning framework that handles the distribution shift problem in a lifelong, multi-phase scheme. In the offline learning phase, we leverage supplementary demonstrations to broaden the state-action coverage of the policy by utilizing a discriminator to effectively train the policy with supplementary demonstrations, thereby enhancing the robustness of the policy to distribution shift. In the subsequent online inference phase, our framework detects the occurrence of distribution shift and conducts self-supervised imitation learning from online experiences to adapt the policy to the online environments. Through extensive evaluations in MuJoCo environments, we demonstrate that our method exhibits better robustness to distribution shift and better adaptation performance to online environments than the baseline algorithms, which indicates superior performance of our framework against the distribution shift.

Robustness, domain adaptation, photometric/occlusion invariance, sensor drift, and alignment style are treated as separate literatures with separate method families. Under label-preserving deployment shift they share one geometric object: the covariance Sigma_task = Cov_{Q_n}(n) of ways inputs can change without changing the label. CORAL, adversarial training, augmentation, metric learning, Jacobian penalties, and alignment constraints are not independent tricks--they are estimators of Sigma_task. Fix that object and the Jacobian penalty is pinned by a matrix Sigma' whose range must cover range(Sigma_task)--the matching principle. We prove optimality in a linear-Gaussian model (Thm. A), necessity of range coverage for any quadratic penalty that zeros deployment drift (Thm. G), and the same dichotomy at global minima (Thm. A_global). Wrong-direction/signal-aligned controls (Lemma C; Cor. E/E) and seven estimators (Lemmas D1--D7), plus label-free TDI, yield a falsifiable recipe when Sigma_task must be learned. Thirteen blocks (ML through Qwen2.5-7B) test matched vs isotropic vs wrong-direction penalties on geometry and deployment drift. Twelve match theory where identifiability holds; Office-31 is a named eigengap failure. Partial passes: geometry can improve without every headline task metric moving. A pilot 7B DPO run (one epoch, 240 pairs): matched style-PMH preserves Style TDI where standard DPO degrades it. We do not claim standard training reaches global minima (assumption (O) is open), that estimated Sigma_task is always identifiable, or dominance on every leaderboard. We claim a falsifiable design recipe: estimate Sigma_task, match Sigma', run the controls, report task and geometry separately.

Climate emulation is an out-of-distribution (OOD) projection task. This is precisely the challenge where modern Machine Learning (ML) methods are most prone to failure. Consequently, while current ML emulators trained on present climate achieve high in-distribution performance, their future reliability under the inevitable distribution shifts of a changing climate remains a critical, poorly understood blind spot. Addressing this challenge requires a fundamental shift in how we understand, evaluate, and design climate emulators. In this work, we first confirm that climate change drives a statistically significant and progressively growing shift in atmospheric state distributions, rendering standard evaluation protocols insufficient. We empirically establish that seasonal variation serves as an effective proxy for these long-term climate shifts, providing access to $\textit{real-world}$ distribution shifts without recourse to heuristics like synthetic perturbations. Motivated by this link, we introduce a novel evaluation framework that leverages seasonal shifts as a rigorous, zero-overhead testbed for emulator robustness. Our systematic characterisation confirms that current state-of-the-art hybrid-ML emulators degrade significantly under these realistic shifts. Finally, we chart a path forward by identifying compositional generalisation, the ability to form novel combinations from observed elementary components, as a principled route towards robust climate emulation. We demonstrate that physically motivated decompositions substantially improve OOD performance with only modest trade-offs against in-distribution performance, providing an avenue towards ML-driven climate emulators robust to an unknown future.

Mechanistic interpretability aims to explain a model's behavior by identifying causally responsible internal structures. Dictionary-based explainers such as sparse autoencoders and transcoders are a primary tool, but their faithfulness under out-of-distribution (OOD) shift has received little systematic attention. We show that distribution shift rotates the subspace that the model actively uses, misaligning the explainer's dictionary trained on in-distribution (ID) activations. We formalize this misalignment as the faithfulness gap, a geometric distance between the ID dictionary and the OOD-active subspace, and show that it controls OOD faithfulness degradation. To reduce this gap, we propose the Geometry-Adaptive Explainer (GAE), which realigns the explainer's dictionary with the OOD-active subspace while preserving the original feature structure. This requires only unlabeled OOD activations and no gradient updates. We prove that GAE improves over the unadapted ID explainer, with excess loss bounded quadratically by the second-moment shift. Empirically, GAE even matches or surpasses all training-based baselines in causal faithfulness across multiple models and OOD settings.

Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployment. In this paper, we propose a framework to analyse and quantify the distributional robustness of neural networks by studying the interactions between layer weights and activations. We model these interactions using Bernoulli distributions, using the separation between classes as a diagnostic proxy for robustness. We demonstrate the usefulness of this framework through models trained on CIFAR-10 and ImageNet. We show that our proposed metrics can distinguish between networks that have memorised their training data and those that have not. We also perform analogous experiments in the activation space and find that the same properties do not hold up. Additionally, we investigate the behaviour of our metrics under various distribution shifts and show that these shifts reduce separation under our path-based diagnostics. Our results suggest that this framework provides useful model-level diagnostics of representation structure and robustness.

The demand for unmanned aerial vehicle (UAV)-based image acquisition and analysis has surged, with UAVs increasingly utilized for semantic segmentation tasks. To meet the real-time analysis requirements of UAV remote sensing missions, performing onboard computation and making decisions based on the results is a natural approach. However, deploying semantic segmentation on resource-constrained UAV platforms presents two significant challenges: 1) hardware constraints limit the ability of UAVs to perform real-time semantic segmentation, and 2) environmental variations during flight cause data distribution shifts, deviating from the original training data. To address these issues, this paper introduces SkySeg, a heterogeneous multi-UAV air-air cooperation framework that integrates computer vision and flight pattern to enable onboard semantic segmentation using low-cost sensors. SkySeg employs an efficient information fusion inference method, combining low-definition, wide-area images with high-definition, focused-area images. Additionally, it incorporates a cross-device test-time adaptation (TTA) strategy to enhance segmentation performance in dynamic environments by collaboratively addressing distribution shifts of test data streams across UAVs. Experimental results demonstrate that our SkySeg framework accelerates inference latency by approximately 3.6x, improves onboard segmentation accuracy by 5.91%, and achieves a 10.91% average accuracy gain in the wild.

We introduce FLUXtrapolation, a benchmark for extrapolating ecosystem fluxes under progressively harder distribution shifts. Ecosystem fluxes are central to understanding the carbon, water, and energy cycles, yet they can only be measured directly at sparsely located measurement towers. Producing global flux estimates therefore requires training models on observed sites using globally available covariates and predicting in unobserved regions, that is, upscaling. Flux upscaling is a challenging domain generalization problem that is affected by a shift in covariate distribution across climates, ecosystem types, and environmental conditions, as well as by conditional shift: important drivers remain unobserved at global scale. We provide a quantitative analysis of both these shifts in $P_X$ and $P_{Y\mid X}$. FLUXtrapolation is designed based on domain expertise on flux upscaling: it defines temporal, spatial, and temperature-based extrapolation scenarios and evaluates performance across held-out domains, temporal aggregations, and tail errors. In a pilot study, we find that baselines perform similarly under median hourly RMSE, but separate under the proposed tail-focused and multi-scale evaluation. FLUXtrapolation therefore poses a realistic and thus relevant challenge for machine learning methods under distribution shift; at the same time, progress on this benchmark would directly support the scientific goal of improving flux upscaling.

We introduce DeRegiME -- Deep Regime Mixture of Experts -- a direct multi-horizon probabilistic forecaster that separates latent uncertainty regimes from the underlying signal and softly assigns each forecast location to learned recurring regimes using a sparse variational Gaussian process (GP) whose nonstationary regime-mixing kernel and Student-t likelihood combine per-regime sub-kernels and noise processes via a shared gate. This yields a single sparse-GP posterior, not a mixture of GP experts. DeRegiME addresses a key limitation of neural forecasters: point forecasts discard residual uncertainty, and probabilistic heads -- whether single marginals, uninterpreted mixtures, quantile sets, or diffusion samples -- rarely expose the regime structure of the residual. Yet distribution shift in noisy heteroskedastic time series may be abrupt, gradual, or horizon-dependent and often appears in residual uncertainty rather than the conditional mean. DeRegiME yields an interpretable mean-residual-noise decomposition with a direct-sum feature-space representation that anchors regimes as clusters of residual similarity whose transitions surface as implicit changepoints. The effective number of regimes is pruned by the stick-breaking gate. We prove kernel validity and predictive-density propriety, and across ten benchmarks and three encoder grids DeRegiME improves negative log predictive density (NLPD) by 20.3% over the strongest encoder-matched baseline, a DeepAR/GluonTS-style dynamic Student-t head, with parallel gains on CRPS (3.0%) and MSE (4.7%). Improvements are consistent across all datasets, which span abrupt, gradual, and seasonal shifts.

Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution shifts caused by changing network conditions. Existing robustness-enhancing approaches are commonly coupled to specific model architectures or data settings, fail to generalize to state-of-the-art raw-byte-based NTC models, or incur significant training overhead. In this paper, we propose UniAlign, a novel model-agnostic framework that improves the robustness of deep learning-based NTC models under distribution shifts. UniAlign combines \emph{domain alignment fine-tuning}, which encourages the learning of domain-invariant traffic representations across heterogeneous network conditions, with \emph{stable model ensembling}, which enhances inference robustness by aggregating checkpoints within a flat loss region. The framework can be seamlessly integrated into existing supervised NTC models without requiring specific feature modalities or introducing non-constant additional training costs. We evaluate UniAlign on three public datasets covering diverse distribution shifts, including encryption schemes, data collection devices, and attack behaviors. Experimental results on two representative NTC models demonstrate that, compared with standard training, UniAlign improves average classification accuracy by 2.51% and average F1 score by 2.71%, outperforming the strongest baseline by 1.45% in accuracy and 1.69% in F1 score, while requiring only 12.4%--53.9% of the training time of all NTC-specific baselines.

Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled training examples, unlabeled test examples, and must make correct predictions on the test set but is allowed to abstain from predicting on out-of-distribution points. Their results rely on ${\cal L}_2$ sandwiching approximations, a strong requirement that leads to poor bounds for several basic function classes such as DNF formulas. Here, we show that the weaker notion of ${\cal L}_1$ sandwiching suffices for efficient PQ learning. As a consequence, we obtain the first quasipolynomial-time PQ learning algorithm for DNFs under the uniform distribution and essentially match the guarantees known for ordinary PAC learning. More broadly, our bounds provide exponential improvements for several classes including constant depth circuits and constant degree polynomial threshold functions. Our main technical ingredient is Iterative Chow Filtering, a new procedure that uses low-degree Chow parameters to identify and remove test points incompatible with the training distribution.

Test-time adaptation (TTA) has recently emerged as a promising approach for improving time series forecasting (TSF) under distribution shift. Existing TSF-TTA methods differ in how they utilize revealed targets, yet the resulting adaptation protocols remain heterogeneous and lack a clearly unified formulation. To address this issue, we revisit TSF-TTA from the perspective of protocol cleanliness and propose an adaptation protocol based solely on matured ground truth, yielding a more principled setting for adaptation. Under this protocol, we further diagnose existing adapters in the frequency domain and find that their prediction corrections often exhibit limited and weakly structured spectral modifications. Motivated by this diagnosis, we propose Frequency-Aware Calibration (FAC), a lightweight calibration method that directly parameterizes prediction corrections in the frequency domain. Across diverse datasets, forecasting horizons, and source forecasters, FAC achieves competitive and consistent performance while requiring substantially fewer trainable parameters than the compared TSF-TTA adapters.

A unified framework for learning under covariate shift is presented, in which a constrained density-ratio network approximates the Radon-Nikodym derivative $r^\star = dP/dQ$ and feeds an anytime PAC-Bayes generalization certificate. A change-of-measure identity decomposes the gap between target risk and importance-weighted source risk into a ratio-bias term governed by $\|r_θ- r^\star\|_{L^2(Q)}$ and a generalization-gap term governed by the variability of the weighted loss. Normalization and moment-matching identities are enforced as hard integral constraints through an augmented-Lagrangian scheme, with a second-moment penalty controlling the effective sample size. PAC-Bayes is instantiated on the weighted risk in a fixed-time regime that yields Bernoulli-KL bounds, identifies the network-weighted Gibbs posterior as the unique KL-regularized minimizer, and quantifies stability under $L^2(Q)$ perturbations of the learned ratio, and is then strengthened by geometric peeling to an anytime certificate uniform in $t \geq t_{\min}$. A pre-registered two-campaign protocol combining a patch test against analytic ground truth with a real-data deployment validates the framework: the network produces calibrated ratios, reduces target $0/1$ loss against unweighted ERM and classical direct ratio-estimation baselines, and attains the anytime certificate. A single fixed-time coverage failure is recorded, with per-split coverage aligning one-to-one with the magnitude of the label shift, confirming that the covariate-only assumption is operationally tight rather than a defect of the certificate.

Visual anomaly detection (AD) for industrial inspection is a highly relevant task in modern production environments. The problem becomes particularly challenging when training and deployment data differ due to changes in acquisition conditions during production. In the VAND 4.0 Industrial Track, models must remain robust under distribution shifts such as varying illumination and their performance is assessed on the MVTec AD 2 dataset. To address this setting, we propose a training-free and class-agnostic anomaly detection pipeline based on the work of SuperAD. Our approach improves generalization through several modifications designed to enhance robustness under distribution shifts. These adaptations include using a DINOv3 backbone, overlapping patch-wise processing, intensity-based augmentations, improved memory-bank subsampling for better coverage of the data distribution, and iterative morphological closing for cleaner and more spatially consistent anomaly maps. Unlike methods that rely on class-specific architectures or per-class hyperparameter tuning, our method uses a single architecture and one shared hyperparameter configuration across all object classes. This makes the approach well suited for industrial deployment, where product variants and appearance changes must be handled with minimal adaptation effort. We achieve segmentation F1 scores of $62.61\%$, $57.42\%$, and $54.35\%$ on test public, private, and private mixed of MVTec AD 2 respectively, thereby outperforming SuperAD and other state-of-the-art methods. Code is available at https://github.com/LukasRoom/SuperADD.

Automated CT triage requires models that are simultaneously accurate across diverse pathologies and reliable under institutional shift. While Vision Transformers provide strong visual representations, many clinically significant findings are defined by quantitative imaging biomarkers rather than appearance alone. We introduce JANUS, a physiology-guided dual-stream architecture that conditions visual embeddings on macro-radiomic priors via Anatomically Guided Gating. On the MERLIN test set (N=5082), JANUS attains macro-AUROC 0.88 and AUPRC 0.74, outperforming all reproduced baselines. It generalizes to an external dataset N=2000; AUROC 0.87), with the largest gains on findings defined by size and attenuation as well as improved calibration on both datasets. We further quantify prediction suppression using the Physiological Veto Rate (PVR), showing that under domain shift JANUS reduces high-confidence false positives substantially more often than true positives. Together, these results are consistent with physically grounded conditioning that improves both discrimination and reliability in CT triage. Code is made publicly available at github repository https://github.com/lavsendahal/janus and model weights are at https://huggingface.co/lavsendahal/janus.

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling. We propose a stage-wise preference optimization framework for hallucination reduction through targeted multimodal data construction. Rather than directly optimizing on generic instruction-following data, our approach progressively constructs hallucination-focused preference pairs near known failure boundaries. The framework emphasizes ambiguous spatial orientation, object relationships, OCR uncertainty, and adversarial false-premise training. Hallucinated negatives are generated through minimally perturbed yet visually inconsistent alternatives, enabling Direct Preference Optimization (DPO) to better separate grounded reasoning from plausible hallucination. Experiments on open-source benchmarks and real-world multimodal evaluation scenarios demonstrate improved grounding consistency, reduced hallucination, and more informative grounded responses. Cross-model qualitative evaluation further shows that the proposed multimodal LLM DPO framework produces more visually grounded responses than several frontier proprietary VLMs, such as in ambiguous spatial reasoning and adversarial false-premise settings. The results suggest that hallucination may arise not only from limited model capacity, but also from inherent tendencies of autoregressive probabilistic generation to favor linguistically plausible continuations under weak visual grounding. Future work may explore physical consistency modeling, uncertainty-aware multimodal reasoning, and architectural alternatives beyond standard autoregressive decoding.

Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typically adopt a task-based formulation, where the data stream is partitioned into a sequence of discrete tasks with pre-defined boundaries. However, such assumptions rarely hold in real-world environments, where data distributions evolve continuously and task identity is often unavailable. To better reflect realistic non-stationary environments, we revisit continual graph learning from a task-free perspective. We propose a unified formulation that models the data stream as a time-varying mixture of latent task distributions, enabling continuous modeling of distribution drift. Based on this formulation, we construct \emph{DRIFT}, a benchmark that spans a spectrum of transition dynamics ranging from hard task switches to smooth distributional drift through a Gaussian parameterization. We evaluate representative continual learning methods under this task-free setting and observe substantial performance degradation compared to traditional task-based protocols. Our findings indicate that many existing approaches implicitly rely on task boundary information and struggle under realistic task-free graph streams. This work highlights the importance of studying continual graph learning under realistic non-stationary conditions and provides a benchmark for future research in this direction. Our code is available at https://github.com/UConn-DSIS/DRIFT.

Neural operators learn to map initial conditions to the terminal solution of partial differential equations (PDEs), providing a surrogate for the full operator mapping. This enables rapid prediction across different input configurations. While recent neural operator architectures have demonstrated strong performance on diverse PDE tasks, their behavior under structured distribution shifts remains insufficiently understood. To investigate this, we study operator learning in a wave propagation setting governed by a one-dimensional variable-coefficient wave equation, using two representative architectures, the Fourier Neural Operator (FNO) and the Deep Operator Network (DeepONet). To examine their generalization under distribution shifts, we consider structured out-of-distribution (OOD) settings that independently vary input frequency and coefficient smoothness. The results show that under smoothness shifts, both models maintain stable performance, with FNO achieving lower error. In contrast, under frequency shifts, FNO exhibits a sharp increase in error under unseen high-frequency inputs, whereas DeepONet shows milder degradation despite higher overall error. Our analysis reveals that these differences arise from how each architecture represents and responds to variations in frequency structure. Together, these findings highlight a fundamental gap between strong in-distribution performance and generalization under distribution shifts in operator learning, underscoring the role of architectural representation bias in developing more reliable neural operators for physics-based PDE simulations beyond the training distribution.

Despite the burgeoning body of work on distribution shifts, provenance shift-where the relationship between data source and label changes at deployment-remains poorly understood and under-addressed. In this paper, we establish a formal connection between provenance shift, counterfactual invariance, and invariant learning to derive a learning objective for robustness. We then introduce \textsc{DeconDTN-Toolkit}, a specialized evaluation and remediation suite designed to simulate provenance shifts of varying degrees while maintaining the training protocol and the infrastructure of existing benchmarks. We reveal the vulnerability of Empirical Risk Minimization under provenance shift, introduce a robust out-of-distribution performance indicator, and conduct a comprehensive evaluation on existing algorithms. Our work provides both the theoretical grounding and the practical tools necessary to characterize the problem of confounding by provenance, and implementations of methods to mitigate it.