Overview

Test-time adaptation studies how pretrained models can adjust to changing data during deployment, improving reliability when target labels or retraining are unavailable. Common approaches use entropy minimization, pseudo-labels, normalization or feature-statistics alignment, and lightweight prompts, adapters, caches, or memory; gradient-free methods aim to reduce compute and memory costs. Work spans image corruptions and domain shifts, medical imaging, time-series forecasting, language-model reasoning, and robotics. A central tension is that noisy self-generated signals can cause error accumulation or forgetting, so methods must determine when adaptation is useful and how to evaluate its benefits beyond average accuracy.

Latest papers

342 papers40 papers in the last four weeks, down 17% on the four weeks before. 0.3% of all new papers.

Oct 20, 2026

Why Static Probes Fail: Context Determines Deception Feature Composition

With increasing autonomy, Large Language Models (LLMs) may engage in deceptive behaviors, such as scheming to pursue misaligned goals or sandbagging to escape oversight. Monitoring outputs alone is insufficient, as models can produce seemingly benign responses while harboring misaligned internal objectives. While mechanistic approaches like linear probing are promising, they rely on the assumption that deception corresponds to a single direction in representation space. We demonstrate that such single-direction probes fail to generalize across diverse deception scenarios. To bridge this gap, we propose representing deception as a multi-dimensional subspace rather than a single direction. Our method utilizes iterative orthogonal decomposition to identify complementary directions that capture distinct facets of deceptive intent. To effectively leverage these directions for detection, we find that static combinations prove brittle due to strong domain dependence across different scenarios. We therefore introduce a domain-adaptive gating mechanism that dynamically composes the extracted directions through few-shot adaptation at test time. With only 10 examples, our approach achieves an average AUROC of 0.97 and 94% recall at 5% FPR across all evaluated datasets, substantially outperforming existing methods.
Oct 20, 2026

Test-time Adaptation for Point Cloud Denoising under Unseen Noise

Although deep learning-based point cloud denoising methods have demonstrated impressive results in recent years, their effectiveness usually degrades substantially in real-world scenarios where the noise distribution of test point clouds deviates from that of the training set. To address this challenge, we propose a test-time adaptive denoising (TTAD) framework that enables existing denoising approaches to adapt to unknown noise patterns at test time without relying on additional supervision or retraining from source data. Taking a pre-trained denoising model and a test noisy point cloud as input, TTAD first employs a residual-driven noise modeling (RDNM) module to estimate the sample-specific noise distribution through analyzing the deviation between the noisy input and its pseudo-clean version denoised by the initial model. Then, a noise-aware contrastive adaptation (NACA) module is designed to build sample-specific noisy-noisier test-time training pair from the denoised point cloud, and update the model parameters over a few adaptation steps per sample at test time through contrastive learning. Furthermore, TTAD naturally extends to a continual TTAD (CTTAD) setting, facilitating efficient progressive refinement across sequential test samples with consistent noise distributions, while reducing the computational cost per sample. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach significantly improves the generalization ability of existing denoising models under unseen noise, achieving superior performance across multiple evaluation metrics.
Oct 17, 2026

IntriAdapt: Generalizable Intrinsic-Guided Test-Time Adaptation for Metric Geometry Estimation

Recovering metric 3D geometry from images is fundamentally ill-posed due to perspective projection ambiguity. Current geometry models incorporate supplied or predicted intrinsics during inference, but do not use them to supervise model adaptation. To refine these predictions, test-time adaptation (TTA) typically relies on external depth measurements. In this paper, we instead use camera intrinsics as an output-side geometric verifier. Comparing the point cloud's viewing rays with those defined by the known intrinsics yields a direct measure of geometric inconsistency. We propose IntriAdapt, a TTA framework that minimizes this closed-form geometric residual. By optimizing a lightweight LoRA adapter on a frozen geometry foundation model, our method aligns the prediction with the specific camera model without depth sensors or external priors. We further extend this approach to video sequences, demonstrating that adapting a short sequence generalizes to other sequences captured by the same camera. The adapted model processes held-out images in a feed-forward pass, without repeating optimization for each frame. Experiments on ten single-image and seven sequence benchmarks across multiple base models show that IntriAdapt consistently outperforms both unadapted and oracle-intrinsics baselines in metric accuracy and relative geometry.
Oct 17, 2026

Transport What Shares the Conduction Pathway: Normal-Anchored SPD Geometric Transport for Source-Free Patient Adaptation of Holter and Patch ECG

Continuous electrocardiogram (ECG) streams are dominated by normal beats (87.9-98.6% of the label-free adaptation prefix in our four databases), and patient-specific waveform distortion is not shared by every beat class; under this combination, source-free and test-time adaptation methods that assume class-balanced target batches collapse. We propose Normal-Anchored Geometric Transport (NAGT, GA_NS), which estimates a closed-form symmetric positive-definite congruence map from label-free normal anchors in the first 5 min of each recording and applies it only to the normal and supraventricular prototypes, keeping the ventricular and fusion prototypes fixed. Decision rules were set on MIT-BIH and the rate-invariant RR head was adopted after the development databases (INCART, SVDB) had been opened; the frozen model was then evaluated once under a pre-specified locked evaluation protocol on the held-out Icentia11k chest-patch cohort. In 493 patients (973 recordings, 3,615,388 evaluated beats), NAGT raised the arrhythmia macro-F1 J from 34.5% to 48.7% (ΔJΔJ = +14.1 [+8.6, +19.3] pp; non-AF 43.9% to 59.8%) and outperformed all five Holm-adjusted comparators, including AdaBN, Tent and T3A. In post hoc analyses of the frozen outputs, ventricular false alarms fell by 68% (41.1 to 13.2 per hour) and 98.3% of normal beats stayed outside the alarm classes. Adaptation takes 5.8 ms per record without back-propagation.
Oct 16, 2026

Hidden Trajectories Don't Lie: Correcting Corruption Drift for Test-Time Adaptation

Test-time adaptation (TTA) adapts pretrained models to distribution shifts encountered during deployment. However, most existing methods rely on the weight representations of the final layer or signals derived from the model's output probability distribution. We study hidden trajectories: the ordered sequence of intermediate representations produced across a deep neural network. We observe that clean and corrupted trajectories become more separable as corruption severity increases. We introduce Drift-TTA, which adds zero-initialized low-rank adapters to a frozen backbone and trains them to align corrupted hidden trajectories with those from cleaner inputs. The approach supports two variants: a source-dependent version trained with clean targets, and a source-free setting that learns from corrupted images at different severities. We develop an online TTA approach that freezes the backbone and adapters while updating a scalar gate to control adaptation strength. We further cast trajectory alignment as MAP inference under a Gaussian observation model and derive a KL-based transfer bound characterizing test-time trajectory misalignment in terms of offline residual error, residual dimensionality, and distribution shift between offline and test corruptions. We evaluate Drift-TTA on CIFAR-10-C, CIFAR-100-C, and ImageNet-C using supervised ViTs and CLIP models. On CIFAR-100-C at severity 5, our source-free online approach improves accuracy over no TTA by 13.3 percentage points with ViT-B/16 and 11.6 percentage points with CLIP ViT-B/16, reaching 74.9% and 47.4%, respectively. Under the same setting, prior TTA baselines yield ECEs of 18.00% for ViT and 14.70% for CLIP, while our approach reduces them to 9.53% and 5.77%, respectively. These results demonstrate that hidden trajectory alignment provides an effective signal for both offline correction and lightweight online test-time adaptation.
Oct 16, 2026

Expand-and-Prune: Test-Time Candidate-Space Adaptation for End-to-End Autonomous Driving

Candidate-based end-to-end driving planners reason over a finite set of trajectory hypotheses. However, for sparse planners, a limited candidate set may provide insufficient support for scene-relevant maneuvers, while fixed downstream candidate budgets do not account for prediction uncertainty. To address these challenges, we introduce Expand-and-Prune, a test-time framework that jointly adapts candidate support and capacity without updating learned parameters. The framework expands the native candidate set using semantic driving intent and temporally propagated predictions and then uses uncertainty in intermediate trajectory scores to adaptively prune the resulting candidates. Across four heterogeneous candidate-based planners and four benchmarks, Expand-and-Prune consistently improves planning performance. It achieves state-of-the-art results on LangAuto, increasing the Driving Score from 68.2 to 75.9, while providing further improvement on Bench2Drive, Fail2Drive, and NAVSIMv2, with particularly strong improvements in out-of-distribution scenarios. Moreover, in its full instantiation, 72.5% of selected trajectories originate from the newly introduced intent-guided or temporal candidates, confirming that candidate-space expansion provides useful hypotheses beyond those generated natively by the planner. The code is available at https://github.com/iis-esslingen/Expand-and-Prune.
Oct 16, 2026

Advancing Sentence-Level Dysarthric Audio-Visual Speech Recognition via Test-Time Adaptation

Dysarthric audio-visual speech recognition (DAVSR) enhances performance by integrating complementary visual cues. However, existing research is largely confined to word-level tasks with limited vocabularies, which severely restricts real-world communication for dysarthric speakers. Furthermore, performance remains heavily dependent on supervised fine-tuning with speaker-specific data; significant variations in age, etiology, and severity cause traditional methods to struggle with unseen speakers. To address these domain shifts and the scarcity of continuous multimodal resources, we first introduce a "source speech search-segmentation" pipeline to construct a structured sentence-level corpus from raw CDSD videos. We then propose the use of unsupervised Test-Time Adaptation (TTA) for sentence-level DAVSR using Sequential-level Generalized Entropy Minimization (SGEM). Our evaluations across the state-of-the-art AV-SUPERB and ViSpeR frameworks demonstrate that TTA consistently alleviates Character Error Rate (CER) degradation for unseen pathological speakers. Paired t-tests verify that these improvements are statistically significant (p < 0.05), highlighting TTA as a promising paradigm for advancing speaker-adaptive assistive speech interfaces.
Oct 15, 2026

T2-z: Test-Time Optimization of Environment Latents for Robotic World Models

Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties such as friction and mass to human-defined environmental rules. We introduce T2-Z for test-time optimization of environment latents, which augments a robotic world model with a learnable environment latent to condition world predictions. This compact latent captures underlying environmental variation without supervision of what environmental factors exist or what values they take. During training, T2-Z alternates between two stages: a world-model optimization stage that fixes the latents and learns general action-conditioned dynamics across environments; and an environment-latent optimization stage that freezes the world model and optimizes the conditioning latents, allowing latent structure to emerge purely through world prediction. At test time, the world model remains frozen and a newly initialized environment latent is optimized from one or more test-time interactions, adapting the model to previously unseen environmental configurations. Across 7 simulated settings and 4 real-world robotic tasks, T2-Z reduces object prediction error metric from 15.20 to 7.00 and raises action success from 33.73% to 72.96%. Its emergent latents capture structured representations of individual and compounded factors across diverse visual scenes. Ablations further show that T2-Z can efficiently infer environment latents from as little as a single test-time interaction trajectory.
Oct 15, 2026

CF-NODE: Counterfactual Spatial Node Intervention for Test-Time Adaptation Under Domain Shift, Evaluated Across Five Diabetic Retinopathy Datasets

Automated fundus-based diabetic retinopathy (DR) grading can substantially expand screening capacity, but source-trained models degrade sharply across different cameras, clinics, and patient populations. Existing test-time adaptation methods depend on entropy minimization or target information accumulated from image batches and streams. These mechanisms can reinforce confidently incorrect predictions and break down when clinical images arrive independently. We introduce CF-NODE, a novel counterfactual test-time adaptation framework for cross- domain DR grading. Instead of trusting prediction confidence or estimating a target distribution, CF-NODE asks how each prediction responds under a controlled intervention on the evidence supporting it. CF-NODE ranks internal spatial nodes using model-derived attention, feature magnitude, and node-set similarity, progressively attenuates the highest-ranked nodes, and uses the stability of the resulting expected-grade response to apply a bounded calibration of the predicted grade distribution. The framework is fully frozen and adapts every image independently using only geometric views and a fixed source-derived prior, requiring no target-derived information or model updates. We evaluate CF-NODE on five external DR datasets under repeated-seed evaluation against TENT, EATA, SAR, and T3A. CF-NODE outperforms all four methods with statistically significant improvements over the second-best method, improves AUC on every target domain, and attains the highest average AUC and macro-F1, delivering stronger grade discrimination together with more balanced recognition across DR severity levels. These results demonstrate that counterfactual intervention sensitivity provides consistent and deployment-ready domain robustness for single-image clinical inference.
Oct 15, 2026

SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token Routing

Test-time adaptation (TTA) mitigates the performance degradation of source-pretrained models on unlabeled test data under distribution shifts. Recent backpropagation-free token-purging methods address 3D point cloud distribution shifts by filtering unreliable tokens. However, their reliance on predefined purge-size candidates requires multiple forward passes per sample and increases inference cost. We propose SATOR (Sample-Adaptive TOken Routing), a source-free and backpropagation-free 3D TTA framework that eliminates this search by deriving both the partitioning threshold and routing decision directly from each sample. SATOR computes token abnormality scores from complementary attention and geometric relation graphs. It then derives a sample-specific partition into retained and pruned tokens via Otsu-based separability, without evaluating candidate sizes. Keep-ratio-calibrated routing then selects the pruned prediction only when its entropy, penalized by the keep ratio, is lower than that of the original prediction. Experiments on ModelNet40-C, ScanObjectNN-C, and ShapeNet-C demonstrate that SATOR achieves state-of-the-art accuracy on three 3D corruption benchmarks.
Oct 14, 2026

MMLA-RSI: Recursive Self-Improvement through RTT and RTMA

An agent can improve its behavior within an unresolved problem by changing how it acts and which experience it retains. We propose MMLA-RSI, a recursive self-improvement scheme with two implementations in Memory-Mediated Learning Architecture: Reasoning-Time Training (RTT) changes the policy state ΦΦ, while Reasoning-Time Memory Adaptation (RTMA) changes authoritative memory MM. Each route also makes its adaptation method an object of improvement. A current numerical updater trains the policy proposing its successor; a current memory manager chooses the records available to the process proposing its successor. An independently admitted successor takes over the same role in the next generation. We give bounded executable rule languages, shared task/proposal interfaces, and one algorithm for either route or their composition. The RTT instance changes scalar schedules in a clipped-momentum update. The RTMA instance chooses NULL or a complete-row write with possible eviction. A fixed interpreter, trusted committer, and independent evaluator bound what can change. State versions, read closures, and conditional properties describe causal execution, accepted transitions, and finite work. Existing numerical-component studies motivate the construction. In four-candidate program selection, retaining LARC feedback updates reduces expected error by 24.65 and 36.65 percentage points for two trained initializations. In chronological continuous-integration replay, feedback binding is positive while retention increases loss. Completed SQL studies improve substantially over an unadapted substrate but do not establish the required additional online benefit. These results characterize their declared components. The two recursive routes and their joint realization are specified here; their beneficial recursive chains and discovery efficiency remain to be evaluated.
Oct 14, 2026

On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs

Vision-language models suffer significant accuracy drops under common corruptions. While test-time adaptation (TTA) successfully mitigates these shifts in CLIP-like contrastive models, its application to generative multimodal large language models (MLLMs) remains underexplored and uniquely challenging due to their sequential token generation. In this work, we demonstrate that representation-based TTA fails to recover performance in MLLMs. Our experiments reveal that even when violating standard TTA assumptions by leveraging target data offline, sample-blind feature alignment recovers only marginal accuracy. We attribute this failure to the nature of corruption shifts: unlike CLIP-like architectures, which benefit from a shared domain-shift direction within a single pooled classification embedding, MLLM visual token sequence shifts are nearly orthogonal and span the full embedding space.These findings bound what any sample-blind, position-shared correction at a single encoder site can achieve, establishing that representation-space interventions alone might be insufficient to ensure corruption robustness in MLLMs.
Oct 14, 2026

Frustratingly Easy Majority Voting Using Length Conditioning

Majority Voting (MV) is a simple and widely used strategy which improves the reasoning accuracy of Large Language Models (LLMs) by allocating additional inference-time computation. Specifically, in MV multiple Chain-of-Thoughts (CoTs) are independently sampled and the most frequent final answer is selected. In this work, we propose Length-Conditioned Majority Voting (LCMV), a Test-Time Training approach which improves MV leveraging an empirical observation that has recently been established in several studies: longer CoTs tend to be associated with a lower probability of correctness. We formulate this inductive bias as a length-conditioned prior probability, which is modeled by a simple logistic function. Moreover, we adapt this prior at test time using only unlabeled testing data and without fine-tuning the LLM. Finally, the adapted prior is used to weight the vote of each sampled answer. Extensive experiments across multiple LLMs and reasoning benchmarks show that LCMV consistently improves over both standard MV and existing length-based and confidence-based aggregation strategies, while retaining the simplicity and model-agnostic nature of MV. Our code is available at: https://github.com/aimagelab/LCMV.
Oct 13, 2026

PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning

Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning. We introduce PaceReasoner, a label-free test-time reinforcement learning framework that uses a model's LONG responses to improve its SHORT-mode accuracy. Both modes share a trainable policy, creating a need for reliable supervision, sufficient SHORT training samples, and continued LONG responses to guide learning. PaceReasoner combines all-response and LONG-only answer consensus through progressive, confidence-weighted supervision. A behavior reward gradually shifts from encouraging SHORT exploration to rewarding agreement with LONG answers, while a ratio controller regulates the balance between modes. Across three model backbones and four benchmarks, PaceReasoner improves average SHORT accuracy over the baselines by 7.4--13.5 percentage points, with fewer than 25 reasoning tokens per response on average. Ablations support the key components, and cross-dataset results demonstrate transfer beyond the adaptation set.
Oct 11, 2026

Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement

Movable agents, such as autonomous vehicles and robots, should be able to autonomously adapt their pre-trained object recognition models to new environments without human annotations. While existing test-time adaptation (TTA) methods address label-free model adaptation, they typically treat test data as independent snapshots, without constructively exploiting a rich, unique source of supervision: the significant variance in prediction quality as an agent observes the same object from different distances and viewpoints. To capitalize on this, we propose MoCaFe, a model-agnostic and hyperparameter-insensitive paradigm that leverages motion-induced prediction variance for unsupervised adaptation. Specifically, we first develop mobility-calibrated filtering of pseudo-labels, which constructs reliable pseudo-labels by fusing cross-view predictions using inverse-variance weights. The filtered pseudo-labels then guide the selection of ``hard samples'' for effective learning. To further suppress pseudo-label corruption, we introduce p-MoCaFe, an optional extension that uses a public dataset to assign weighting factors to data samples, yielding an estimator of the clean loss with bounded bias. Extensive experiments on autonomous driving (nuScenes, KITTI) and embodied-agent datasets show that MoCaFe significantly outperforms state-of-the-art TTA schemes, achieving up to approximately 20% accuracy gain.
Oct 11, 2026

Generalizable fetal brain biometry via adaptive artificial intelligence

Fetal brain biometry provides a quantitative basis for assessing prenatal growth and identifying congenital brain abnormalities. However, comprehensive assessment remains limited by labor-intensive manual measurements and automated models that lose accuracy across imaging sequences and institutions. We introduce BioTTA, an anatomically guided test-time adaptation framework that measures 11 fetal brain biometrics from reconstructed three-dimensional magnetic resonance images. BioTTA adapts pretrained models to individual unlabeled volumes using geometric consistency and atlas priors, without access to source images. In a retrospective study across five centers in China and Switzerland, BioTTA improved measurement accuracy across three out-of-distribution datasets and two network architectures. It reduced mean absolute measurement errors by 46-82% relative to the corresponding models without adaptation, achieving errors similar to those of supervised fine-tuning. Its measurements were mapped onto normative growth trajectories derived from expert annotations, enabling gestational-age-specific assessment through a web-based reporting platform. Across four disease cohorts, the platform achieved 82.1-95.0% accuracy in binary detection of ventriculomegaly or cerebellar abnormalities, with performance similar to that of a senior radiologist. BioTTA provides a practical foundation for standardized fetal brain biometry across heterogeneous imaging settings, supporting scalable prenatal growth assessment and quantitative evaluation of brain abnormalities.
Oct 11, 2026

Harnessing SPAD Noise: Test-Time Gated Attention for Indoor Depth Estimation

Monocular depth estimation (MDE) has emerged as a cost-effective alternative to hardware-dependent 3D sensing modalities, yet predicting precise metric depth remains a persistent challenge due to intrinsic scale ambiguity, edge bleeding, and limited zero-shot generalization in unseen environments. Recent multi-modal approaches incorporate 1D/3D Single-Photon Avalanche Diode (SPAD) data to resolve these ambiguities, but they mainly treat SPAD noise as a harmful artifact required for denoising or leave the noise ignored. In this paper, we present an essentially different insight: native SPAD noise is an informative prior that implicitly encodes deterministic environmental characteristics. Driven by this paradigm shift, we introduce a novel, lightweight Test-Time Gated Attention framework by Harnessing SPAD Noise, therefore dubbed HSN. Tailored for indoor scenarios, HSN leverages the synergistic combination of 1D SPAD histograms and Gate Adapters (GAs). Through three complementary optimization phases, it generates channel-wise gated attention vectors to dynamically adjust encoder feature maps at inference time, effectively resolving ambiguous scale and boundary challenges without the heavy computational overhead or dense 3D modalities that other TTA methods suffer from. Extensive experiments on challenging real-world indoor benchmarks show that HSN achieves state-of-the-art metric depth accuracy in in-domain settings, while exhibiting even greater potential under zero-shot generalization to unfamiliar environments. Furthermore, interpretability analysis reveals that the proposed gated attention mechanism adaptively shifts attention toward deeper semantic layers under intensifying SPAD noise. Code will be made publicly available.
Oct 9, 2026

DPAL: A Test-Time Adaptation Loss for Financial Time Series Forecasting

Test-time adaptation (TTA) enables time series forecasters to update after deployment as new observations become available. However, adaptation objectives that focus primarily on prediction errors at individual time steps do not fully address the needs of financial time series forecasting. In addition to pointwise return fitting, return direction and the price trajectories reconstructed from sequences of returns are also important. To better account for these properties, we introduce Direction- and Price-Aware Adaptation Loss (DPAL), which combines pointwise return fitting with directional and price-calibration terms. We apply DPAL within existing TSF-TTA frameworks without modifying the source forecaster or the adapter architecture. Across a diverse collection of financial datasets, DPAL reduces reconstructed-price mean squared error in most evaluated settings.
Oct 8, 2026

GenIA: Generative Reconstruction with Test-Time Input Alignment

Reconstructing complete 3D object assets from monocular or sparse multi-view observations remains challenging. Generative 3D foundation models can complete object geometry beyond the observed views, but their predictions may not faithfully reproduce the observed geometry, appearance, or pose. We introduce GenIA, a framework for test-time input-aligned generation that grounds SAM3D's generative prior in geometric and photometric observations without retraining the foundation model. We improve object pose by deriving translation and scale from geometry while retaining the learned rotation prior, and align appearance through visibility-biased attention, cross-observation fusion, and differentiable rendering guidance during denoising. An optional post-denoising refinement further adapts the appearance latent, lightweight decoder adapters, and object placement to the observations. Our framework also supports externally supplied geometry; when given temporal shapes of dynamic objects, it recovers a shared, input-aligned canonical appearance and stable world-space placement. Across synthetic and real benchmarks, GenIA improves pose prediction and object reconstruction from monocular, multi-view, and dynamic inputs, outperforming recent optimization-based, per-frame image-to-3D, and video-to-4D methods. Our project page is available at https://facebookresearch.github.io/GenIA.
Oct 8, 2026

Training on the Future: A Delay-Aware Audit of Test-Time Adaptation for Time-Series Forecasting

Test-time adaptation (TTA) methods for time-series forecasting update a deployed model, or a small adapter around it, from incoming ground truth. But the label of an HH-step forecast exists only HH steps later, and real data pipelines add further delay. We build a leakage-free harness in which the label of forecast origin ss is released for updates only at step s+ds+d with d≥Hd \ge H, and enforce this rule inside the released code of four recent TTA methods (TAFAS, COSA, PETSA and DynaTTA), run on their own backbones and checkpoints across five benchmarks (ETTm1, ETTh2, Weather, Electricity and Traffic). As references we add two closed-form correctors: a bank of recursive least squares (RLS) filters combined by a per-coordinate median, with no tunable hyperparameters and 56 microseconds per step on the 7-channel streams, and an ELF-style linear corrector. Under causal delayed labels the picture is asymmetric. On ETTm1 every audited method genuinely adapts, yet the RLS bank still beats three of the four at a fraction of their cost; only DynaTTA beats the bank, only at the minimum causal delay, and at roughly 2,500 times the per-update cost; the ELF-style corrector beats all four. On the other four datasets, the largest statistically significant improvement any published method achieves over its own frozen checkpoint is half a percent, on all four at least one published method is significantly worse than the frozen model at the minimum causal delay, and on drift-heavy ETTh2 longer label delays make every adapter that separates from the frozen model, ours included, significantly harmful. Leaky next-step updates inflate the apparent gains of simple adapters by up to 110%, and the backbone training recipe moves frozen online error by up to a factor of 25, more than any adaptation effect we measure. We release the harness, integration patches and all cached runs.
Oct 8, 2026

Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits

Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)? We systematically study this along three axes: adaptation, aggregation, and context construction. Our evaluation spans modern TFMs across the TabArena benchmark, supplemented by experiments on wide and large-scale tables from OpenML. For adaptation, we introduce DiagScale, a diagonal query-key similarity update. It trains only 0.003-0.03% of model parameters and achieves gains comparable to full fine-tuning across three independently pretrained backbones. For aggregation, both pool composition and selection strategy matter. TabPFN-3 already averages predictions from different preprocessing variants of the same data, and adding more such predictions yields diminishing returns. With a broader pool of 96 configurations, greedy selection reduces error by 2.4% relative to the default predictor, but uniform averaging increases error. For context construction, attention-guided retrieval improves TabPFN-3's predictions on some large tables and supports source pools beyond the full context memory limit. The context expansion methods we test yield no consistent improvement. Taken together, our results suggest that adaptation and selective aggregation yield consistent benchmark-level gains. The benefits of context construction depend more on the task and data regime. Adaptation and aggregation over the same backbone yield further gains when combined, but require substantially more computation than default inference. These trade-offs motivate choosing strategies according to the available computation budget. Code is available at https://github.com/kanghui-learning/test-time-compute-for-tabular-foundation-models.
Oct 8, 2026

SR-TTA: Spatial-Redundancy Test-Time Adaptation for Interference-Robust Respiration Sensing

Future 6G networks aim to expose sensing as a native service by reusing communication infrastructure. We study respiration sensing on a cell-free massive multiple-input multiple-output (MIMO) base station, where a 64-antenna channel must be fused into a breathing waveform. The state-of-the-art hand-crafted fusion is near-optimal in benign conditions. It collapses, however, under strong in-band motion interference, whose frequency falls inside the respiration band. We show that a learned complex-weight beamformer recovers respiration by spatial nulling, and that the remaining gap to a per-recording oracle can be closed at deployment by label-free test-time adaptation. Crucially, we identify which label-free signal makes this work. Frequency- and variance-based criteria cannot separate an in-band interferer from breathing. Our spatial-redundancy test-time adaptation (SR-TTA), which maximizes consistency across random antenna subsets under an out-of-band spectral veto, preserves benign performance in our tests. The respiration-rate error drops from 5.8 to 0.8 breaths per minute (bpm) under simulated in-band interference, and the pipeline maps onto the Open Radio Access Network (O-RAN) architecture as O-RAN distributed-unit (O-DU) range-gating, an adaptation xApp, and a calibration rApp. On real testbed recordings, a one-time cross-subject calibration plus SR-TTA reduces failures from 47% to 7%, drawing level with the hand-crafted combiner using label-free test-time adaptation.
Oct 8, 2026

Skeleton-Guided Progressive Test-Time Adaptation for Thin Curvilinear Structures

Accurate segmentation of thin curvilinear structures is vital for various real-world applications, from vessel analysis to road extraction. Yet their intricate geometry makes even minor pixel-wise errors enough to break the global topology, and this structural fragility turns severe domain shifts into catastrophic failures. The difficulty is most acute under cross-modality gaps, where the imaging process itself differs fundamentally between source and target. While test-time adaptation (TTA) offers a practical source-free remedy, existing methods adapt feature statistics and confidence, neither of which constrains connectivity, and thus degrade under such extreme gaps. To address this, we propose Skeleton-Guided Progressive Test-Time Adaptation (SGP-TTA). Progressive Batch Normalization (ProgBN) shifts normalization from frozen source statistics toward current target estimates under a sample-count schedule, so that the source-target balance follows the stage of adaptation rather than a fixed coefficient. Consensus Skeleton Recall (CSR) then derives a structural target from geometrically aligned multi-view predictions and updates only the BN affine parameters to preserve connected structures. Extensive experiments show that SGP-TTA consistently outperforms existing TTA methods in topological connectivity, with the largest margins under cross-modality shift. The project page is available at https://boa-jang.github.io/SGP-TTA.
Oct 7, 2026

CIRSeg: Coarse-to-Fine Intensity-Robust Liver Segmentation with Source-Free Continual Test-Time Adaptation

Reliable liver segmentation in contrast-enhanced MRI is essential for quantitative hepatic assessment, treatment planning, and longitudinal disease monitoring. However, limited annotated data and scanner- or vendor-dependent intensity variations can cause overfitting and poor generalization to unseen acquisition domains. Moreover, simultaneously achieving robust global localization and precise boundary delineation remains challenging, while predictions may contain isolated false-positive regions outside the main liver component. To address these challenges, we propose CIRSeg, a coarse-to-fine, intensity-robust liver segmentation framework based on nnU-Netv2. CIRSeg combines 3D CutMix with stochastic intensity transfer using either Nyul augmentation or histogram matching to improve robustness to heterogeneous MRI intensities. Its cascaded architecture decouples low-resolution anatomical localization from full-resolution boundary refinement. At inference, source-free test-time adaptation based on confidence-filtered predictions and probability-prior regularization further improves robustness to out-of-distribution inputs. As a final deterministic post-processing step, largest connected component filtering removes isolated false-positive regions. On the CARE 2026 test set, CIRSeg achieves Dice scores of 97.13% and 97.93% on the in-domain and unseen-domain subsets, with corresponding HD95 values of 20.18 mm and 11.30 mm, respectively. These results demonstrate consistently accurate segmentation across both in-domain and unseen acquisition settings. The code is available at https://github.com/jingkunchen/MICCAI_CARE_2026
Oct 6, 2026

REFIT: Recognize, Fix, and Test Wearable Sensor Placement Shifts without Labels

We present REFIT, an input calibration for frozen activity-recognition models whose inertial sensors are worn differently at deployment than in training. When users move a watch to the other wrist or put a strap sensor back on turned, the model sees the same motion on changed axes. REFIT undoes such shifts without labels or retraining. It describes them by families of axis transforms, such as reflections and rotations, and fits each family to the user's data so that simple statistics match those of the training data. The family that removes most of the mismatch names the shift. REFIT fixes the shift by applying the best member of that family before the frozen model and re-estimating its normalization statistics. It tests the fixed model with a label-free accuracy estimate and asks the user to re-wear the sensor when it is low. Experiments on real left/right sensor pairs and on real and simulated re-attachment show that REFIT outperforms label-free test-time adaptation methods on every dataset and restores most of the accuracy lost to re-attachment. It names injected shifts far more reliably than a confidence-based selector. After a correction over all signed permutations of the axes, the estimate separates successful from failed corrections.
Oct 6, 2026

Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration

Post-training quantization is a standard route to fitting vision transformers (ViTs) into edge compute and memory budgets, yet quantized models become especially brittle under distribution shift. Test-time adaptation (TTA) addresses such shifts without labels, but most existing approaches are poorly aligned with the constraints of quantized inference. Prevailing TTA methods recover accuracy through backpropagation, while backprop-free methods often still incur overhead from extra forward passes or parameter updates, and lightweight feature- or logit-level methods recover only part of the loss. Across these approaches, a quantization-specific failure mode that amplifies the drop is not directly targeted: under shift, activations occupy frozen quantizers' calibrated ranges differently, distorting their code distribution. We propose Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters. QuAR recalibrates activations at the input to a frozen quantizer, mapping the test stream's running per-channel statistics back toward the source calibration. On ImageNet-C with ViT-B, QuAR achieves the highest mean accuracy among state-of-the-art backprop-free TTA methods at 3-, 4-, 6- and 8-bit weight/activation precision, outperforming the strongest baseline by 2.28 points at 8 bits and 4.00 at 3 bits, with 46% lower latency and a memory overhead of only 0.17 MB (0.01% of peak inference memory). Analysis and diagnostics trace the gain to a reduced per-channel mismatch at these quantizers, which restores the code distribution the baselines leave unchanged or distort further. A single fixed configuration remains ahead across continual streams, non-i.i.d. label shift, seven out-of-distribution suites, and three other backbones.
Oct 6, 2026

Test-Time Agent Evolution for Long-Horizon Legal Reasoning

Legal intelligence aims to support reliable decision-making across long-horizon legal processes involving evolving case states and multiple roles. However, real-world legal deployment exhibits substantial case heterogeneity in facts, evidence, and procedural contexts, exposing the limitations of static agent strategies. Moreover, legal reasoning is inherently interdependent across roles and procedural stages, making global reliability fundamentally different from isolated role competence. To address these challenges, we study training-free test-time agent adaptation, where agents continuously exploit deployment-time signals from preceding cases and ongoing interactions without updating model parameters. We propose \method, which introduces Test-Time Memory Evolution to retrieve reusable experience from previous cases, adapt it to the current factual and procedural context, and consolidate accumulated experience for subsequent decision-making. Further, Rubric-Aligned Collaboration verifies and revises role-specific actions according to behavioral and procedural requirements, enabling coordinated decision-making across roles and stages. Extensive experiments on J1-EVAL and LegalWorld across five backbone models demonstrate consistent improvements over representative reasoning and agent baselines with reasonable interaction and computational costs. Ablation and case studies further show that the two components provide complementary benefits in experience adaptation and cross-role coordination, improving the reliability and efficiency of long-horizon legal reasoning.
Oct 6, 2026

Spectra: Exact Component Transport for Test-Time Prior Adaptation in Simulation-Based Inference

Simulation-based inference (SBI) has become a powerful approach to Bayesian inference in complex scientific models whose likelihoods are difficult or impossible to evaluate. Amortized SBI learns reusable inference models from simulated data, enabling rapid posterior inference for new observations, and modern generative models have made these models increasingly expressive. However, this reuse is limited to the prior distribution chosen during training, whereas scientific analyses often need revised priors as knowledge accumulates or alternative assumptions are tested. We introduce Spectra, a test-time adaptation method for diffusion-based SBI. Spectra uses an exact score-transport identity to obtain the adapted score from a frozen diffusion model in closed form for structured prior changes, without additional simulation or training. Across six SBI benchmarks, Spectra achieves accurate adaptation under strong prior shifts at low online sampling cost. This enables pretrained SBI models to incorporate updated prior information at test time.
Oct 5, 2026

Source-Learned Reliance for Selective Test-Time Adaptation of Multimodal Time Series

Multimodal wearable systems must remain reliable when sensor streams become noisy or unavailable. Existing multimodal test-time adaptation (TTA) methods often assess reliability online, but cross-modal agreement can be misleading when sensors measure different physical processes, and evaluating alternative modality configurations adds inference cost. We propose CARAT, which decouples model reliance from runtime corruption detection to guide omission or attenuation, amortizing reliance estimation through source training. An asymmetric modality-dropout curriculum prepares a missingness-resilient backbone for omission and derives a frozen, backbone-specific reliance proxy from windowed input-projection gradient norms. At deployment, a lightweight one-class detector flags suspect streams, and the proxy guides a joint choice between replacing the suspect set with the backbone's trained missingness symbol and attenuating its representations before fusion, without candidate-subset evaluation. Across four wearable datasets, five corruption types, three backbones, and eight TTA baselines, CARAT achieves the highest overall macro-F1 and best mean rank (2.42), exceeding EATA, the strongest baseline, by 1.58 F1 points across 12 equally weighted dataset-backbone settings. Across five profiled configurations, CARAT uses 9.49% fewer GFLOPs and updates 47.82% fewer parameters than EATA. A pattern also emerges across sensing regimes: multimodal TTA methods such as PTA are competitive on IMU-dominated homogeneous datasets, whereas unimodal TTA methods like TENT and EATA match or exceed it on heterogeneous datasets. These results position CARAT as a practical default to wearable TTA, offering competitive robustness with modest computational requirements and benefits that vary across backbones and dataset regimes.
Oct 5, 2026

Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts

Vision-language models (VLMs) achieve strong zero-shot transferability but remain vulnerable to target-domain shifts at inference time. Test-time adaptation (TTA) offers a practical remedy, yet most existing VLM-TTA methods follow a prediction-side adaptation paradigm. They use test samples to adjust logits, prototypes, caches, priors, or feature statistics, often incurring additional computational overhead. In this paper, we take a different perspective and reframe VLM-TTA as candidate verification rather than prediction adjustment. We propose Test-Time Correction (TTC), a hypothesis-based correction framework guided by a simple principle: hypothesize, reconstruct, correct. Given a test feature and its top-k candidate labels, TTC treats each candidate label as a hypothesis, reconstructs the feature within the corresponding latent subspace stored in a memory bank, and measures the resulting divergence shift. This shift quantifies how much the candidate subspace and its relations to other candidates change after the hypothetical insertion of the test feature. A correct candidate hypothesis induces only a small shift, whereas an incorrect one perturbs the subspace more strongly. TTC therefore corrects the prediction by selecting the candidate with the minimum aggregated divergence shift. This training-free candidate-verification mechanism avoids iterative optimization and provides a favorable accuracy-efficiency trade-off. Across five TTA settings and 15 benchmark datasets, including zero-shot classification, domain generalization, few-shot classification, base-to-novel generalization, and cross-dataset evaluation, TTC consistently improves accuracy over state-of-the-art VLM-TTA methods while achieving up to 2x speedup, over 3x lower CPU memory usage, and up to 1.4x lower GPU memory usage than the lowest-memory training-free baseline.