Papers Test-time Adaptation
“Test-time Adaptation” 태그가 달린 논문 868편 · 필터 해제
Learning to Predict Distributions over Weight Updates for Test-Time Adaptation
Hypernetworks have recently shown success in dynamically adapting the parameters of Large Language Models (LLMs) at runtime based on signals such as task descriptions or additional demostrations. Here we ask: how much ad…
Test-time AdaptationWISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most existing ATTA methods implicitly assume …
Test-time AdaptationLabel-free steering: Compressing test-time reinforcement learning into bias-only subspaces
Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters. This raises…
Reinforcement LearningTest-time AdaptationInteractive Memory Learning for Long-Term Conversations
Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these successes, existing approaches typically adopt a static heuristic par…
Reinforcement LearningTest-time AdaptationSparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation
Wild test-time adaptation (WTTA) updates a source model online under small test batches, concurrent distribution shifts, and time-varying class imbalance. Most WTTA methods derive their adaptation signals, including pred…
Test-time AdaptationIMVS: Interactive Medical Volume Segmentation with Test-Time Adaptation - A New Method for Annotating Radiology Datasets
Annotating large radiology datasets is bottlenecked by the manual effort of delineating structures slice-by-slice in 3D volumes. Interactive methods reduce this effort but stay interaction-inefficient: slice-wise methods…
Test-time AdaptationFrom Few-Shot Segmentation to Clinician-in-the-Loop Medical Image Analysis
Few-shot medical image segmentation (FSMIS) seeks to delineate unseen structures from a small support set, but its standard formulation fixes task-defining evidence before inference. This assumption is fragile when query…
Medical Image SegmentationInteractive SegmentationTest-time AdaptationDistilling Image Prototypes for Guided Test-Time Adaptation
Test-Time Adaptation (TTA) enhances the robustness of models against distribution shifts but faces two critical challenges: error accumulation from noisy pseudo-labels and catastrophic forgetting of source knowledge. Unc…
Test-time AdaptationAugmenting Human Performance with an XR Agent Learning from Online Behavior and BCI Evidence
We present OLIVE, a framework for adapting a foundation model to provide real-time assistance in temporally demanding, high-stakes, and dynamic tasks. We show that passive EEG, fused online with behavioral evidence, can …
Test-time AdaptationAdapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You
Test-time adaptation (TTA) typically assumes that model parameters can be updated at inference time. This assumption is restrictive for inference-only accelerators, frozen or third-party models, and memory-constrained de…
Test-time AdaptationSafin-1: Safety from Within through Memory-Native State Evolution
Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety should be an intrinsic property of the model itself, rather than a be…
Long-Context UnderstandingTest-time AdaptationRECAST: Recent & Context-Aware Sampling for Test-Time Adaptation in Streaming Biosignals
Streaming biosignals vary across subjects and drift over time, so population-trained models lose accuracy during long-term monitoring. Test-time adaptation (TTA) enables online personalization by updating the model on in…
Test-time AdaptationTemporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs
Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which involves potential distribution shifts that may harm model generalizatio…
Test-time AdaptationGraph Neural NetworkGenerative Semantic Scene Completion
Outdoor LiDAR semantic scene completion (SSC) recovers a dense semantic voxel grid from a scan observing 1% of the target volume, under class imbalance beyond 7,000x. We recast SSC as generative semantic scene completion…
Test-time AdaptationFairness-Aware Test-Time Prompt Tuning
Vision-language models have displayed remarkable capabilities in multi-modal understanding and are increasingly used in critical applications where economic and practical deployment constraints prohibit re-training or fi…
Test-time AdaptationTowards Purified Multi-Label Test-Time Adaptation of Vision-Language Models
Test-time adaptation (TTA) has been widely explored in single-label recognition, effectively mitigating distribution shifts, especially when combined with vision-language models. However, real-world images often contain …
Test-time AdaptationRA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
Vision-Language-Action (VLA) models provide a versatile foundation for general robotic manipulation, yet they exhibit significant brittleness when confronted with novel task distributions. While In-Context Imitation Lear…
Computational EfficiencyTest-time AdaptationTest-Time Adaptation for ECG Classification via SQI-Gated Self-Training and Beat-Rhythm Consistency
Deep learning models for electrocardiogram (ECG) classification often suffer from significant performance degradation when deployed in unseen domains due to shifts in acquisition devices and patient populations. Test-tim…
Test-time AdaptationECG ClassificationLiST: Local-Simplex Test-Time LoRA Fusion
Task-specific LoRA adapters offer a modular way to specialize large language and vision-language models. However, existing adapter composition methods are mostly static and cannot adapt to individual test inputs. To addr…
Test-time AdaptationPETA:Parameter-Efficient Test-Time Adaptation for Virtual Screening
Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP and its recent extensions substantially accelerate this process by …
Test-time Adaptation