Donor-driven nodule properties in synthetic CT transfer to real lung CT vision-language tasks while host-driven anatomy properties do not, enabling a label-free diagnostic for model routing.
hub Canonical reference
Tent: Fully Test-time Adaptation by Entropy Minimization
Canonical reference. 100% of citing Pith papers cite this work as background.
52
Pith papers citing it
285
external citations · Pith
Background
100% of classified citations
abstract
A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. Tent handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark. These results are achieved in one epoch of test-time optimization without altering training.
hub tools
citation-role summary
background 7
citation-polarity summary
roles
background 7polarities
background 7representative citing papers
Remote sensing MLLMs perform poorly on negation tasks with hallucinations and accuracy drops, but the NeFo test-time learning method substantially improves negation understanding and generalizes to unseen tasks using ~5% unlabeled test samples.
QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.
TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.
A test-time adaptation framework anchors adversarial training to a non-robust teacher's predictions, yielding more stable optimization and better robustness-accuracy trade-offs than standard self-consistency methods.
NPS-Net formulates optic disc and cup segmentation as nested radially monotone polar occupancy estimation to guarantee star-convexity, nesting, and high accuracy for glaucoma screening.
An uncertainty-aware test-time adaptation framework improves cross-region spatio-temporal fusion of land surface temperature by updating only the fusion module guided by epistemic uncertainty, land use consistency, and bias correction.
IMSE adapts Vision Transformers for test-time and continual test-time adaptation by tuning only singular values from SVD decompositions and using expert diversity plus domain retrieval, reaching SOTA with far fewer trainable parameters.
NeuroKalman mitigates state drift in vision-language UAV navigation by using memory-augmented Kalman filtering where attention retrieves historical anchors to correct predictions without gradient updates.
Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
DC-TTA improves interactive segmentation accuracy by partitioning user clicks into subsets for independent test-time adaptation of SAM models and merging the specialized predictors.
CoDiRe blends VLM and target model predictions via MSP-based weighting and Optimal Transport rectification to enable stable continual test-time adaptation, outperforming CoTTA by 10.55% on ImageNet-C at 48% of the compute cost.
CreTTA reformulates test-time adaptation of marginal distributions as residual energy learning, producing a contrastive objective that cancels the partition function and uses relative energy differences for adaptive gradient reweighting to avoid overfitting.
T^2VLA is a test-time reinforcement learning framework for VLAs that uses internal confidence to define intrinsic rewards via similarity to high-confidence expert demonstrations and a dual-expert bootstrapping mechanism.
TopoTTA integrates persistent homology into test-time adaptation to derive topological pseudo-labels from anomaly maps, improving segmentation by an average 15% F1 on six benchmarks while generalizing across 2D and 3D data.
FFN performs efficient test-time training on multi-hour videos by forgetting the exiting frame, anticipating the next, and adapting only when a surprise metric exceeds a dynamic threshold.
Introduces Black-CL black-box benchmark and BETA textual-prototype method that matches or exceeds white-box continual learning performance on ten datasets using 0.05M parameters.
SAEFS uses VQA-derived semantic anchors, dual-stream evidence extraction, and Dirichlet-based evidential fusion to achieve 10.2% higher average C-index in zero-shot cross-domain WSI survival analysis.
MAMVI performs unified single-step TTA on masked multi-view point clouds with hybrid masking and confidence-adaptive learning rates, reporting SOTA on ShapeNet-C and ScanObjectNN-C plus 4.9-8.9x speedup.
A gradient-free framework adapts pretrained HAR classifiers to new users via Bayesian prototype updates in prototypical networks, improving F1 scores with 3s calibration data.
HMARS introduces a hierarchical multi-agent memory system that outperforms standard retrieval and other baselines on long-document and multi-turn reasoning tasks through improved evidence coverage.
DOME learns sample-specific domain variables from sparse supervision via vision-language models and a sparse domain bank to improve test-time adaptation performance.
TTT-SCL dynamically generates test-aligned training sets for supervised causal learning using score-based functions and outperforms prior SCL and traditional causal discovery methods on benchmarks and real data.
Proposes meta-learning attack with priority-aware gradient alignment for sample-wise targeted attacks on TTA that maintain label distribution consistency with no-attack baseline.
citing papers explorer
-
When Does Synthetic CT Transfer? A Label-Free Donor/Host Diagnostic for Medical Vision-Language Model Routing on Real Lung CT
Donor-driven nodule properties in synthetic CT transfer to real lung CT vision-language tasks while host-driven anatomy properties do not, enabling a label-free diagnostic for model routing.
-
Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs
Remote sensing MLLMs perform poorly on negation tasks with hallucinations and accuracy drops, but the NeFo test-time learning method substantially improves negation understanding and generalizes to unseen tasks using ~5% unlabeled test samples.
-
Query-Conditioned Test-Time Self-Training for Large Language Models
QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.
-
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.
-
Learning Robustness at Test-Time from a Non-Robust Teacher
A test-time adaptation framework anchors adversarial training to a non-robust teacher's predictions, yielding more stable optimization and better robustness-accuracy trade-offs than standard self-consistency methods.
-
Nested Radially Monotone Polar Occupancy Estimation: Clinically-Grounded Optic Disc and Cup Segmentation for Glaucoma Screening
NPS-Net formulates optic disc and cup segmentation as nested radially monotone polar occupancy estimation to guarantee star-convexity, nesting, and high accuracy for glaucoma screening.
-
Uncertainty-Aware Test-Time Adaptation for Cross-Region Spatio-Temporal Fusion of Land Surface Temperature
An uncertainty-aware test-time adaptation framework improves cross-region spatio-temporal fusion of land surface temperature by updating only the fusion module guided by epistemic uncertainty, land use consistency, and bias correction.
-
IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
IMSE adapts Vision Transformers for test-time and continual test-time adaptation by tuning only singular values from SVD decompositions and using expert diversity plus domain retrieval, reaching SOTA with far fewer trainable parameters.
-
Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering
NeuroKalman mitigates state drift in vision-language UAV navigation by using memory-augmented Kalman filtering where attention retrieves historical anchors to correct predictions without gradient updates.
-
Neural Collapse in Test-Time Adaptation
Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
-
DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation
DC-TTA improves interactive segmentation accuracy by partitioning user clicks into subsets for independent test-time adaptation of SAM models and merging the specialized predictors.
-
Test-Time Distillation for Continual Model Adaptation
CoDiRe blends VLM and target model predictions via MSP-based weighting and Optimal Transport rectification to enable stable continual test-time adaptation, outperforming CoTTA by 10.55% on ImageNet-C at 48% of the compute cost.
-
Contrastive Residual Energy Test-time Adaptation
CreTTA reformulates test-time adaptation of marginal distributions as residual energy learning, producing a contrastive objective that cancels the partition function and uses relative energy differences for adaptive gradient reweighting to avoid overfitting.
-
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
T^2VLA is a test-time reinforcement learning framework for VLAs that uses internal confidence to define intrinsic rewards via similarity to high-confidence expert demonstrations and a dual-expert bootstrapping mechanism.
-
Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation
TopoTTA integrates persistent homology into test-time adaptation to derive topological pseudo-labels from anomaly maps, improving segmentation by an average 15% F1 on six benchmarks while generalizing across 2D and 3D data.
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN performs efficient test-time training on multi-hour videos by forgetting the exiting frame, anticipating the next, and adapting only when a surprise metric exceeds a dynamic threshold.
-
Black-Box Continual Learning for Vision-Language Models
Introduces Black-CL black-box benchmark and BETA textual-prototype method that matches or exceeds white-box continual learning performance on ten datasets using 0.05M parameters.
-
Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis
SAEFS uses VQA-derived semantic anchors, dual-stream evidence extraction, and Dirichlet-based evidential fusion to achieve 10.2% higher average C-index in zero-shot cross-domain WSI survival analysis.
-
MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds
MAMVI performs unified single-step TTA on masked multi-view point clouds with hybrid masking and confidence-adaptive learning rates, reporting SOTA on ShapeNet-C and ScanObjectNN-C plus 4.9-8.9x speedup.
-
Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
A gradient-free framework adapts pretrained HAR classifiers to new users via Bayesian prototype updates in prototypical networks, improving F1 scores with 3s calibration data.
-
HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning
HMARS introduces a hierarchical multi-agent memory system that outperforms standard retrieval and other baselines on long-document and multi-turn reasoning tasks through improved evidence coverage.
-
DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation
DOME learns sample-specific domain variables from sparse supervision via vision-language models and a sparse domain bank to improve test-time adaptation performance.
-
Test Time Training for Supervised Causal Learning
TTT-SCL dynamically generates test-aligned training sets for supervised causal learning using score-based functions and outperforms prior SCL and traditional causal discovery methods on benchmarks and real data.
-
Sample-wise Targeted Adversarial Attacks on Test-time Adaptation
Proposes meta-learning attack with priority-aware gradient alignment for sample-wise targeted attacks on TTA that maintain label distribution consistency with no-attack baseline.
-
Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixelwise adaptive calibration, reporting over 4.1 mIoU gains.
-
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
SkyPart achieves state-of-the-art single-pass cross-view geo-localization on SUES-200, University-1652, and DenseUAV by using prototype-based part discovery, altitude-conditioned modulation, and Kendall-weighted loss, with widening gains under weather corruptions.
-
Seeking Consensus: Geometric-Semantic On-the-Fly Recalibration for Open-Vocabulary Remote Sensing Semantic Segmentation
SeeCo is a training-free on-the-fly recalibration method using multi-view geometric consistency and adaptive textual calibration to improve open-vocabulary semantic segmentation in remote sensing images.
-
PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices
PI-TTA stabilizes source-free test-time adaptation for sensor-based human activity recognition by adding physics-consistent constraints, yielding up to 9.13% accuracy gains and lower physical violation rates on three benchmarks under streaming shifts.
-
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
A parameter-free sampling strategy called CUTS combined with Mixed-CUTS training prevents mode collapse in RL for saturated LLM reasoning tasks and raises AIME25 Pass@1 accuracy by up to 15.1% over standard GRPO.
-
ProtoTTA: Prototype-Guided Test-Time Adaptation
ProtoTTA is a test-time adaptation framework for prototype models that uses intermediate prototype signals and entropy minimization to improve robustness and semantic focus under distribution shifts.
-
Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation
DiTTA distills SAM2 temporal segmentation knowledge into image models via efficient test-time adaptation and a lightweight fusion module to produce annotation-free video semantic segmentation that matches or exceeds fully supervised performance.
-
RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
RL-AWB uses a soft actor-critic RL agent to per-image tune a novel gray-pixel illuminant estimator, achieving competitive nighttime white balance with only five training images and better cross-sensor generalization than daytime-trained baselines.
-
The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Entropy minimization on self-generated outputs elicits strong reasoning in pretrained LLMs, matching or exceeding supervised RL methods on benchmarks.
-
EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
A test-time adaptation system that triggers model updates only on detected domain shifts, plus a decoupled batch-normalization update, achieves high accuracy with low energy on edge devices.
-
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
DO-ALL applies dataset distillation to generate synthetic source anchors that stabilize continual test-time adaptation under evolving domains without storing original source data.
-
Continual Self-Improvement with Lightweight Experiential Latent Memories
Lightweight modular latent memories trained on self-generated rewards enable continual self-improvement in LLMs, outperforming raw ICL and matching offline training on math benchmarks.
-
Theoretical Grounding of Out-Of-Distribution Detection With Reinforcement Learning Optimizer
Develops an RL-augmented gradient descent optimizer for dynamic OOD detection together with a temporal error decomposition framework comparing it to standard GD.
-
EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering
EASE-TTT creates a soft attention target from evidence chunks to guide query-side test-time adaptation, yielding higher macro-average scores than full-context, retrieval-only, and standard qTTT baselines on six LongBench QA tasks.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
-
Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception
Proposes HCL framework with HRR, TAG, and PCC modules for test-time adaptation in camouflaged object detection, claiming consistent outperformance on benchmarks under distribution shifts.
-
SkySeg: Collaborative Onboard Semantic Segmentation with Heterogeneous UAVs in the Wild
SkySeg is a heterogeneous multi-UAV framework that fuses low- and high-definition images and uses cross-device test-time adaptation to enable real-time onboard semantic segmentation, reporting 3.6x faster inference and accuracy gains of 5.91% onboard and 10.91% in the wild.
-
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
MoASE++ combines activation sparsity experts with domain-adaptive on-policy distillation to achieve state-of-the-art continual test-time adaptation on image classification and segmentation benchmarks.
-
ERPPO: Entropy Regularization-based Proximal Policy Optimization
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
-
Environment-Adaptive Preference Optimization for Wildfire Prediction
EAPO adapts wildfire models to new environments via k-nearest neighbor data retrieval and hybrid fine-tuning that emphasizes rare extreme events, achieving ROC-AUC 0.7310 on real data.
-
Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models
Agentic AI systems are required to overcome the parameter coverage ceiling that prevents foundation models from handling certain out-of-distribution cases.
-
Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It
MaskGen improves domain generalization for biomedical image segmentation by using source intensities plus domain-stable foundation model representations with minimal added complexity.
-
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
MemRL enables self-evolving AI agents through reinforcement learning on episodic memory with a two-phase retrieval process that filters noise and selects high-utility strategies based on environmental feedback.
-
No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation
Observability-constrained test-time prompt tuning for LiDAR semantic segmentation reweights spatial supervision using per-location reliability estimates from beam terminations and neighborhood support, with prompt adapters and temporal prototype alignment.
-
APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms
Presents APRIL-MedSeg, a modular YAML-configurable toolbox for 2D medical image segmentation integrating semi-supervised, domain adaptation, distillation, weakly supervised, text-guided, and foundation model paradigms with unified dataset and deployment interfaces.
- Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs