Image de couverture de livre

Rethinking Test-Time Training: Tilting The Latent Distribution For Few-Shot Source-Free Adaptation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Syed, Tahir Qasim, Khan, Behraj
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting
par: Khan, Behraj, et autres
Publié: (2025)

Technical note on Fisher Information for Robust Federated Cross-Validation
par: Khan, Behraj, et autres
Publié: (2025)

Adapting to Fragmented and Evolving Data: A Fisher Information Perspective
par: Khan, Behraj, et autres
Publié: (2025)

Causal Covariate Shift Correction using Fisher information penalty
par: Khan, Behraj, et autres
Publié: (2025)

Efficient Learning Under Density Shift in Incremental Settings Using Cramér-Rao-Based Regularization
par: Khan, Behraj, et autres
Publié: (2025)

Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
par: Khan, Behraj, et autres
Publié: (2025)

Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift
par: Khan, Behraj, et autres
Publié: (2025)

Textual analysis of End User License Agreement for red-flagging potentially malicious software
par: Khan, Behraj, et autres
Publié: (2024)

Mitigating covariate shift in non-colocated data with learned parameter priors
par: Khan, Behraj, et autres
Publié: (2024)

Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models
par: Khan, Behraj, et autres
Publié: (2025)

Asymmetric Co-Training for Source-Free Few-Shot Domain Adaptation
par: Li, Gengxu, et autres
Publié: (2025)

Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations
par: Azeem, Hiba, et autres
Publié: (2026)

Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images
par: Usman, Annayah, et autres
Publié: (2026)

Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models
par: Khan, Behraj, et autres
Publié: (2025)

The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
par: Akyürek, Ekin, et autres
Publié: (2024)

Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
par: Park, Junghwan, et autres
Publié: (2025)

Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
par: Chi, Zhixiang, et autres
Publié: (2025)

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
par: Farina, Matteo, et autres
Publié: (2025)

Weight Averaging for Out-of-Distribution Generalization and Few-Shot Domain Adaptation
par: Xu, Shijian
Publié: (2025)

In-Context Learning of Physical Properties: Few-Shot Adaptation to Out-of-Distribution Molecular Graphs
par: Kaszuba, Grzegorz, et autres
Publié: (2024)

Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
par: Singh, Vikash, et autres
Publié: (2026)

Optimization-Inspired Few-Shot Adaptation for Large Language Models
par: Gao, Boyan, et autres
Publié: (2025)

COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation
par: Das, Arnav M., et autres
Publié: (2024)

Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond
par: Gu, Shangding, et autres
Publié: (2025)

Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
par: Kihara, Kosuke, et autres
Publié: (2025)

Few-Shot Concept Unlearning with Low Rank Adaptation
par: Shreyas, Udaya, et autres
Publié: (2025)

Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
par: Sójka, Damian, et autres
Publié: (2026)

Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation
par: Sun, Hankang, et autres
Publié: (2025)

Time and Frequency Synergy for Source-Free Time-Series Domain Adaptations
par: Furqon, Muhammad Tanzil, et autres
Publié: (2024)

Towards Practical Emotion Recognition: An Unsupervised Source-Free Approach for EEG Domain Adaptation
par: Imtiaz, Md Niaz, et autres
Publié: (2025)

Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models
par: Zhang, Yi, et autres
Publié: (2026)

Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
par: Xue, Yihao, et autres
Publié: (2023)

SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer
par: Bhaumik, Kishor Kumar, et autres
Publié: (2024)

Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
par: Huang, Wei-Ping, et autres
Publié: (2026)

Dynamic Model Switching for Improved Accuracy in Machine Learning
par: Hasani, Syed Tahir Abbas
Publié: (2024)

HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks
par: Przewięźlikowski, M., et autres
Publié: (2022)

AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation
par: Kim, Hyeongyu, et autres
Publié: (2026)

SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
par: Lendering, Camile, et autres
Publié: (2026)

Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy
par: Guan, Yunchuan, et autres
Publié: (2025)

IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learning
par: Liao, Wenwen, et autres
Publié: (2026)