6 papers
Ramen: Robust Test-Time Adaptation of Vision-Language Models with Active Sample Selection
Wenxuan Bao, Yanjun Zhao, Xiyuan Yang +1
Pretrained vision-language models such as CLIP exhibit strong zero-shot generalization but remain sensitive to distribution shifts. Test-time adaptation adapts models during infere…
FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation
Xinrui He, Ting-Wei Li, Tianxin Wei +5
Federated cross-domain recommendation (Federated CDR) aims to collaboratively learn personalized recommendation models across heterogeneous domains while preserving data privacy. R…
Panda: Test-Time Adaptation with Negative Data Augmentation
Ruxi Deng, Wenxuan Bao, Tianxin Wei +1
Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-t…
Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
Wenxuan Bao, Ruxi Deng, Jingrui He
Pretrained vision-language models such as CLIP achieve strong zero-shot generalization but remain vulnerable to distribution shifts caused by input corruptions. In this work, we in…
Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
Tianxin Wei, Yifan Chen, Xinrui He +2
Distribution shifts between training and testing samples frequently occur in practice and impede model generalization performance. This crucial challenge thereby motivates studies…
Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation
Wenxuan Bao, Zhichen Zeng, Zhining Liu +2
Powerful as they are, graph neural networks (GNNs) are known to be vulnerable to distribution shifts. Recently, test-time adaptation (TTA) has attracted attention due to its abilit…