activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

Dong Yan, Jian Liang, Yanbo Wang +3

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority vo…

cs.LG2026

Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation

Zhengbo Wang, Jian Liang, Ran He +2

Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces significant memory overhead, wh…

cs.LG2026

Learning Fair Domain Adaptation with Virtual Label Distribution

Yuguang Zhang, Lijun Sheng, Jian Liang +1

Unsupervised Domain Adaptation (UDA) aims to mitigate performance degradation when training and testing data are sampled from different distributions. While significant progress ha…

cs.LG2025

Adapting Vision-Language Models Without Labels: A Comprehensive Survey

Hao Dong, Lijun Sheng, Jian Liang +3

Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when direct…

cs.LG2025

The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models

Lijun Sheng, Jian Liang, Ran He +2

Test-time adaptation (TTA) methods have gained significant attention for enhancing the performance of vision-language models (VLMs) such as CLIP during inference, without requiring…

cs.LG2025

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

Lijun Sheng, Jian Liang, Zilei Wang +1

Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstre…