9 papers · 1 filter
On the Vulnerability of Parameter-Level Defenses to Model Merging
Kuangpu Guo, Qingyan Zheng, Jian Liang +4
The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization. R…
Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
Kuangpu Guo, Aijing Yu, Jian Liang +4
Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, traditional basic merging methods often experience perf…
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…
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…
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…
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…