3 papers
cs.CR2026
StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge
Anning Hu, Yangyu Li, Yuqi Huang +2
Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recommendation.…
cs.LG2026
Q-learning Penalized Transformer for Safe Offline Reinforcement Learning
Shengchao Hu, Peng Wang, Jifeng Hu +5
This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an offline dataset. This problem is in…
cs.LG2026
Write Back the : Revisiting the Same Tokens with Fresh Representations
Wencheng Ye, Anning Hu, Xiangdong Zhang +5
Transformers process information strictly forward through depth, preventing deeper computation from revisiting and refining earlier representations. To augment the standard forward…