3 papers
cs.CV2026
Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
Qingxin Xiao, Peilin Zhao, Yangyang Zhao +2
During MLLM decoding, attention often abnormally concentrates on irrelevant image tokens. While existing research dismisses this as invalid noise and forcibly redirects attention t…
cs.AI2026
Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback
Jiaye Lin, Mengdi Li, Xufeng Zhao +4
Reward models trained through Reinforcement Learning from AI Feedback (RLAIF) methods frequently suffer from limited generalizability, which hinders the alignment performance of po…
cond-mat.mtrl-sci2025
Inverse Materials Design by Large Language Model-Assisted Generative Framework
Yun Hao, Che Fan, Beilin Ye +7
Deep generative models hold great promise for inverse materials design, yet their efficiency and accuracy remain constrained by data scarcity and model architecture. Here, we intro…