5 papers
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning
Caoyuan Ma, Wenpu Liu, Weichu Xie +12
Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their language backbones. We propos…
Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation
Yishuo Cai, Jiahui Liu, Yuanxin Liu +9
''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoning over crops, models can ac…
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
Wenpu Liu, Yuqi Xu, Weichu Xie +8
Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual correctness, yet the collective…
EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
Shiqi Huang, Ziyue Wang, Zhongrong Zuo +3
Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, existing RL pipelines rely he…
Step-wise Rubric Rewards for LLM Reasoning
Weichu Xie, Haozhe Zhao, Wenpu Liu +15
Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models, but rewards only final-answer correctness with no supervision ov…