4 papers
Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
Muzhi Dai, Shixuan Liu, Zhiyuan Zhao +3
The rapid advancement of multimodal large language models (MLLMs) has led to breakthroughs in various applications, yet their security remains a critical challenge. One pressing is…
Stable Reinforcement Learning for Efficient Reasoning
Muzhi Dai, Shixuan Liu, Qingyi Si
The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the ca…
S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
Muzhi Dai, Chenxu Yang, Qingyi Si
As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (Co…
From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
Muzhi Dai, Jiashuo Sun, Zhiyuan Zhao +4
Aligning large vision-language models (LVLMs) with human preferences is challenging due to the scarcity of fine-grained, high-quality, and multimodal preference data without human…