1 citations · 1 across the 3 of their papers we have counts for
4 papers
GRACE: Generative Representation Learning via Contrastive Policy Optimization
Jiashuo Sun, Shixuan Liu, Zhaochen Su +6
Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and…
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…
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…