4 papers
Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning
Zhipeng Chen, Xiaobo Qin, Wayne Xin Zhao +2
Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the reasoning ability of large language models (LLMs). However, due to the limited amount…
Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
Zhipeng Chen, Xiaobo Qin, Youbin Wu +4
Reinforcement learning with verifiable rewards (RLVR), which typically adopts Pass@1 as the reward, has faced the issues in balancing exploration and exploitation, causing policies…
StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models
Xiangxiang Zhang, Jingxuan Wei, Donghong Zhong +31
Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanis…
Seed1.5-VL Technical Report
Dong Guo, Faming Wu, Feida Zhu +194
We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter v…