About me
I am a Master’s Student at the School of Software and Microelectronics, Peking University, supervised by Assoc. Prof. Qi Jing. Concurrently, I work as a research assistant at PKU-DCAI Group, supervised by Prof. Wentao Zhang.
My research focuses on Multimodal Large Language Models, Reinforcement Learning and Agent.
Education
- Peking University
Master’s Student at the School of Software & Microelectronics
2024/09 - Present - Nanjing University
B.S. in the Department of Computer Science and Technology
2020/09 - 2024/06
Intern & Work Experience
- Meituan Longcat Interaction Team, Beijing, China
2025/12 - Present
Position: Research Intern
Publications:- ToolVerse: Unlocking Massive Environments and Long Horizon Tasks for Agentic Reinforcement Learning (Co-first author, In Submission)
- Shanghai Artificial Laboratory, Shanghai, China
2025/06 - 2025/12
Position: Research Intern, supervised by Dr. Jiantao Qiu
Publications: - Peking University, Beijing, China
2024/10 - Present
Position: Research Assistant in Prof. Wentao Zhang ‘s DCAI Group
Publications:- Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification (Co-first author, NIPS 2025 poster)
Publications
- VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL
Zengjie Hu*, Jiantao Qiu*, Tianyi Bai*, Haojin Yang, Binhang Yuan, Qi Jing,Conghui He, Wentao Zhang
(First-author, CVPR 2026 Findings) - Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification
Tianyi Bai*, Zengjie Hu*, Fupeng Sun*, Jiantao Qiu, Yizhen Jiang, Guangxin He, Bohan Zeng, Conghui He, Binhang Yuan, Wentao Zhang
(Co-first author, NeurIPS 2025 poster) - ToolVerse: Unlocking Massive Environments and Long Horizon Tasks for Agentic Reinforcement Learning
Shuaiyu Zhou*, Fengpeng Yue*, Zengjie Hu*, Yuanzhe Shen, Chenyang Zhang, feng hong, Cao Liu, Ke Zeng
(Co-first author, In Submission) - AICC: Parse HTML Finer, Make Models Better – A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser