About me
I am a third-year undergraduate student in the School of Computer Science and Technology at HUST. I began my research journey while working with Prof. Yao Wan at HUST, and join his undergraduate research team, ONE Lab. At present, I am collaborating with Prof. Tianyi Zhou at UMD and will be joining the CCVL Lab at JHU as an on-site intern, co-supervised by Yaoyao Liu and Jieneng Chen.
I am currently seeking a Ph.D position in Machine Learning for Fall 2026.
My research interests lie in Machine Learning and Large Language Model, especially on
- Reasoning: reasoning interpretability, MLLM reasoning, reward hack.
- Self-evolution: self-play.
- World Model: simulated world, robotics.
Here is my CV. Please feel free to contact me!
🔥 News
- 2025.08:  🎉 Our paper, NoWait, has been accepted at EMNLP 2025 Findings!
- 2025.05:  🎉 Our paper, CodeSync, has been accepted at ICML 2025!
- 2025.01:  🎉 One paper, GUI-World, has been accepted at ICLR 2025!
📝 Publications

Wait, We Don’t Need to “Wait”! Removing Thinking Tokens Improves Reasoning Efficiency
Chenlong Wang, Yuanning Feng, Dongping Chen, Zhaoyang Chu, Ranjay Krishna, Tianyi Zhouâ€


GUI-World: A Dataset for GUI-oriented Multimodal LLM-based Agents
Dongping Chen*, Yue Huang*, Siyuan Wu, Jingyu Tang, Liuyi Chen, Yilin Bai, Zhigang He, Chenlong Wang, Huichi Zhou, Yiqiang Li, Tianshuo Zhou, Yue Yu, Chujie Gao, Qihui Zhang, Yi Gui, Zhen Li, Yao Wan†, Pan Zhou†, Jianfeng Gao†, Lichao Sunâ€
P.S. * indicates equal contribution. †indicates corresponding author. ‡ indicates project leaders.
đź“– Experience
-
2025.09 - Present, On-site Research Intern at CCVL in Johns Hopkins University.
- 2025.04 - Present, Remote Research Intern in University of Maryland.
- Explore the inherent mechanism in large reasoning models and conduct in-depth research on efficient multimodal reasoning with
NoWait
. - Evaluate and alleviate the reward hack.
- Explore the inherent mechanism in large reasoning models and conduct in-depth research on efficient multimodal reasoning with
- 2024.04 - Present, Research Intern at ONE Lab in Huazhong University of Science and Technology.
- Code generation & interpertability on code knowledge updating task. We propose
CodeSync
, an automated data engine for code knowledge updating. - Research on LLM-based GUI Agents. We propose a dataset
GUI-World
focusing on GUI-oriented capabilities in current MLLMs.
- Code generation & interpertability on code knowledge updating task. We propose
- 2022.09 - 2026.06 (expected), BEng., Huazhong University of Science and Technology.