Rongsheng Wang | 王荣胜

Rongsheng Wang | 王荣胜🧑‍🚀

I am a first-year Ph.D. student at CUHK(SZ) The Chinese University of Hong Kong, Shenzhen, supervised by Prof. Benyou Wang. My research focuses on exploring trustworthy medical large language models (LLMs) and multimodal large models (MLLMs), as well as exploring multimodal generative for healthcare applications.

I like collaborating with Claude Code and CodeX . They are my good partners! I am a perfectionist. I want to solve the problems in my hands in perfect ways, which is, however, not achievable in many situations.

Email: rongshengwang@link.cuhk.edu.cn / CV / Twitter / RedNote Google Scholar / Github

News

Jan. 2026 One paper accepted by ICLR 2026, congrats to all co-authors! See you at Brazil!

May 2025 Two papers accepted by ACL 2025, congrats to all co-authors!

Apr. 2025 Our team won the gold medal in the AIMO-2 competition, ranking 14th out of 2213!

Publications

† Equal contribution. * Corresponding author. The leading papers are highlighted.

If you would like to view my other publications, you are welcome to access them on my Google Scholar.

	GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine? Tongxu Luo†, Rongsheng Wang†, Jiaxi Bi†, Chenming Xu†, Zhengyang Tang†, Jianlong Chen, Juhao Liang, Ke Ji, Shuqi Guo, Yuhao Du, Fan Bu, Wenyu Du, Xiaotong Zhang, Kyle Li, Shaobo Wang, Linfeng Zhang, Yuxuan Liu, Xin Lai, Chenxin Li, Yiduo Guo, Zhexin Zhang, Xinyuan Wang, Tianyi Bai, Ziniu Li, Benyou Wang* Homepage / Code / Paper Preprint GameCraft-Bench evaluates whether agents can build playable games end-to-end in a real game engine.
	MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation Rongsheng Wang†, Minghao Wu†, Hongru Zhou, Zhihan Yu, Zhenyang Cai, Junying Chen, Benyou Wang* Code / Paper / Poster ICLR 2026 (Poster) MicroVerse is a world model designed to faithfully simulate biological processes at the microscale.
	MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos Rongsheng Wang†, Junying Chen†, Ke Ji, Zhenyang Cai, Shunian Chen, Benyou Wang* Code / Paper / Dataset / Model Preprint MedGen is a medical video generation model, built on the large-scale, caption-rich MedVideoCap-55K dataset.
	Exploring Compositional Generalization of Multimodal LLMs for Medical Imaging Zhenyang Cai†, Junying Chen†, Rongsheng Wang†, Weilong Wang, Yonglin Deng, Dingjie Song, Yize Chen, Zixu Zhang, Benyou Wang* Code / Paper / Dataset ACL 2025 (Main) Multimodal LLMs achieve strong generalization in medical imaging largely through compositional generalization (CG).