Minghong Cai

Ph.D. student at MMLab, The Chinese University of Hong Kong

Email: minghongcai [at] link.cuhk.edu.hk / onevfall [at] gmail.com

Biography

Hi, I'm Minghong Cai (蔡明宏). I am a second-year Ph.D. student at CUHK MMLab, advised by Prof. Xiangyu Yue and Prof. Dahua Lin. Before that, I got my B.E. degree at Tongji University in 2024. My research focuses on building scalable and interactive multimodal generative models, with particular interests in unified multimodal generation, controllable long-form video modeling, and Physical AI. Please do not hesitate to contact me if you are interested in any of my research.

Selected Publications

( show selected / show all by date )

ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection

Ruize Ma^*, Minghong Cai^*, Yilei Jiang^*, Jiaming Han, Yi Feng, Yingshui Tan, Xiaoyong Zhu, Bo Zheng, Xiangyu Yue

EMNLP 2026 Main

[Paper]

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

Kaixin Ding, Xi Chen, Minghong Cai, Zhiyuan Xu, Yiyang Wang, Yuxiang Lu, Junyi Li, Shuyang Chen, Yuan Gao, Xin Tao, Pengfei Wan, Hengshuang Zhao

arXiv 2026

[Paper] [Project Page] [Code] [Dataset] [Leaderboard]

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

Qize Yu, Jiadi You, Yuran Wang, Jiaqi Liang, Bowen Ping, Yang Tian, Yue Chen, Minghong Cai, Zeying Gong, Ruihai Wu, Yinchuan Li, Junwei Liang, Yingcong Chen

arXiv 2026

Affordance-aware vision-language-action modeling for robot manipulation.

[Paper] [Project Page] [Code]

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

Peiwen Sun, Xudong Lu, Huadai Liu, Yang Bo, Dongming Wu, Huankang Guan, Minghong Cai, Jinpeng Chen, Xintong Guo, Shuhan Li, Fang Liu, Rui Liu, Xiangyu Yue

ECCV 2026

[Paper] [Project Page] [Code]