Ye Fang | Fudan University

About Me

I am a Ph.D. student at Fudan University, with expected graduation in June 2028, supervised by Prof. Dahua Lin. I also work closely with Dr. Tong Wu and Dr. Jiaqi Wang.

My research spans world models, controllable video generation, and multimodal understanding. I am also interested in interactive virtual worlds, gaming, and embodied intelligence.

Please feel free to contact me if you’re interested in related research or would like to discuss potential collaborations!

Contact me via Email

Google Scholar Citations: 648

Research Vision

From seeing the world to acting in it.

I am interested in how models perceive, generate, and interact with the world.

Interactive world models

Modeling how environments evolve and respond to actions. I am interested in spatial and temporal consistency, memory across interactions, and predicting future states in virtual and physical environments.

Controllable video generation

Generating and editing videos with precise control over motion, appearance, lighting, and materials, while maintaining temporal consistency and preserving content that should remain unchanged.

Multimodal understanding

Connecting language with visual and 3D representations to understand objects, scenes, and events. I am interested in spatial and temporal reasoning across images, videos, and 3D data.

News

Sep 2026GPT-Policy was released: in-context robot learning with VLM agents.
Feb 2026V-RGBX was accepted by CVPR 2026.
Jan 2026GPT4Scene was accepted by ICLR 2026.
Jul 2025GPT4Point++ was accepted by IEEE TPAMI.

Publications

Google Scholar

(Co-)First Author Publications

CVPR 2026

V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties

Ye Fang, Tong Wu, Valentin Deschaintre, Duygu Ceylan, Iliyan Georgiev, Chun-Hao Paul Huang, Yiwei Hu, Xuelin Chen, Tuanfeng Yang Wang

Paper Project Code Video

First author

NeurIPS 2024

Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials

Ye Fang^*, Zeyi Sun^*, Tong Wu, Jiaqi Wang, Ziwei Liu, Gordon Wetzstein, Dahua Lin

Paper Project Code Video

First author · Equal contribution

Preprint 2025

RelightVid: Temporal-Consistent Diffusion Model for Video Relighting

Ye Fang^*, Zeyi Sun^*, Shangzhan Zhang, Tong Wu, Yinghao Xu, Pan Zhang, Jiaqi Wang, Gordon Wetzstein, Dahua Lin

Paper Project Code Video

First author · Equal contribution

Preprint 2026GPT-Policy

In-Context Robot Learning with VLM Agents

Dongzhou Cheng^*, Taoran Yi^*, Ye Fang^*, Xingwu Zhang^*, Fan Feng^*, Yixuan Li^*, Gengxiong Zhuang^*, Rongze Wang, Shuai Yang, Wei Song, Weizhi Xue, Minyan Wu, Jie Gui, Jiaqi Wang, Tong Wu^†