Xianfeng Wu

Xianfeng Wu (吴显峰)

Research Intern

Currently, I am working closely with Tianlong Chen. My research interests lie in Multi-modal Foundation Models, 3D Vision, and AI4Science.

Latest News

Selected Publications

Relight Teaser

Learning Latent Proxies for Controllable Single-Image Relighting

Haoze Zheng*, Zihao Wang*, Xianfeng Wu*, Yajing Bai, Yexin Liu, Yun Li, Xiaogang Xu, Harry Yang
CVPR'26
4DLangVGGT Teaser

4DLangVGGT: 4D Language Visual Geometry Grounded Transformer

Xianfeng Wu*, Yajing Bai*, Minghan Li, Xianzu Wu, Xueqi Zhao, Zhongyuan Lai, Wenyu Liu, Xinggang Wang
Arxiv
PDF Code Project
LightGen Teaser

LightGen: An Efficient Text2Img Generation Pretrain Pipeline based on MAR

Xianfeng Wu*, Yajing Bai*, Haoze Zheng*, Harold Haodong Chen*, Yexin Liu*, et al.
ArXiv
PDF Code
ProfilingDIT Teaser

Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models

Xuran Ma, Yexin Liu, Yaofu Liu, Xianfeng Wu, et al.
ICCV'25
Code
Unveiling Teaser

Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly

Yexin Liu*, Zhengyang Lian*, Yueze Wang*, Xianfeng Wu*, , et al.
CVPR'25
Code
FSC Teaser

FSC: Few-point Shape Completion

Xianzu Wu*, Xianfeng Wu*, Tianyu Luan, Yajing Bai, Zhongyuan Lai, Junsong Yuan
CVPR'24
Code

* Full publication list available on Google Scholar.

Experience