Shu Pu

I'm an undergraduate student at Huazhong University of Science and Technology (HUST) in Wuhan, and it's my privilege to work with Professor Yao Wan there. I am currently a research intern supervised by Zhuang Liu. I'm interested in Physical World Perception and Generation, 3D Vision and Computer Graphics. Some particular directions, such as Unified Models and Diffusion Models, are included.

I am actively seeking Ph.D. positions for Fall 2026.

Email  /  CV  /  Bio  /  Scholar  /  Github  /  Transcript  /  Blog

profile photo

Research

I'm interested in Physical World Perception and Generation, 3D vision and computer graphics.

Memorization in 3D Shape Generation: An Empirical Study
Shu Pu, Boya Zeng, Kaichen Zhou, Mengyu Wang, Zhuang Liu
Under review, CVPR 2026
Paper (coming soon) / Code

An empirical study of memorization in 3D shape generation models.

Judge Anything: MLLM as a Judge Across Any Modality
🎉🎉🎉 Accepted by ACM KDD 25' DB Track Oral!
Shu Pu, Yaochen Wang, Dongping Chen, Zhiyuan Zhang*, Zetong Zhou*, Shuang Gong*, Yuhang Chen*, Qi Qin*, Zhongyi Zhang*, Guohao Wang*, Yi Gui, Yao Wan, Philip S. Yu
Arxiv, 2025
ArXiv / GitHub

A system analysis for utilizing MLLM as a judge across any modality and an Omni-Modality competitive arena.

ISGBench: Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment
🎉🎉🎉 Accepted by ICLR 25' Spotlight!
Dongping Chen*, Ruoxi Chen*, Shu Pu*, Zhaoyi Liu*, Yanru Wu*, Caixi Chen*, Benlin Liu, Yue Huang, Yao Wan, Pan Zhou, Ranjay Krishna
ICLR, 2025
pdf / arXiv / GitHub

A comprehensive evaluation framework for interleaved text-and-image generation.


Thanks to this Jon Barron's website template to create such a clean and neat personal website. The source code is open-source. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.