Hi! Here is Yuhang

Yuhang Chen (陈宇航)

Yuhang Chen (or Francis, a name from a novel and TV series he really likes, House of Cards) is an apprentice.

He is a Junior student in the School of Computer Science and Technology (Qiming College) at Huazhong University of Science and Technology (HUST), Wuhan, China. He is fortunate to be guided by Associate Professor Yao Wan from HUST. He is a member in ONE Lab, where he met his academic mentor, Dongping Chen (PhD student, now at the University of Maryland).

His research interests lie in 3D spatial reconstruction and generation, multimodal foundation models and world models, He is continuing to take his initial steps in scientific research. He is always a learner.

News

(04/25/2025) Our paper Paper2Web has been accepted to ACL 2026!

(02/28/2026) Our paper GapEval has been accepted to CVPR 2026 Findings!

(01/10/2026) Our paper GapEval has been Preprinted!

(10/10/2025) Our paper Paper2Web has been Preprinted!

(03/25/2025) Our paper Judge Everything has been accepted to KDD 2025 (oral)!

(11/20/2024) Our paper Judge Everything has been Preprinted!

(09/01/2023) I begin my University life!

Publications

Selected publications are highlighted. Equal contribution^*. Project lead^✝. Corresponding author^✉.

	Quantifying the Gap between Understanding and Generation within Unified Multimodal Models Chenlong Wang^, Yuhang Chen^, Zhihan Hu^, Dongping Chen, Wenhu Chen, Sarah Wiegreffe, Tianyi Zhou^✉ arXiv BibTeX CVPR 2026 Findings* GapEval is a framework evaluating inference consistency in multimodal models. Results show misalignment between understanding and generation, exposing limits of “unified” architectures and calling for deeper cognitive convergence.
	PAPER2WEB: LET’S MAKE YOUR PAPER ALIVE! Yuhang Chen^, Tianpeng Lv^, Siyi Zhang, Yixiang Yin, Yao Wan^1✉, Philip S. Yu, Dongping Chen^✝ Website arXiv Code BibTeX *ACL 2026* Paper2Web is the first benchmark for assessing academic webpage generation, and PWAgent, an autonomous system designed to bridge the gap between static PDFs and interactive project sites
	JUDGE ANYTHING: MLLM AS A JUDGE ACROSS ANY MODALITY Shu Pu^§, Yaochen Wang^§, Dongping Chen^✝, Yuhang Chen^* Guohao Wang^, Qi Qin^, Zhongyi Zhang^* Zhiyuan Zhang^, Zetong Zhou^, Shuang Gong^, Yi Gui, Yao Wan^✉, Philip S. Yu Website arXiv Code Data BibTeX KDD 2025 oral* We extend MLLM-as-a-Judge across multiple modalities, present TaskAnything and JudgeAnything benchmarks that reveal MLLM-as-a-Judge excel at judging MMU but struggle with MMG tasks.

Research Projects

	Quantifying the Gap between Understanding and Generation within Unified Multimodal Models arXiv BibTeX GapEval is a framework evaluating inference consistency in multimodal models. Results show misalignment between understanding and generation, exposing limits of "unified" architectures and calling for deeper cognitive convergence.
	PAPER2WEB: LET'S MAKE YOUR PAPER ALIVE! Website arXiv Code BibTeX Paper2Web is the first benchmark for assessing academic webpage generation, and PWAgent, an autonomous system designed to bridge the gap between static PDFs and interactive project sites.
	JUDGE ANYTHING: MLLM AS A JUDGE ACROSS ANY MODALITY Website arXiv Code Data BibTeX We extend MLLM-as-a-Judge across multiple modalities, present TaskAnything and JudgeAnything benchmarks that reveal MLLM-as-a-Judge excel at judging MMU but struggle with MMG tasks.

Research Experience

ONE Lab, HUST
Nov. 2024 - Present
Multimodal Foudation Models and Multimodal Agents.

University of Maryland
Nov. 2025 - Jan. 2026
Unidfied Model and World Model

Education Experience

Huazhong University of Science and Technology
B.S. in Computer Science, 2023-2027(expected.)

Remote Intern
Research intern, 2025.11 - 2026.1

Honors and Awards

Outstanding Academic Performance Scholarship, 2023.9.
Outstanding Academic Performance Scholarship, Technology Innovation Scholarship, 2024.9.
Second Prize in the Hubei Province Artificial Intelligence Practical Competition, 2025.5.
Third Prize in Computer System Development Capability Competition, 2025.9.
Second Prize in RuiKang Robot Developer Competition, 2025.9.
Outstanding Academic Performance Scholarship, Technology Innovation Scholarship, 2025.10.

Here are photos I took while traveling in Japan. I love traveling in Japan—the people, the scenery, and the food. I hope to study there someday and eventually settle down in this wonderful and fascinating country.

Hey, There. I'm Yuhang Chen

Cinephile

Researcher