Wujian Peng 彭舞鉴

Ph.D. Candidate
School of Computer Science, Fudan University & Shanghai Innovation Institute

Email | Google Scholar | GitHub

Biography

I am a final-year Ph.D. candidate at Fudan University and Shanghai Innovation Institute , advised by Prof. Zuxuan Wu. I received my B.S. degree from Xi'an Jiaotong University in 2022. I am currently a research intern with the Qwen Team, working on large multimodal models and multimodal agents.

My current research interests include:

Large Multimodal Models: Enhancing fine-grained recognition and real-world understanding.
Unified Multimodal Models: Unifying multimodal understanding and generation within a shared architecture.
Multimodal Physical Agent: Building multimodal agents for embodied navigation and manipulation.

I am expected to graduate in 2027 and am actively seeking job opportunities. Please feel free to reach out to me via email: wjpeng22[AT]m[DOT]fudan[DOT]edu[DOT]cn .

Internship

Qwen Team

Research Intern

Aug 2025 – Present

Contributed to the development of Qwen3.7, Qwen3.8, and Qwen4.0.

Publications

* denotes equal contribution, † denotes corresponding author

LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation

Zijie Diao, Yitong Chen, Sicheng Xie, Tianyi Lu, Wujian Peng, Guojin Zhong, Houze Xu, Ziyi Ye, Zuxuan Wu, Yu-Gang Jiang

Under review

📄 Paper GitHub

Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification

Wujian Peng*, Lingchen Meng*, Yuxuan Cai, Xianwei Zhuang, Yuhuan Yang, Rongyao Fang, Chenfei Wu, Junyang Lin, Zuxuan Wu†, Shuai Bai†

ICML, 2026

📄 Paper GitHub

Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization

Zhuohan Liu*, Wujian Peng*, Yitong Chen, Zuxuan Wu†

CVPR, 2026

📄 Paper GitHub

INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning

Wujian Peng*, Lingchen Meng*, Yitong Chen, Yiweng Xie, Yang Liu, Tao Gui, Hang Xu, Xipeng Qiu,
Zuxuan Wu†, Yu-Gang Jiang

NeurIPS, 2025

📄 Paper GitHub

Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding

Wujian Peng, Sicheng Xie, Zuyao You, Shiyi Lan, Zuxuan Wu†

CVPR, 2024

📄 Paper GitHub

BMB: Balanced Memory Bank for Long-Tailed Semi-Supervised Learning

Wujian Peng, Zejia Weng, Hengduo Li, Zuxuan Wu†, Yu-Gang Jiang

TMM, 2024

Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data

Zuxuan Wu*, Zejia Weng*, Wujian Peng, Xitong Yang, Ang Li, Larry S Davis, Yu-Gang Jiang

TPAMI, 2024

📄 Paper GitHub

Enhancing Vision Foundation Models via Multimodal Continual Pre-Training

Yitong Chen*, Lingchen Meng*, Wujian Peng,Jun Tao, Chenjie Xu, Zuxuan Wu†, Yu-Gang Jiang

WAICA, 2026

Best Student Paper Award

📄 Paper GitHub

Technical Reports

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Qwen Team

📄 Paper GitHub Blog

Honors & Awards

Outstanding Student, Fudan University
Outstanding Student, Xi'an Jiaotong University

Professional Service

Journal Reviewer: TIP, TMM
Conference Reviewer: CVPR, ICCV, ICML, ICLR, NeurIPS