Da Peng

Da Peng

PhD Student, Xi'an Jiaotong University

Researcher in LVLMs & UMMs

โœ‰๏ธ MetaPDa@gmail.com | ๐Ÿ“ Currently in Beijing

Hi, I'm Da Peng, a Ph.D. student at Xi'an Jiaotong University, advised by Prof. Wei Ke. My research focuses on unified multimodal models and large vision language models. More broadly, I am interested in artificial intelligence and machine learning, particularly in enabling models to better connect and reason across vision, language, and other modalities. Currently, my research is focused on physical perception in real-world environments, where I explore simple yet effective approaches for improving model understanding and reasoning.

I have been fortunate to collaborate with many talented researchers, including Zonghao Guo, Yansong Li, Shichu Sun, Jiale Wang, Xuesong Yang, and Yichen Zhang. This list will continue to grow over time.

Feel free to reach out if you are interested in discussing research ideas or potential collaborations.

News

  • ๐Ÿ”ฅ [2026.06] ECCV+1 !
  • ๐Ÿš€ [2026.05] Joined Tongyi as Research Intern .
  • ๐Ÿบ [2026.03] Cheers for Open Source !
  • ๐Ÿ”ฅ [2026.03] CVPR+1 ! See you in Denver !

Experience

  • 2026.05 - Present
    Tongyi (Qwen)
    Research Intern ยท World perception enhancement for multimodal large models.
  • 2024.09 - 2026.04
    THUNLP
    Research Intern ยท Unified multimodal models and efficient video understanding.
  • 2023.12 - 2024.02
    NEC (China) Co., Ltd.
    Intern

More content will be added here soon...

* Equal Contribution  |  All works will be organized and added soon.

๐Ÿ”ฅ Qwen3.8-Max: A New Bar for Coding and Cowork

Qwen Team

Technical Report [Blog]

๐Ÿ”ฅ Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Yichen Zhang*, Da Peng*, Zonghao Guo, Zijian Zhang, Xuesong Yang, Tong Sun, Shichu Sun, Yidan Zhang, Yanghao Li, Haiyan Zhao, Wang Xu, Qi Shi, Yangang Sun, Chi Chen, Shuo Wang, Yukun Yan, Xu Han, Qiang Ma, Wei Ke, Liang Wang, Zhiyuan Liu, Maosong Sun.

ECCV 2026 [Paper] [HuggingFace] [Code]

๐Ÿ”ฅ FlexiVideo: Variation-Aware Temporal Dynamics Modeling for Efficient Video Understanding

Da Peng*, Xuesong Yang*, Zonghao Guo, Yichen Zhang, Chi Chen, Yidan Zhang, Yuan Yao, Fang Wan, Wei Ke, Maosong Sun.

CVPR 2026 [Paper] [Code]

๐Ÿ”ฅ Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition

Xiaoying Zhang, Da Peng, Yipeng Zhang, Zonghao Guo, Chengyue Wu, Jen-Tse Huang, Chi Chen, Wei Ke, Helen Meng, Maosong Sun.

Preprint [Paper] [Code]