Da Peng

I am Da Peng, a PhD student at Xi'an Jiaotong University, advised by Wei Ke. My research primarily focuses on UMMs and MLLMs. I am broadly interested in Artificial Intelligence and Machine Learning. I believe that bridging the gap between vision, language, and other modalities is crucial for the next generation of general-purpose AI. My long-term goal is to explore simple, scalable, and effective architectures for multimodal intelligence.

Please feel free to reach out if you are interested in discussing research or potential collaborations.

News

🚀 [2026.05] Joined Tongyi as Research Intern .
🍺 [2026.03] Cheers for Open Source !
🔥 [2026.03] CVPR+1 ! See you in Denver !

Experience

2026.05 - Present

Tongyi (Qwen)

Research Intern

World perception enhancement for multimodal large models.
2024.09 - 2026.04

THUNLP

Research Intern

Unified multimodal models and efficient video understanding.
2023.12 - 2024.02

NEC (China) Co., Ltd.

Intern, Shanghai

More content will be added here soon...

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

🔥 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.

Preprint [Paper] [HuggingFace] [Code]

🔥 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

🔥 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]