Xiangpeng Yang

Hi, I'm Xiangpeng. I am currently a Ph.D. student at the University of Technology Sydney (UTS).

My research interests involve Generative AI, Video Generation, and Multi-modal Learning. Specifically, I focus on video world models, video generation, and multi-modal foundation models.

Looking ahead, I am deeply motivated to build unified video models capable of jointly understanding dynamic visual environments and generating coherent future content within a single framework. I believe this direction is a crucial step toward world models, where systems can reason about and interact with the physical world through continuous video understanding and prediction.

I am currently seeking research intern opportunities. If there are suitable positions available, please feel free to reach out. Thank you!

• [12/2025] We Release the Code and Model of VideoCoF.
• [07/2025] Gave an invited talk at Sydney AI Meet-Up.
• [06/2025] Gave an invited talk at Twelve Labs (video).
• [03/2025] Gave an invited talk at Qingke AI (video).
• [01/2025] VideoGrain is accepted to ICLR 2025.
• [12/2023] DGL is accepted to AAAI 2024.

• Unified Video Editing with Temporal Reasoner

  Xiangpeng Yang, Ji Xie, Yiyuan Yang, Min Xu, Qiang Wu

  ArXiv (2025)

  TL;DR: Seeing, Reasoning, then Editing, A Unified Framework Reasoning over Video Content before Editing.

  ArXiv Project Code Hugging Face Video
• VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing

  Xiangpeng Yang, Linchao Zhu, Hehe Fan, Yi Yang

  The International Conference on Learning Representations (ICLR), 2025

  TL;DR: The first work propose Multi-Grained Video Editing, including Class, Instance and Part-level

  Paper Project Code Video
• 
  DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval

  Xiangpeng Yang, Linchao Zhu, Xiaohan Wang, Yi Yang

  AAAI Conference on Artificial Intelligence (AAAI), 2024

  TL;DR: Training only 0.83 MB parameters to achieve better performance than full finetuning.

  Paper Code Video

• Baidu Research — Aug 2022 – Mar 2023 (Beijing)
• ByteDance AI Lab — May 2021 – Sep 2021 (Beijing)

• Baidu AI Studio - Lane Recognition Competition, Top 3/1020 (2020)

• Regular Reviewer: CVPR, ICLR, ICML, NeurIPS, ICCV, ECCV