GitHub

Hi there 👋

I'm ✨ Kunchang Li ✨, a researcher at Seed, Bytedance.

Please check my website for more details.

💼 Experiences

  • [2016-2020]🎉 I received my B.E. degree in Software Engineering at Beihang University.
  • [2020-2025]💪 I received my Ph.D. degree in Computer Science at SIAT, UCAS, advised by Prof. Yu Qiao and Prof. Yali Wang. I have been a Research Intern at MEGVII, SenseTime, Shanghai AI Lab and Bytedance.

🔭 Research Interests

  • 📹 Video Understanding
  • ⚡️ EfficientArchitecture
  • 📚 Multi-modality Learning
  • 🦄 Video Generation
  • 🤔 Unified Model

Pinned Loading

  1. Open-source unified multimodal model

    Python 6.2k 545

  2. [ECCV2024] Video Foundation Models & Data for Multimodal Understanding

    Python 2.4k 159

  3. [CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

    Python 3.3k 268

  4. [ICCV2023 Oral] Unmasked Teacher: Towards Training-Efficient Video Foundation Models

    Python 348 18

  5. [ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

    Python 1.1k 96

  6. [ICLR2022] official implementation of UniFormer

    Python 908 115

Read the original on github.com ↗