Bei Liu

Senior Researcher, Microsoft Research Asia, Beijing.

prof_pic.jpg

📍 Beijing, China

🏢 Microsoft Research Asia

🔬 Visual Computing Group

My research focuses on Multimodal AI, Document Understanding, and AI Agents. I also serve as a Guest Associate Professor at Nagoya University in Japan. Before joining Microsoft, I earned my Ph.D. and Master’s degrees from Kyoto University, Japan, under the guidance of Professors Katsumi Tanaka, Masatoshi Yoshikawa, and Makoto P. Kato. I hold a Bachelor’s degree from Nanjing University, China.

My current interest is in enabling agents that actively read, navigate, and reason over complex documents, combining perception, planning, and tool use.

I am open to research collaboration, academic visits, and supervising interns working on multimodal agents. Feel free to reach out!

news

Jan 1, 2025 One paper accepted to MMM 2025, awarded 🏆 Best Paper!
Dec 1, 2024 One paper accepted to ACM MMAsia 2024, awarded Best Student Paper Runner-Up. 🎉

selected publications

  1. NeurIPS
    Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning
    Yuchong Sun, Hongwei Xue, Ruihua Song, Bei Liu, Huan Yang, and Jianlong Fu
    In NeurIPS, 2022
  2. CVPR
    Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions
    Hongwei Xue, Tiankai Hang, Yanhong Zeng, Yuchong Sun, Bei Liu, Huan Yang, Jianlong Fu, and Baining Guo
    In CVPR, 2022
  3. ICLR
    CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment
    Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, and Jiebo Luo
    In ICLR, 2023
  4. NeurIPS
    Spatiotemporal Predictive Pre-training for Robotic Motor Control
    Jiange Yang, Bei Liu, Jianlong Fu, Bocheng Pan, Gangshan Wu, and Limin Wang
    In NeurIPS, 2024
  5. MMAsia
    ViCo: Engaging Video Comment Generation with Human Preference Rewards
    Yuchong Sun, Bei Liu, Xu Chen, Ruihua Song, and Jianlong Fu
    In MMAsia, 2024
    Best Student Paper Runner-Up