Skip to content
@Multimedia-Semantic-Analytics-Lab

Multimedia Semantic Analytics Lab

MSALab

Multimedia Semantic Analytics Lab

The Multimedia Semantic Analytics Lab (MSALab), led by Prof. Yunhai Tong, is a research group at Peking University dedicated to advancing the frontier of Artificial Intelligence through high-quality research, education, and real-world impact.


🌟 About Us

MSALab is a center of excellence focusing on semantic understanding across multiple modalities.
Our mission is to explore state-of-the-art AI methods that enable machines to better understand and generate meaning from vision, language, and video.

We conduct fundamental and applied research to push forward the capabilities of modern AI systems in perceiving and reasoning about the world.


🔬 Research Highlights

Our research interests include, but are not limited to:

  • Multi-modal Learning
  • Visual Perception
  • Video Content Analysis
  • Language and Semantic Understanding

We aim to bridge different modalities and uncover the semantic structures behind diverse data sources.


🚀 Current Research Directions

We are currently focusing on the following key directions:

  1. Multi-modal Large Language Models (MLLMs)
  2. Text-to-Image and Text-to-Video Generation & Editing
  3. Large Language Models (LLMs)

🎓 Join Us

MSALab is actively recruiting self-motivated research interns and Ph.D. students.

We are looking for candidates who:

  • Have strong coding skills
  • Possess a solid mathematical background
  • Show strong interest in:
    • Multi-modal learning
    • Large Language Models
    • Text-to-Image / Text-to-Video generation and editing

📍 Location: Peking University

If you are passionate about cutting-edge AI research, we warmly welcome you to join our team.


📄 Publications

Recent research works can be found here
(Link to be updated)


📫 Contact

For collaboration or recruitment inquiries, please contact us through official channels.


Multimedia Semantic Analytics Lab · Peking University

Popular repositories Loading

  1. LoomVideo LoomVideo Public

    Official implementation of LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing

    Python 80 3

  2. PerceptionDLM PerceptionDLM Public

    Official Repo For PerceptionDLM Codebase

    Python 77 4

  3. .github .github Public

Repositories

Showing 3 of 3 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…