Multi-Modal Learning Group (MML-Group)

Welcome to MML-Group.

🌐 Resources

• GitHub: https://github.com/MML-Group

• 🤗 Hugging Face: https://huggingface.co/MML-Group

We are a research group dedicated to advancing multimodal artificial intelligence through open research and open-source development.

Our current research focuses on:

• 🎨 Visual Content Generation
• 👁️ Vision-Language Analysis
• 🤖 AI Agents

Our goal is to build foundation models and practical systems that can perceive, generate, reason, and interact across multiple modalities.

As our research progresses, we will continue to release models, datasets, benchmarks, and tools to support the broader AI community.

Vision

We believe the future of AI lies in multimodal intelligence. Through open collaboration and reproducible research, we aim to make multimodal foundation models more capable, accessible, and impactful.

⭐ Follow the organization to stay updated with our latest projects and research.