Research

Our research focuses on developing machine learning methods that enable AI systems to autonomously interact with the world, learn generalizable rules from experience, and drive automatic self-evolution and scientific discovery in efficient ways.

AI for AI that improves AI.

We develop AI methods that autonomously develops and improves AI models. Our research focuses on:

AI-driven scientific discovery.

We leverage self-evolving AI with improved creativity to accelerate discoveries in biomedical sciences.

Research Themes

Our work spans fundamental machine learning research and applications in biomedical sciences:

Fundamental ML:

• Discrete neural communication
• Generative flow networks (GFlowNets)
• Multi-agent reinforcement learning
• Federated learning
• Continual learning

Biomedical Applications:

• Electronic health records analysis
• Medical imaging
• Genomic data integration
• Drug discovery and development