Medical AI / AI for Science
Empowering clinical decision-making through AI-based medical image analysis and diagnosis for comprehensive patient care.
Foundation Model
We study how to adapt and fine-tune foundation models for domain-specific tasks, with a focus on efficient and robust transfer to areas such as medicine and robotics.
Physical AI
Advancing the frontier of Embodied AI by integrating multimodal perception with real-world robotic control to automate complex physical tasks.
Generative AI
Advancing the theoretical understanding and empirical performance of generative AI models, including diffusion models, autoregressive models, and other emerging generative paradigms.
High-level Scene Understanding
Developing high-level scene understanding models such as semantic segmentation, object detection, and scene reconstruction for autonomous systems, robotics, and other applications.