Chunyan Miao

Real-world proactive agents can now infer latent user needs and act on them in real-time, rivaling state-of-the-art models in intent detection while maintaining low latency.

Stop wasting compute: selectively activating reasoning in embodied agents based on action entropy slashes computational cost while boosting navigation performance.

Noisy real-world graphs are holding back heterogeneous graph learning, but ToGRL's two-stage topology learning approach unlocks significant performance gains.

Clinical AI can achieve clinician-level diagnostic accuracy and continuous improvement via a self-evolving framework that actively learns from clinical experience.