Interest

Recovering 3D structure from 2D images via correspondence, pose, geometry, reconstruction, and equivariance.

Building multi-modal LLMs that see, hear, reason, and act across images, audio, video, and 3D scenes.

Feed-forward 3D foundation models that recover geometry, correspondence, and renderable scenes from images.

Symmetry, invariance, and equivariance as inductive biases for geometrically aware representations.

Building embodied agents that perceive in 3D, reason with language, and act reliably in the physical world.

Spatial AI as a core engine for AI+X across AR/VR, driving, healthcare, infrastructure, and animal behavior.