Research Highlights

Developing robust methods to perceive, understand, and reconstruct the 3D world from visual data.

Integrating vision and language to build powerful multimodal foundation models for diverse real-world tasks.

Building deep learning models that respect geometric structure through invariance and equivariance principles.

Combining spatial perception and machine learning to enable reliable, generalizable embodied AI in the physical world.

Translating computer vision and multimodal AI research into real-world systems, from AR/VR to autonomous driving.

We integrate the geometric deep learning module on the existing vision-langauge foundation model.