Wen Zhou

Satellite foundation models already encode the latent physical signals needed to map ground-level urban livability, bypassing the need for costly ground surveys in data-scarce regions.

HOMIE redefines video personalization by seamlessly integrating inter- and intra-subject inputs, achieving unprecedented fidelity and interaction accuracy.

DomainShuttle achieves unprecedented flexibility in text-to-video generation, allowing seamless transitions between in-domain fidelity and cross-domain creativity.