Chen-Yang Si

An understanding-driven approach unlocks systematic spatial-memory management for world models, dramatically improving long-video generation quality.

AURORA-LM achieves state-of-the-art performance in language generation by leveraging a continuous-latent diffusion framework that preserves text fidelity while enhancing generative capabilities.

Achieve high-fidelity, temporally coherent video editing without paired training data by combining sparse semantic control with dense motion and texture synthesis.