Pinar Yanardag

Generating videos that simultaneously obey multiple interacting physical laws, like buoyancy and fluid dynamics, is now achievable with a novel RL framework that explicitly aligns temporal dynamics and global scene coherence.

Users can now inject custom visual concepts into autoregressive world models without any training, revolutionizing interactive video generation.

Reducing video diffusion memory usage by 92.7% without sacrificing quality could revolutionize streaming video applications.