Zeyue Xue

SGF bridges the gap in video generation by allowing future losses to inform past latent encodings, resulting in unprecedented long-video extrapolation capabilities.

Ultra Flash achieves real-time high-resolution video generation at unprecedented frame rates, pushing the boundaries of what’s possible in streaming video AI.

Raw context outperforms compact memory designs, revealing that memory structure is crucial for effective video generation in action-conditioned models.

Real-time infinite video generation is now feasible, achieving over 1.3 million frames in a single 24-hour rollout without sacrificing quality.

Unlock the full potential of your pretrained video diffusion models with a surprisingly simple four-stage post-training framework that drastically improves visual quality, temporal coherence, and instruction following.

Achieve real-time, synchronized audio-visual generation at 25 FPS by distilling a bidirectional diffusion model into a fast, autoregressive architecture, overcoming training instability with novel alignment and token handling techniques.