Kaiwen Zheng

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale