Towards One-step Causal Video Generation via Adversarial Self-Distillation

ArXi:2511.01419v2 Announce Type: replace Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a distillation-based framework for efficient causal video generation that enables high-quality synthesis with extremely limited denoising steps.