Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning

Excerpt

arXiv:2608.14706v1 Announce Type: cross Abstract: Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data. We introduce Equilibrium Forcing (EqF), a simplified framework for video denoising generative models without noise level conditioning. EqF pioneers modular training- and inference-time designs for noise-unconditional generation that decoup