Paper recorded by Signals 4 on 2026-10-21 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-21 on arXiv · recorded by Signals 4 on 2026-10-22
Category: cs.CV · 计算机视觉 · first seen 2026-10-22
Increasing the attention context length significantly improves streaming video generation quality, while incurring prohibitive memory and computational costs as the context grows. Existing methods attempt to capture this contextual information through attention selection or compression, but remain limited by bounded representations and lack explicit attention-level supervision to retain historical