Signals 4 · free daily AI digest

Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History

Paper recorded by Signals 4 on 2026-09-29 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-29 on arXiv · recorded by Signals 4 on 2026-09-30

Category: cs.CV · 计算机视觉 · first seen 2026-09-30

Abstract

Autoregressive video diffusion enables interactive streaming generation, but suffers from error accumulation over long rollouts. Self-rollout training reduces exposure bias, yet finite rollouts leave long-range drift unresolved. We observe that the noise level of the history key-value (K/V) representations trades visual quality against motion, and that restoring gradients through the history align

Read on arXiv →

#14 most recent of 357 cs.CV papers we have recorded · ↑ newer: GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long- · ↓ older: VISTA: Internalizing Collective Visual Experience via On-Policy Distil
Cite this page: Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History: the #14 most recent of 357 cs.CV papers we have recorded (as of 2026-09-29). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/self-aligned-forcing-streaming-video-diffusion-with-differentiable-noisy-history.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions