arXiv：cs.AI· Yifan Shen, Yewei Xia, Gongxu Luo, Peiyuan Zhu, Boyang Sun, Zhenhao Chen, Guangyi Liu, Guangyi Chen, Kun Zhang·· 17 小时前
Prospective Forcing：让自回归长视频扩散模型学会前瞻预测
Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion
AI 导读
研究者提出 Prospective Forcing，一种多头预测框架，通过挂载共享条件的轻量偏移专用预测头，让自回归视频生成器在训练时同时预测多个未来时间偏移的视频块，而非仅预测下一块，从而提升长视频生成的时间一致性。推理阶段可利用被接受的未来块预测跳过完整窗口的主干执行以加速采样，并通过可学习嵌入生成多个候选块，由学习到的验证器择优或回退到标准自回归生成。
正文
Abstract:Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future. This limited prediction horizon makes it challenging to maintain video quality over extended rollouts. To address this problem, we introduce Prospective Forcing, a multi-head prediction framework that injects long-range predictive signals into autoregressive video representations. Built on a rolling-window generator, Prospective Forcing attaches lightweight, offset-specific heads that share the same conditioning information and independently predict chunks at different future temporal offsets. By extending supervision beyond the next chunk, these heads encourage the shared history representation to retain information useful for longer-horizon prediction, supporting temporally consistent generation. At inference time, we accelerate sampling by using accepted future-chunk predictions to skip full-window backbone executions. We equip the head with learnable embeddings to generate multiple candidates for the next chunk, and a learned verifier either selects a candidate or rejects all and falls back to standard autoregressive generation.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14654 [cs.CV] |
| (or arXiv:2610.14654v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14654 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yifan Shen [view email]
[v1]
Sat, 10 Oct 2026 07:07:54 UTC (14,400 KB)
来源：arXiv：cs.AI · arxiv.org