Official implementation of Context Forcing: Consistent Autoregressive Video Generation with Long Context
Shuo Chen*, Cong Wei*, Sun Sun, Ping Nie, Kai Zhou, Ge Zhang, Ming-Hsuan Yang, Wenhu Chen
Abstract: Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long rollouts but receives supervision from a teacher limited to short 5-second windows. This structural discrepancy creates a critical student-teacher mismatch: the teacher's inability to access long-term history prevents it from guiding the student on global temporal dependencies, effectively capping the student's context length. To resolve this, we propose Context Forcing, a novel framework that trains a long-context student via a long-context teacher. By ensuring the teacher is aware of the full generation history, we eliminate the supervision mismatch, enabling the robust training of models capable of long-term consistency. To make this computationally feasible for extreme durations (e.g., 2 minutes), we introduce a context management system that transforms the linearly growing context into a Slow-Fast Memory architecture, significantly reducing visual redundancy. Extensive results demonstrate that our method enables effective context lengths exceeding 20 seconds—$2\text{--}10\times$ longer than state-of-the-art methods like LongLive and Infinite-RoPE. By leveraging this extended context, Context Forcing preserves superior consistency across long durations, surpassing state-of-the-art baselines on various long video evaluation metrics.
- 🔥🔥 News:
2026/2/5: Arxiv paper and project page released.
- [] Opensourse inference code and checkpoints. Refactoring the codebase; will be open-sourced shortly.
- [] Opensourse training code.
We would like to thank the following work for their exceptional effort.
- CausVid
- Self Forcing
- LongLive
- Rolling Forcing
- Infinity-RoPE
- WorldPlay
- Stable Video Infinity
- FramePack
If you find this codebase useful for your research, please kindly cite our paper:
@misc{chen2026contextforcingconsistentautoregressive,
title={Context Forcing: Consistent Autoregressive Video Generation with Long Context},
author={Shuo Chen and Cong Wei and Sun Sun and Ping Nie and Kai Zhou and Ge Zhang and Ming-Hsuan Yang and Wenhu Chen},
year={2026},
eprint={2602.06028},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2602.06028},
}