- Rating
- 4
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces Connected Self Forcing (CSF), a training framework for improving long-horizon autoregressive video generation. It propagates feedback from later chunks through historical KV writing and into the computations that generated earlier chunks. Shortcut Gradient Replay recovers selected cross-chunk gradient paths through local recomputation without retaining the full rollout graph. Experiments under multiple initializations report improvements in visual quality and temporal consistency for 60- and 240-second videos, while the inference procedure remains unchanged.
Critical strengths
- The paper is well written and easy to follow, with clear motivation and an accessible explanation of the proposed training framework.
- The motivation is closely aligned with the proposed method. Reconnecting future-to-history gradients directly addresses the missing supervision of historical generation caused by detached KV caches.
- The experiments cover Causal CD, TF, and Causal ODE initializations. The consistently higher Avg.(6) scores across these settings support the effectiveness of the method beyond a single initialization (Tables 1 and 2).
Critical weaknesses
- The novelty appears relatively limited. Overall, the method seems to be an incremental extension of SGF, mainly propagating future feedback beyond KV writing into historical latent generation (Section 3.3).
- The evaluation is not sufficiently comprehensive. While Appendix D.2 provides full VBench results for short videos, the long-video evaluation reports only a subset of dimensions. Additional assessments, such as VisionReward [1] scores or human preference evaluations, are also missing.
- The main experimental comparisons are limited to SF and SGF, leaving the method's competitiveness against a broader range of autoregressive video generation approaches unclear.
- The paper has a strong related work section (History modeling), but it could benefit from a brief discussion of Dummy Forcing [2], Light Forcing [3], and HeadCast [4], particularly their approaches to historical context and attention.
- The experiments primarily focus on single-shot video generation. Could the authors also evaluate the method on multi-shot video generation tasks to assess its generalizability?
[1] Jiazheng Xu et al. VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(13): 11269–11277, 2026.
[2] Hang Guo et al. Efficient Autoregressive Video Diffusion with Dummy Head. arXiv preprint arXiv:2601.20499, 2026.
[3] Chengtao Lv et al. Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention. Proceedings of the 43rd International Conference on Machine Learning, 2026.
[4] Jinliang Shen et al. HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation. arXiv preprint arXiv:2607.20125, 2026.
Questions for authors
See Weaknesses.
Hi Reviewers,
The authors have posted their rebuttal along with new results. Please review their responses, engage with the authors to discuss any remaining concerns.
Best, Area Chair