Preprint
Jul 2026
Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency
This work proposes Cycle-World, a novel framework designed for stable and temporally consistent long-video generation that tackles error drift by enforcing strict temporal reversibility across both the training and inference phases, and demonstrates that forward generative drift can be strictly bottlenecked by a cycle-...
Zihan Su, Teng Hu, Jiangning Zhang et al.
· 1 citation