| title | DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory |
|---|---|
| authors | Zhenhao Yang, Xiaoshi Wu, Zhengyao Lv, Xiaoyu Shi, Xintao Wang, Pengfei Wan, Kun Gai, Kwan-Yee K. Wong |
| date | 2026-05-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.31336 |
| affiliation | KlingAI Research |
| upvotes | 10 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| primer | World models |
| abstract | Recent advances in video generative models have promoted rapid progress in controllable world models. However, maintaining fine-grained spatio-temporal consistency under long-horizon reasoning remains a key challenge. In this work, we move beyond explicit 3D memory and coarse frame-level implicit modeling, and propose a fine-grained, learnable, and scalable memory for consistent world generation. We first identify two fundamental limitations of naïve learnable memory architectures in long-horizon extrapolation, namely computational inefficiency and attention dispersion. Through a systematic analysis of attention dispersion, we propose DecMem, a decoupled memory architecture that employs Sparse Global Memory for efficient fine-grained access to global history and Anchored Local Memory for stable and high-quality extrapolation. Extensive experiments demonstrate that DecMem significantly outperforms current state-of-the-art methods. By ensuring precise and efficient long-term memory and achieving superior extrapolation capabilities, DecMem enables minute-level controllable long video generation with high fidelity and consistency. |
cite
@misc{yang2026decmem,
title={DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory},
author={Zhenhao Yang and Xiaoshi Wu and Zhengyao Lv and Xiaoyu Shi and Xintao Wang and Pengfei Wan and Kun Gai and Kwan-Yee K. Wong},
year={2026},
eprint={2605.31336},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.31336}
}