| title | 4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling |
|---|---|
| authors | Jianhui Zhang, Zuyao Lin, Pengxin Xu, Jingdong Wang, Xingyu Chen |
| date | 2026-10-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.17625 |
| affiliation | Zhongguancun Academy |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| primer | World models |
| abstract | For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated generation at different times and viewpoints. We introduce 4LC, a 4D latent cache with composite visual representations and a flexible spatiotemporal access interface. As a latent cache, 4LC directly reuses visual representations of static and dynamic content to provide generation conditions, avoiding per-request RGB rendering and re-encoding. As a composite cache, 4LC binds visual representations from multiple visual encoders (e.g., VAE, DINO, V-JEPA, VGGT) to shared geometry and motion, allowing the composite representations to describe the dynamic world with rich information. Besides, we design a flexible spatiotemporal interface, which directly reads the cache at independently specified times and viewpoints and combines readouts across observations, providing a common conditioning format for diverse downstream tasks. Building on 4LC, we develop 4LC-Video to address multiple video generation tasks through different configurations of source observations, spatiotemporal requests, and historical reuse, including camera control, temporal control, novel-view synthesis, scene revisits, and long-term generation. Our experiments show more efficient condition acquisition, effective spatiotemporal controllability, and scene consistency across tasks using a single 4LC-Video model without task-specific fine-tuning. |
cite
@misc{zhang2026lc,
title={4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling},
author={Jianhui Zhang and Zuyao Lin and Pengxin Xu and Jingdong Wang and Xingyu Chen},
year={2026},
eprint={2610.17625},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.17625}
}