跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-13AI 評分40

4LC:用 4D 潛在快取提升動態世界建模的條件生成效率

4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling

AI 導讀

研究提出 4LC,一種用於動態世界建模的 4D 潛在快取,可重用靜態與動態視覺表示作為生成條件,避免每次請求都進行 RGB 渲染和重新編碼。它將多個視覺編碼器的表示與共享幾何及運動資訊結合,並可按指定時間和視點讀取。基於 4LC 的 4LC-Video 支援鏡頭控制、時間控制、新視點合成、場景重訪及長期生成,單一模型毋須按任務微調。

正文

Published on Oct 13

Authors:

,

,

,

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.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.17625

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

jianhuizhang/4LC-Video

Updated about 3 hours ago

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.17625 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.17625 in a Space README.md to link it from this page.

Collections including this paper 1

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co