跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-09-26AI 評分35

Adaptive Latent Capacity for World Models

Adaptive Latent Capacity for World Models

AI 導讀

Adaptive LeWorldModel(ALeWM)是一種基於 JEPA 的世界模型,透過學習前綴長度分佈,將預測資訊集中在寬廣潛在表示的緊湊前綴中。研究另提出 MixSIGReg,鼓勵較早的座標保留更多有助預測及遞迴規劃的資訊。在受控動態系統及目標條件視覺控制測試中,ALeWM 的平均成功率持續高於經調校的固定寬度 LeWM,平均規劃容量則較低。

正文

Published on Sep 26

Authors:

,

,

,

Abstract

We introduce Adaptive LeWorldModel (ALeWM), a world model based on a joint-embedding predictive architecture (JEPA) that learns to concentrate predictive information in compact prefixes of a wide latent representation. To encourage this ordering, ALeWM learns a sequence-conditioned distribution over prefix lengths and trains the predictor to estimate the full next embedding from a sampled input prefix. As standard anti-collapse objectives encourage variation across latent coordinates and do not organize them by predictive importance, we also introduce MixSIGReg. MixSIGReg regularizes the masked embeddings against a prior-weighted mixture with Gaussian active prefixes and zeros in the remaining coordinates. As a result, the ALeWM objective encourages early coordinates to retain information useful for prediction and recursive planning. Our analysis shows that the mixture distribution used by MixSIGReg assigns higher variance to earlier coordinate blocks and lower variance to later ones. In addition, we show that, under specified assumptions, prediction error is minimized by placing the information most useful for prediction in earlier blocks. Empirically, we study the behavior of ALeWM in a controlled dynamical system with known state variables and in goal-conditioned visual control. We show that ALeWM consistently achieves higher mean success rates than tuned fixed-width LeWM, with lower planning capacity on average.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2609.32921

Don't have the latest CLI?

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

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.32921 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.32921 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/2609.32921 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

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