---
title: "La-JEPA: Compact Robot Policies with Latent World Modeling"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.08156v1"
permalink: "https://feed.astralor.com/items/itm_87afb4041b66fa636d74cdbc"
published: "2026-11-05T15:16:38.000Z"
score: 62
channel: "tech"
tags: ["推理效率","RAG","多模态","La-JEPA","Compact Robot Policies","Latent World Modeling","World-action","Latent Action JEPA"]
---

# La-JEPA: Compact Robot Policies with Latent World Modeling

## 速览

World-action models adapt pretrained video generators, and vision-language-action models build on pretrained vision-language backbones; both tie policy architecture and inference cost to large transformers designed for …

## 关键点

- World-action models adapt pretrained video generators, and vision-language-action models build on pretrained vision-language backbones; both tie policy architecture and inference cost to large transformers designed for …
- It remains unclear how much these generation-oriented choices affect control.
- In this work, we introduce Latent Action JEPA (La-JEPA), a compact world-action model whose policy transformer is trained from scratch in the feature space of a pretrained V-JEPA 2.1 encoder.

## 全文

World-action models adapt pretrained video generators, and vision-language-action models build on pretrained vision-language backbones; both tie policy architecture and inference cost to large transformers designed for generation rather than control. It remains unclear how much these generation-oriented choices affect control. In this work, we introduce Latent Action JEPA (La-JEPA), a compact world-action model whose policy transformer is trained from scratch in the feature space of a pretrained V-JEPA 2.1 encoder. Following Fast-WAM, La-JEPA learns to predict future features jointly with actions during training and generates only actions at inference. Among policies without embodied pretraining, La-JEPA achieves state-of-the-art performance in clean and randomized RoboTwin 2.0 scenes and on LIBERO-Plus with correct instructions, while using far fewer parameters than the strongest competing policies. It runs substantially faster than Fast-WAM at comparable performance and outperforms the closest JEPA-based methods, LeapBot-WA and JEPA-WAM, on LIBERO-Plus and RoboTwin 2.0 without their pretrained policy backbones. On four real-robot tasks, its average success is comparable to pi0.5 and above non-embodied-pretrained baselines. Through a design study of the choices behind La-JEPA, we show that JEPA features outperform video VAE latents, most clearly out of distribution, and that training-time future prediction choices significantly impact the policy even when future prediction is skipped at inference. We correct the LIBERO-Plus instructions, as the officially released evaluator corrupts them for most variants, and re-evaluate several strong open baselines. Without a generative pretrained policy backbone, La-JEPA is better and faster than far larger policies, suggesting that robot foundation models may benefit from architectures designed for control rather than inherited from generation.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_87afb4041b66fa636d74cdbc