Pith.

Robotics · arXiv:2606.15768 v2 · submitted 14 Jun 2026

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

Jialei Chen, Kai Wang, Kang Chen, Shuaihang Chen, Feng Gao, Wenhao Tang, Zhiyuan Li, Weilin Liu

show 4 more authors

Zhuyu Yao, Boxun Li, Yuanbo Xu, Chao Yu

The paper says

“LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference.”

from the abstract · picked out as the main claim by a classifier

Pith says

Pith has not reviewed this paper.

Get a Pith Review, $5

Reviews

Reviews by people

No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene. World-Action Models (WAMs) address this limitation by conditioning policies on predicted futures, yet existing approaches typically rely on computationally expensive video generation with substantial pixel-level redundancy. We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video. At the core of LaWAM is a latent-action-conditioned Latent World Model (LaWM). We obtain LaWM by training a latent action model in the latent space of a pretrained vision foundation model and repurposing its forward decoder to predict future observation features for scene evolution. LaWAM then conditions action generation on these predicted latent visual subgoals to enable dynamics-aware robot control. LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference. LaWAM runs in 187 ms per action-chunk prediction and achieves up to 24x lower wall-clock latency than pixel-space WAMs.

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-10-27 · no language-model review

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.07 · states limitation 0.08 · human participants 0.06 · controlled comparison 0.57 · randomized assignment 0.01 · states quantitative result 0.99 · compares with prior results 0.94 · mentions code or data availability 0.03

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v2). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene. background 0.82 0.05 0.03 asserted 0.98
World-Action Models (WAMs) address this limitation by conditioning policies on predicted futures, yet existing approaches typically rely on computationally expensive video generation with substantial pixel-level redundancy. background 0.67 0.05 0.03 asserted 0.98
We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video. contribution 1.00 0.89 0.39 asserted 1.00
At the core of LaWAM is a latent-action-conditioned Latent World Model (LaWM). method 0.74 0.60 0.06 asserted 1.00
We obtain LaWM by training a latent action model in the latent space of a pretrained vision foundation model and repurposing its forward decoder to predict future observation features for scene evolution. method 0.99 0.93 0.06 asserted 1.00
LaWAM then conditions action generation on these predicted latent visual subgoals to enable dynamics-aware robot control. method 0.96 0.79 0.15 asserted 0.99
LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference. result 1.00 0.95 0.45 asserted 1.00
LaWAM runs in 187 ms per action-chunk prediction and achieves up to 24x lower wall-clock latency than pixel-space WAMs. result 1.00 0.95 0.16 asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.96

What was examined, and what was not

Sources read

  • arXiv listing abstract v2

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-10-27: 1 request, 6,358 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Cited by 13 Pith papers
How the literature uses it

20 arXiv papers cite this in 50 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it · 30 sentences without a confident label

Builds on it 1 paper
Uses its method or tool 1 paper
Compares with it 3 papers
Cites it as background 10 papers

Challenges and discussion

Know something about this paper? Leave a comment.

No comments yet.

Sign in to comment