World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
Summary
This paper introduces World-Language-Action (WLA) models, embodied foundation models that jointly predict textual subtasks, subgoal images, and robot actions from text, images, and robot states, achieving state-of-the-art multi-task and long-horizon learning in simulated and real-world environments.
View Cached Full Text
Cached at: 06/05/26, 06:07 AM
Paper page - World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
Source: https://huggingface.co/papers/2606.05979 Authors:
,
,
,
,
,
,
,
,
,
,
Abstract
World-language-action models combine textual instruction processing with robot state prediction through an autoregressive transformer backbone, enabling efficient long-horizon task execution and cross-embodiment learning.
We propose world-language-action (WLA) models as a new class ofembodied foundation models. WLA takes textual instructions, images, and robot states as inputs to jointly predict textual subtasks, subgoal images, and robot actions, conjoining theworld modeling interfaceto learn from extensiveegocentric videosas in theworld-action model(WAM) and thelanguage reasoningcapacities to solve complex long-horizon tasks as in vision-language-action (VLA) models. At the core of WLA lies an autoregressive (AR) Transformer backbone, instead of a bidirectional diffusion Transformer as in WAMs, to predict the next state, comprising thesemantic-level textual intentionand complementaryfine-grained physical dynamics. The physical dynamics are supervised by theworld modeling objectivebased on a dedicated World Expert, and are leveraged to ease the characterization of the state-action correlation for theAction Expert. WLA leveragesmeta-queriesto make the world prediction implicitly impact the action generation so that the former can be disabled during inference. The world prediction can also be activated to enabletest-time scalingfor improved robot control. Our WLA-0 prototype, with 2B active parameters, achieves 40 ms per inference on an NVIDIA RTX 5090. Evaluations across simulated and real-world environments demonstrate that WLA-0 achieves state-of-the-art multi-task and long-horizon learning abilities, e.g., 92.94\% success rate on RoboTwin2.0 Clean and 56.5\% success rate on RMBench. WLA-0 also holds the promise to learn novel tasks directly fromcross-embodiment robot videoswithout action annotations.
View arXiv pageView PDFGitHub6Add to collection
Get this paper in your agent:
hf papers read 2606\.05979
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.05979 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.05979 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.05979 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
World Action Models: The Next Frontier in Embodied AI
This survey paper introduces World Action Models (WAMs), a unified framework for embodied AI that integrates predictive state modeling with action generation. It provides a taxonomy of existing methods, analyzes the data ecosystem, and outlines evaluation protocols for this emerging paradigm.
Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
Light-WAM is a lightweight world action model for efficient robot manipulation that uses a compact video backbone and downsampled latent space for future-video supervision, achieving high performance with low inference latency.
Learning Visual Feature-Based World Models via Residual Latent Action
This paper introduces RLA-WM, a visual feature-based world model that leverages residual latent actions and flow matching to efficiently predict future visual states. The method outperforms existing video-diffusion and feature-based approaches while enabling novel robot learning techniques from offline, actionless demonstration videos.
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
LaWAM enables efficient robot control by predicting compact latent visual subgoals instead of expensive video generation, achieving state-of-the-art success rates with up to 24x lower latency than pixel-space world action models.
The DAWN of World-Action Interactive Models
This paper introduces DAWN, a latent generative baseline for World-Action Interactive Models (WAIMs) that jointly models scene evolution and action generation through recursive refinement, achieving strong long-horizon planning in autonomous driving scenarios.