Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning

Hugging Face Daily Papers Papers
autonomous-driving world-models discrete-tokens diffusion causal-reasoning counterfactual-reasoning vision-action

Summary

Introduces Discrete-WAM, a unified discrete latent vision-action world policy that enables compositional causal reasoning and counterfactual reasoning in autonomous driving through aligned discrete tokens and a shared discrete diffusion framework.

Autonomous driving requires reasoning about how ego actions shape the evolution of the surrounding world. However, most end-to-end methods rely on direct state-to-action mappings, capturing correlations without explicitly modeling action-conditioned dynamics. Conversely, continuous-latent world models often lack compositional structure for causal reasoning across counterfactual futures. We introduce Discrete-WAM, a unified latent vision-action world policy that represents future visual states and ego actions as aligned discrete tokens, enabling compositional causal reasoning across alternative futures. Built upon this unified discrete alignment, Discrete-WAM establishes a shared discrete diffusion framework with unified generative tasks, jointly formulating world modeling, world-action policy, and hierarchical decision-enabled policy, supporting compositional generalization across diverse driving scenarios. Experiments on large-scale autonomous-driving benchmarks show that Discrete-WAM achieves competitive performance while supporting controllable generation and counterfactual reasoning, offering a principled path toward more reliable decision-making.
Original Article
View Cached Full Text

Cached at: 06/05/26, 06:07 AM

Paper page - Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning

Source: https://huggingface.co/papers/2606.05645 Authors:

,

,

,

,

,

,

,

,

,

,

,

Abstract

Discrete-WAM introduces a unified discrete latent vision-action world policy that enables compositional causal reasoning and counterfactual reasoning in autonomous driving through aligned discrete tokens and a shared discrete diffusion framework.

Autonomous drivingrequires reasoning about how ego actions shape the evolution of the surrounding world. However, most end-to-end methods rely on direct state-to-action mappings, capturing correlations without explicitly modeling action-conditioned dynamics. Conversely, continuous-latentworld modelsoften lack compositional structure forcausal reasoningacross counterfactual futures. We introduce Discrete-WAM, a unified latent vision-action world policy that represents future visual states and ego actions as aligneddiscrete tokens, enabling compositionalcausal reasoningacross alternative futures. Built upon this unified discrete alignment, Discrete-WAM establishes a shareddiscrete diffusion frameworkwith unified generative tasks, jointly formulating world modeling, world-action policy, and hierarchical decision-enabled policy, supportingcompositional generalizationacross diverse driving scenarios. Experiments on large-scale autonomous-driving benchmarks show that Discrete-WAM achieves competitive performance while supporting controllable generation andcounterfactual reasoning, offering a principled path toward more reliable decision-making.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.05645

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/2606.05645 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.05645 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.05645 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

The DAWN of World-Action Interactive Models

Hugging Face Daily Papers

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.

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

Hugging Face Daily Papers

AHA-WAM is an asynchronous world-action model that uses dual Diffusion Transformers to decouple world prediction from action execution, achieving efficient long-horizon planning and real-time control. It achieves state-of-the-art performance on robotic manipulation tasks with up to 92.8% success on RoboTwin and 78.3% on real-world tasks, while reaching 24.17 Hz closed-loop control.

World Action Models: The Next Frontier in Embodied AI

Hugging Face Daily Papers

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.