The DAWN of World-Action Interactive Models
Summary
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.
View Cached Full Text
Cached at: 05/14/26, 04:17 AM
Paper page - The DAWN of World-Action Interactive Models
Source: https://huggingface.co/papers/2605.11550
Abstract
World-Action Interactive Models (WAIMs) jointly model scene evolution and actions through recursive refinement, enabling effective long-horizon planning in autonomous driving scenarios.
A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. ExistingWorld Action Models(WAMs) largely miss this reciprocity, treating world prediction and action generation as either isolated parallel branches or rigid predict-then-plan pipelines. We formalize this perspective asWorld-Action Interactive Models(WAIMs), and instantiate it in autonomous driving withDAWN(Denoising Actions and World iNteractive model), a simple yet stronglatent generative baseline.DAWNoperates in a compactsemantic latent spaceand couples aWorld Predictorwith aWorld-Conditioned Action Denoiser: the predicted world hypothesis conditions action denoising, while the denoised action hypothesis is fed back to update the world prediction, so that both are recursively refined during inference. Rather than eliminating test-time world evolution altogether or rolling out the full future in pixel space,DAWNperforms a short explicit latent rollout that is sufficient to supportlong-horizon trajectory generationin complex interactive scenes. Experiments show thatDAWNachieves strong planning performance and favorable safety-related results across multipleautonomous driving benchmarks. More broadly, our results suggest that interactive world-action generation is a principled path toward truly actionable world models.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.11550
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/2605.11550 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.11550 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.11550 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.
AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
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.
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
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.
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
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.
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.