Skip to content
AI News HubLIVE
Original source2 min read

BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving

Summary

BrainWAM coordinates semantic priors from vision-language models with predictive dynamics from world models at the action-representation level, avoiding attention-allocation mismatch and achieving state-of-the-art results on NAVSIM v1 and v2.

SourcearXiv RoboticsAuthor: Bing Zhan, Shuyao Shang, Jiahao Gu, Shuo Lu, Yuan Xu, Zhao Wang, Yida Wang, Xueyang Zhang, Kun Zhan, Lue Fan, Zhaoxiang Zhang
BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 13 Aug 2026]

Title:BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving

View a PDF of the paper titled BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving, by Bing Zhan and 10 other authors

View PDF HTML (experimental)

Abstract:Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) models exploit VLM priors for semantic reasoning, while World Action Models (WAMs) provide future-aware prediction through generative world modeling. This naturally motivates a unified planner that can leverage both semantic priors and predictive dynamics. However, we find that a naive combination through joint token-level attention suffers from an attention-allocation mismatch, where semantic shortcuts dominate the shared attention space and suppress predictive dynamics. Inspired by neuroscience evidence that complex behavior arises from coordination among functionally specialized systems, we propose BrainWAM, a structured action-space coordination framework that converts semantic reasoning and predictive world modeling into two specialized action-oriented pathways, and aligns them at the level of compact action representations. We further introduce an asynchronous rectified-flow inference strategy with decoupled video and action denoising, which shortens inference latency while preserving planning-relevant predictive context. BrainWAM reaches state-of-the-art performance on both NAVSIM v1 (89.5 PDMS) and NAVSIM v2 (89.6 EPDMS), consistently outperforming VLA-only or WAM-only methods, highlighting BrainWAM as a practical and promising direction for autonomous driving systems.

Subjects:

Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2608.12854 [cs.RO]

(or arXiv:2608.12854v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2608.12854

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Bing Zhan [view email] [v1] Thu, 13 Aug 2026 05:56:17 UTC (2,377 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving, by Bing Zhan and 10 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-08

Change to browse by:

cs cs.AI cs.CV

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • VLA-only and WAM-only methods each cover only one side of planning: semantic reasoning or future prediction.
  • Naive token-level fusion lets semantic shortcuts dominate shared attention and suppress predictive dynamics.
  • BrainWAM uses two specialized action-oriented pathways aligned on compact action representations.
  • Asynchronous rectified-flow inference decouples video and action denoising to reduce latency, reaching 89.5 PDMS and 89.6 EPDMS.

Highlights and analysis are generated automatically and may contain errors. Check the original source.