SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

[2608.07468] SimWAM: A Simple World Action Model for End-to-End Autonomous Driving Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2608.07468 (cs) [Submitted on 7 Aug 2026 ( v1 ), last revised 29 Sep 2026 (this version, v5)] Title: SimWAM: A Simple World Action Model for End-to-End Autonomous Driving Authors: Zongchuang Zhao , Xin Zhou , Tianyang Xu , Zhengyang Sun , Kaixuan Zhou , Yu Wu , Honglin Li , Dingkang Liang , Xiang Bai View PDF HTML (experimental) Abstract: In autonomous driving, World-Action Models (WAMs) have improved end-to-end planning by transferring video dynamics priors to action prediction, but many still couple planning with future-video generation at inference, incurring substantial computational overhead. We present SimWAM, a simple yet effective WAM that leverages future-video prediction solely as a training-time supervision signal. It co-trains a pretrained video expert and a lightweight action expert with joint flow matching. An isolated attention mask keeps action prediction independent of future frames, allowing trajectory prediction without future-frame generation at inference. This design supports multiple pretrained video backbones and independent action-expert scaling within a shared attention interface, while preserving the joint learning objective. Moreover, we apply reinforcement learning to optimize a compositional driving reward beyond trajectory imitation. Experiments show that SimWAM achieves $91.9$ PDMS on NAVSIM with a favorable trade-off between accuracy and latency among world-model-based planners, while transferring zero-shot to nuScenes. It also achieves competitive planning accuracy on WOD-E2E and PhysicalAI-Autonomous-Vehicles. These results position SimWAM as a plain yet solid baseline for efficient autonomous driving. The code and model weights are available at this https URL . Comments: The code and model weights are available at this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.07468 [cs.CV] (or arXiv:2608.07468v5 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.07468 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zongchuang Zhao [ view email ] [v1] Fri, 7 Aug 2026 17:59:09 UTC (424 KB) [v2] Tue, 11 Aug 2026 08:27:03 UTC (424 KB) [v3] Mon, 17 Aug 2026 16:14:55 UTC (428 KB) [v4] Thu, 27 Aug 2026 02:08:21 UTC (454 KB) [v5] Tue, 29 Sep 2026 13:51:23 UTC (1,024 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark 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? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving#677721
• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving#443289
• DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT#612753
• DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT#611276
• Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment#447925