MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
MindVLA-U1 is the first unified streaming VLA architecture for autonomous driving. It produces both language tokens and continuous action trajectories in a single forward pass using a unified VLM backbone, processes video framewise, and uses a learned memory channel for temporal context. On the WOD-E2E benchmark, it surpasses experienced human drivers for the first time (RFS 8.20 vs 8.13) with 2 diffusion steps, achieves state-of-the-art planning ADEs, and matches VA-class throughput (16 FPS) while preserving natural-language interfaces.
[2605.12624] MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
[Submitted on 12 May 2026]
Title:MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
View a PDF of the paper titled MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving, by Yuzhou Huang and 8 other authors
View PDF HTML (experimental)
Abstract:Autonomous driving has progressed from modular pipelines toward end-to-end unification, and Vision-Language-Action (VLA) models are a natural extension of this journey beyond Vision-to-Action (VA). In practice, driving VLAs have often trailed VA on planning quality, suggesting that the difficulty is not simply model scale but the interface through which semantic reasoning, temporal context, and continuous control are combined. We argue that this gap reflects how VLA has been built -- as isolated subtask improvements that fail to compose into coherent driving capabilities -- rather than what VLA is. We present MindVLA-U1, the first unified streaming VLA architecture for autonomous driving. A unified VLM backbone produces autoregressive language tokens and flow-matching continuous action trajectories in a single forward pass over one shared representation, preserving the natural output form of each modality. A streaming design processes the driving video framewise rather than as fixed video-action chunks, while a learned memory channel carries temporal context across frames so planned trajectories evolve smoothly without redundant multi-frame VLM modeling. The unified architecture admits fast/slow execution on dense/sparse Mixture-of-Transformers (MoT) backbones via flexible self-attention context management, and exposes a measurable language-to-action route: a language-predicted driving intent steers action diffusion through classifier-free guidance (CFG), turning language-side intent into a control signal for continuous trajectory generation. On the long-tail WOD-E2E benchmark, MindVLA-U1 surpasses experienced human drivers for the first time (8.20 RFS vs. 8.13 GT RFS) with 2 diffusion steps, achieves state-of-the-art planning ADEs over prior VA/VLA methods by large margins, and matches VA-class throughput (16 FPS vs. RAP-DINO's 18 FPS) while preserving natural-language interfaces.
Comments: Work in progress. Project page: this https URL
Subjects:
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2605.12624 [cs.RO]
(or arXiv:2605.12624v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.12624
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Benjin Zhu [view email] [v1] Tue, 12 May 2026 18:09:42 UTC (11,151 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving, by Yuzhou Huang and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-05
Change to browse by:
cs 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?)