Pith. sign in

REVIEW 16 cited by

A Survey on Vision-Language-Action Models for Autonomous Driving

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.24044 v1 pith:2ACEYQLK submitted 2025-06-30 cs.CV cs.AIcs.RO

Sicong Jiang , Zilin Huang , Kangan Qian , Ziang Luo , Tianze Zhu , Yang Zhong , Yihong Tang , Menglin Kong
show 12 more authors
Yunlong Wang Siwen Jiao Hao Ye Zihao Sheng Xin Zhao Tuopu Wen Zheng Fu Sikai Chen Kun Jiang Diange Yang Seongjin Choi Lijun Sun
This is my paper
classification cs.CVcs.AIcs.RO
keywords autonomousdrivingmodelssurveyawesome-vla4addomaingithublanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA for Autonomous Driving (VLA4AD). We (i) formalize the architectural building blocks shared across recent work, (ii) trace the evolution from early explainer to reasoning-centric VLA models, and (iii) compare over 20 representative models according to VLA's progress in the autonomous driving domain. We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, accuracy, and explanation quality. Finally, we detail open challenges - robustness, real-time efficiency, and formal verification - and outline future directions of VLA4AD. This survey provides a concise yet complete reference for advancing interpretable socially aligned autonomous vehicles. Github repo is available at \href{https://github.com/JohnsonJiang1996/Awesome-VLA4AD}{SicongJiang/Awesome-VLA4AD}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Steadily moving semi-infinite fracture in plane poroelasticity

    physics.geo-ph 2026-04 unverdicted novelty 7.0 of 10

    A new coupled boundary integral method models steadily moving semi-infinite fractures in plane poroelasticity, solving for mechanical deformation and fluid exchange with verification on analytical test cases.

  2. MoRAL: Sensor-Grounded BEV Reasoning for Compact VLMs toward Edge-Oriented Autonomous Driving

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A 2B VLM fine-tuned in two stages on a physics-encoded bird's-eye view image outperforms a zero-shot 8B VLM on eight driving-reasoning question types and raises emergency-braking recall from 10.8% to 47.8%.

  3. MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    MVPruner is a two-stage dynamic token pruning technique that uses view diversity for initial budget allocation and instruction text for task-aligned selection, delivering 87.3% FLOPs reduction and 4.97x prefilling spe...

  4. EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    EgoDyn-Bench finds a Perception Bottleneck: foundation models hold ego-motion logic in language but misalign it with vision, underperforming geometric baselines until given explicit trajectories.

  5. EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency.

  6. From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving

    cs.RO 2026-02 conditional novelty 6.0 of 10

    A VLM-based and a vision-only end-to-end planner are behaviorally complementary in a long tail of driving scenarios; selecting the better trajectory lifts NAVSIM PDMS from 90.80 to 92.10 at modest compute.

  7. LinMU: Multimodal Understanding Made Linear

    cs.CV 2026-01 conditional novelty 6.0 of 10

    LinMU achieves linear-complexity multimodal understanding by swapping self-attention for an M-MATE dual-branch block and distilling from a frozen teacher VLM, matching accuracy with up to 2.7x faster TTFT and 9x highe...

  8. VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer

    cs.RO 2025-12 conditional novelty 6.0 of 10

    AEGIS wraps VLA robot policies in a CBF-based safety layer that uses VLM obstacle identification, raising collision avoidance from 18.69% to 77.85% and task success by 17.25 points on the new SafeLIBERO benchmark.

  9. E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving

    cs.CV 2025-12 conditional novelty 6.0 of 10

    An emotion-aware vision-language-action driving model estimates VAD emotion from commands and uses it to improve grounding and waypoint planning.

  10. PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    PriorEye augments end-to-end driving models with a dual-memory architecture that stores and gates geospatial visual priors to improve performance and robustness to sensor corruption on NAVSIM-v2.

  11. MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    MVPruner is a two-stage adaptive token pruning technique for multi-view VLMs that achieves 87.3% FLOPs reduction and 4.97x prefilling speedup while retaining 98.5% accuracy on DriveLM.

  12. Steadily moving semi-infinite fracture in plane poroelasticity

    physics.geo-ph 2026-04 conditional novelty 5.0 of 10

    XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.

  13. XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments

    cs.CV 2026-04 unverdicted novelty 4.0 of 10

    XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial...

  14. Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey

    cs.RO 2025-10 conditional novelty 4.0 of 10

    A survey that groups VLA efficiency techniques into four categories: model architecture, perception features, action generation, and training/inference strategies.

  15. A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach

    cs.RO 2025-12 conditional novelty 3.0 of 10

    A position/review paper argues data-driven model predictive control is the best route to safe, adaptive, human-like autonomous-driving motion planning, but provides no new derivation or experiment.

  16. Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition

    cs.RO 2025-07 conditional novelty 3.0 of 10

    This paper summarizes the CVPR 2025 V2X cooperative driving challenge, its winning solutions, and the open research problems it reveals.

Pith tools