StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Driving

• URL: http://arxiv.org/abs/2603.09482v1
• Date: Tue, 10 Mar 2026 10:33:58 GMT
• Title: StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Driving
• Abstract summary: StyleVLA is a physics-informed VLA framework for generating diverse and physically plausible driving behaviors.<n>We construct a large-scale instruction dataset with over 1.2k scenarios, 76k Bird's Eye View (BEV) samples, and 42k First Person View (FPV) samples.<n>Experiments show that StyleVLA significantly outperforms proprietary models and state-of-the-art VLA models.
• Score: 8.903468887918754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Language Models (VLMs) bridge visual perception and linguistic reasoning. In Autonomous Driving (AD), this synergy has enabled Vision Language Action (VLA) models, which translate high-level multimodal understanding into driving behaviors, typically represented as future trajectories. However, existing VLA models mainly generate generic collision-free trajectories. Beyond collision avoidance, adapting to diverse driving styles (e.g., sporty, comfortable) is essential for personalized driving. Moreover, many methods treat trajectory generation as naive token prediction, which can produce kinematically infeasible actions. To address these limitations, we present StyleVLA, a physics-informed VLA framework for generating diverse and physically plausible driving behaviors. We introduce a hybrid loss that combines a kinematic consistency constraint with a continuous regression head to improve trajectory feasibility. To train StyleVLA, built on Qwen3-VL-4B, we construct a large-scale instruction dataset with over 1.2k scenarios, 76k Bird's Eye View (BEV) samples, and 42k First Person View (FPV) samples, with ground-truth trajectories for five driving styles and natural-language instructions. Experiments show that our 4B-parameter StyleVLA significantly outperforms proprietary models (e.g., Gemini-3-Pro) and state-of-the-art VLA models. Using a composite driving score measuring success rate, physical feasibility, and style adherence, StyleVLA achieves 0.55 on BEV and 0.51 on FPV, versus 0.32 and 0.35 for Gemini-3-Pro. These results show that a specialized, physics-informed, lightweight model can surpass closed-source models on domain-specific tasks.

Related papers

• WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning [4.427336047705734]
  Vision-Language-Action (VLA) models have recently demonstrated strong generalization in robotic manipulation.<n>This work introduces a unified framework WOLF-VLA that integrates whole-body optimal-control (OC) motion synthesis with large-scale multi-modal dataset.<n>We construct a comprehensive dataset of dynamically feasible humanoid trajectories across six locomotion-related task families.<n>We train a VLA model using the collected joint trajectories, ego-centric visual observations and natural language instruction, yielding a policy that exhibits strong reasoning and robustness to initial-condition variability.
  arXiv  Detail & Related papers  (2026-06-24T08:59:59Z)
• DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model [22.06522773748522]
  We present DriveStack-VLA, a framework built upon a large VLM backbone.<n>We develop dual visual modeling components to strengthen the spatial grounding of VLA driving.<n>DriveStack-VLA achieves 91.6 PDMS on NAVSIMv1, 91.0S on NAVSIMv2, and a driving score of 79.49 with a success rate of 56.36% on the closed-loop Bench2Drive.
  arXiv  Detail & Related papers  (2026-06-23T01:40:54Z)
• VLGA: Vision-Language-Geometry-Action Models for Autonomous Driving [6.130994037021129]
  Vision-language-action models can describe scenes and reason about them in language, but struggle to ground their actions in the dense 3D world around them.<n>We introduce VLGA, the first vision-language-action model supervised to reconstruct the dense 3D world it drives through.
  arXiv  Detail & Related papers  (2026-06-10T17:57:06Z)
• UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving [48.461267171124945]
  We propose UniDriveVLA, a Unified Driving Vision-Language-Action model for autonomous driving.<n>It comprises three experts for driving understanding, scene perception, and action planning, which are coordinated through masked joint attention.<n>It achieves state-of-the-art performance in open-loop evaluation on nuScenes and closed-loop evaluation on Bench2Drive.
  arXiv  Detail & Related papers  (2026-04-02T15:48:45Z)
• Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation [58.21084913574353]
  We introduce Pri4R, a simple approach that endows VLA models with an implicit understanding of world dynamics.<n>Pri4R augments VLA with a lightweight point track head that predicts 3D point tracks.<n>We show that 3D point track prediction is an effective supervision target for learning action-world dynamics.
  arXiv  Detail & Related papers  (2026-03-02T07:23:53Z)
• VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving [26.557803260279258]
  Cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models inherently lack this capability.<n>We propose a novel architecture, VGGDrive, which empowers Vision-language models with cross-view Geometric Grounding for autonomous driving.
  arXiv  Detail & Related papers  (2026-02-24T11:33:44Z)
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving [52.63591791507895]
  We propose textbfDriveVLA-W0, a training paradigm that employs world modeling to predict future images.<n>This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment.<n>Experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines.
  arXiv  Detail & Related papers  (2025-10-14T17:59:47Z)
• Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends [11.678954304546988]
  Vision-language-action (VLA) models extend vision-language models (VLM)<n>This paper reviews post-training strategies for VLA models through the lens of human motor learning.
  arXiv  Detail & Related papers  (2025-06-26T03:06:57Z)
• Unified Vision-Language-Action Model [86.68814779303429]
  We present UniVLA, a unified and native multimodal VLA model that autoregressively models vision, language, and action signals as discrete token sequences.<n>Our approach sets new state-of-the-art results across several widely used simulation benchmarks, including CALVIN, LIBERO, and Simplenv-Bridge.<n>We further demonstrate its broad applicability on real-world ALOHA manipulation and autonomous driving.
  arXiv  Detail & Related papers  (2025-06-24T17:59:57Z)
• AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning [37.176428069948535]
  Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving.<n>Current VLA models struggle with physically infeasible action outputs, complex model structures, or unnecessarily long reasoning.<n>We propose AutoVLA, a novel VLA model that unifies reasoning and action generation within a single autoregressive generation model.
  arXiv  Detail & Related papers  (2025-06-16T17:58:50Z)
• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models [89.44024245194315]
  We introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs)<n>We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens.<n>Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T22:23:04Z)
• TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies [95.30717188630432]
  We introduce visual trace prompting to facilitate VLA models' spatial-temporal awareness for action prediction.<n>We develop a new TraceVLA model by finetuning OpenVLA on our own collected dataset of 150K robot manipulation trajectories.<n>We present a compact VLA model based on 4B Phi-3-Vision, pretrained on the Open-X-Embodiment and finetuned on our dataset.
  arXiv  Detail & Related papers  (2024-12-13T18:40:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.