RESEARCH PAPERYear 2025

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Zewei Zhou; Tianhui Cai; Seth Zhao; Yun Zhang; Zhiyu Huang; Bolei Zhou; Jiaqi Ma

Read paper PDF DOI Code

Classification

View four quadrants

Major category: VLA
Quadrant: Not applicable
Architecture: One Model
Prediction paradigm: Not applicable
Subcategories: Autoregressive VLA VLA post-training & data augmentation
Source review status: Verified from primary sources

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@article{autovla,
  title={Autovla: A vision-language-action model for end-to-end autonomous driving with adaptive reasoning and reinforcement fine-tuning},
  author={Zhou, Zewei and Cai, Tianhui and Zhao, Seth and Zhang, Yun and Huang, Zhiyu and Zhou, Bolei and Ma, Jiaqi},
  journal={NeurIPS},
  volume={38},
  pages={27920--27956},
  year={2026}
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

What Matters for Latent Actions in Robot Learning

SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation