RESEARCH PAPERSubmitted 5 Apr 2026

DriveVA: Video Action Models are Zero-Shot Drivers

Mengmeng Liu; Diankun Zhang; Jiuming Liu; Jianfeng Cui; Hongwei Xie; Guang Chen; Hangjun Ye; Michael Ying Yang; Francesco Nex; Hao Cheng

Read on arXiv PDF

Classification

View four quadrants

Major category: WAMs
Quadrant: Q1 · One Model × Joint prediction
Architecture: One Model
Prediction paradigm: Joint prediction
Subcategories: Autonomous driving Joint video-action modeling Generalization & action alignment
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{driveva,
      title={DriveVA: Video Action Models are Zero-Shot Drivers}, 
      author={Mengmeng Liu and Diankun Zhang and Jiuming Liu and Jianfeng Cui and Hongwei Xie and Guang Chen and Hangjun Ye and Michael Ying Yang and Francesco Nex and Hao Cheng},
      year={2026},
      journal={arXiv:2604.04198},
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation

Grounding Generated Video Plans in Simulation Towards Versatile Dexterous Controllers

HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy