Abstract:Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene understanding and reasoning capabilities. Recent attempts to incorporate dense visual supervision via world modeling often overemphasize pixel-level image reconstruction, neglecting semantically meaningful scene representation learning. In this work, we propose LVDrive, a Latent Visual representation enhanced VLA framework for autonomous driving. LVDrive introduces a future scene prediction task into the VLA paradigm, where future representations are learned entirely in a high-level latent space under auxiliary supervision from a pretrained vision backbone. Departing from inefficient autoregressive generation, we jointly model future scene and motion prediction within a unified embedding space, processed in a single forward pass to conduct the future-aware reasoning. We further design a two-stage trajectory decoding strategy that explicitly leverages the learned latent future representations to refine trajectory generation. Extensive experiments on the challenging Bench2Drive benchmark demonstrate that LVDrive achieves significant improvements in closed-loop driving performance, outperforming both action supervised methods and image-reconstruction-based world model approaches.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.22089 [cs.CV] |
| (or arXiv:2605.22089v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22089 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaodong Mei [view email]
[v1]
Thu, 21 May 2026 07:31:49 UTC (2,215 KB)