Teaching Vision-Language-Action Models What to See and Where to Look
Yuguang Yang, Canyu Chen, Zhewen Tan, Yizhi Wang, Zichao Feng, Chunyang Liu, Kehua Sheng, Juan Zhang, Linlin Yang, Baochang Zhang, Yan Wang, Bo Zhang, Xianbin Cao
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/shivateam/driveteach-vlaOfficialIn paper★ 0
Abstract
Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing VLAs' training relies heavily on text-centric visual question answering and chain-of-thought reasoning data, which emphasizes linguistic reasoning rather than action-grounded planning. As a result, the learned representations capture semantic knowledge but lack spatial dependencies crucial for reliable trajectory prediction. We propose DriveTeach-VLA, a framework that explicitly teaches VLAs what to see and where to look. Driving-aware Vision Distillation (DVD) injects driving-specific perceptual priors into the vision encoder, while 2D Trajectory-Guided Prompts (2D-TGP) provide spatial conditioning aligned with feasible driving trajectories. Together, they form a vision-guided learning pipeline: what to see (DVD pretraining) - where to look (TGP-guided SFT) - how to act (TGP-guided GRPO). DriveTeach-VLA achieves the state-of-the-art performance on NAVSIM and nuScenes. Our code is available at: https://github.com/ShivaTeam/DriveTeach-VLA.