# Data-Efficient Adaptation of a Driving VLA to Class 8 Trucks

arXiv: https://arxiv.org/abs/2609.38570 · HTML: https://mlsanity.com/paper/2609.38570/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning VLA and VLM driving policies, one of 9 directions in End-to-end autonomous driving.
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- End-to-end autonomous driving / [Reasoning VLA and VLM driving policies](https://mlsanity.com/driving/reasoning-vla-and-vlm-driving-policies/)

## Builds on (most cited first, 17 of 17)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [Residual Policy Learning](https://mlsanity.com/paper/1812.06298/) (2018)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditions](https://mlsanity.com/paper/2407.07462/) (2024)
- [SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios](https://mlsanity.com/paper/2602.08440/) (2026)
- [RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulation](https://mlsanity.com/paper/2602.01789/) (2026)
- [Learning from Mistakes: Post-Training for Driving VLA with Takeover Data](https://mlsanity.com/paper/2603.14972/) (2026)
- [FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation](https://mlsanity.com/paper/2602.22056/) (2026)
- [TruckDrive: Long-Range Autonomous Highway Driving Dataset](https://mlsanity.com/paper/2603.02413/) (2026)
- [MVAdapt: Zero-Shot Multi-Vehicle Adaptation for End-to-End Autonomous Driving](https://mlsanity.com/paper/2604.11854/) (2026)
- [CLAP: Contrastive Latent-space Prompt Optimization for End-to-end Autonomous Driving](https://mlsanity.com/paper/2605.17284/) (2026)
- [Flow-based Policy Adaptation without Policy Updates](https://mlsanity.com/paper/2606.06461/) (2026)

## Abstract (arXiv)

Class 8 trucks differ from passenger cars in geometry, dynamics, and maneuvering requirements. As a result, vision-language-action (VLA) models trained for passenger vehicles do not readily transfer to Class 8 trucks, particularly in unstructured scenarios such as accident scenes and construction zones. Rather than training a truck-driving VLA from scratch, we propose an adapt-then-steer strategy that adapts an off-the-shelf VLA to generate trajectories for Class-8 trucks in these challenging scenarios. In the adapt stage, we use NVIDIA's Alpamayo 1.5 as the base model, fine-tuning only its action-generation stack on a few hundred real-world construction and accident-related highway scenarios. In the steer stage, we introduce Flow Velocity Steering (FVS) to further refine the model's predictions while holding the adapted VLA fixed. FVS is a compact, flow-time-conditioned residual module that adds learned corrections to the action-space flow velocity used to update the action sequence at each generation step. In open-loop evaluation on a scenario-disjoint held-out set, targeted fine-tuning more than halves single-candidate average displacement error (ADE) and final displacement error (FDE) over the entire 6.4 s horizon compared to the base model. Using the same targeted demonstrations, FVS further reduces the fine-tuned model's full-horizon ADE and FDE by 13.9% and 16.5%, respectively. At matched data budgets, targeted supervision yields 19-26% lower full-horizon ADE than general truck-driving supervision, while the targeted model remains competitive with a model fine-tuned on approximately 65 times as many general truck-driving scenarios. These results support adapt-then-steer for data-efficient vehicle-domain transfer to Class 8 trucks. Our project website is available at https://truckvla.github.io.