DriveMA-2B is the official 2B checkpoint accompanying DriveMA: Driving Vision-Language-Action Models with Verifiable Meta-Actions. It is fine-tuned from Qwen3.5-2B using the DriveMA three-stage pipeline: action-centric pretraining, action-conditioned trajectory supervised fine-tuning, and turn-level reinforcement learning.

DriveMA formulates driving planning as a two-turn generation process. The first turn predicts a compact, interpretable meta-action from multi-view observations and vehicle state. The second turn generates future waypoints conditioned on that meta-action.

DriveMA-2B uses the same model architecture, processor, and standard loading interface as Qwen3.5-2B:

For general multimodal inference, follow the Qwen3.5-2B usage instructions. To reproduce the model's driving-planning behavior, start from the official DriveMA repository and use its inference scripts and prompt templates, which implement the expected multi-view inputs, vehicle-state fields, two-turn interaction, and output format.

On the Waymo Open Dataset vision-based end-to-end planning benchmark, the paper reports the following results for DriveMA-2B:

See the paper and code repository for the full evaluation protocol, comparisons, and ablations.

DriveMA-2B is intended for research on vision-language-action modeling and end-to-end autonomous-driving planning. The released dataset repository contains annotations; users must obtain the corresponding source image/video assets under their original licenses and update local paths as described in the code repository.

This model is not validated for deployment in safety-critical systems and should not be used to control a real vehicle without independent safety validation, system-level safeguards, and compliance with applicable laws and regulations.