cs.CVNov 18, 2026

DRIFT: Detachable Reasoning for Runtime-Flexible and Efficient End-to-End Driving

Authors: Emad Aghajanzadeh, Bethany Anne Wong, Leonhard Kunze, Moritz Thoma, Maximilian Forstenhäusler, Nael Fasfous, Manoj Rohit Vemparala, Pierpaolo Mori, 

Organizations: Technical University of Munich, Germany · BMW Group, Germany · University of Glasgow, UK · TU Wien, Austria

Abstract

The integration of vision-language models (VLMs) into end-to-end (E2E) autonomous driving has demonstrated strong potential by providing scene description and reasoning capabilities. However, VLMs are computationally expensive, and switching language reasoning on and off at runtime without hurting closed-loop performance has not been demonstrated, which hinders practical adoption. To address these issues, we propose DRIFT, an E2E autonomous driving framework that integrates a lightweight language model (LM) for visual question answering and action commentary. By efficiently projecting intermediate driving representations into the language embedding space, we demonstrate that a compact LM (<150M parameters) can achieve strong scene description and action commentary. Furthermore, we introduce a runtime-flexible planning module that is trained on surrogate reasoning features distilled from the LM and can be conditioned on either the LM or the surrogate reasoning features at inference. This design enables bypassing the LM entirely when required by deployment constraints, without sacrificing driving performance. With only 255M parameters, DRIFT reaches up to a Driving Score (DS) of 97.03 and a Success Rate of 89.39% (mean over three runs) on Bench2Drive by interleaving its LM and surrogate reasoning at a chosen reasoning rate. This is on par with the strongest non-language models while being far more compact than existing VLM-based models. DRIFT further achieves competitive results on the real-world NAVSIM and AlpaSim benchmarks at significantly lower computational cost than existing VLM-based approaches. Project page: https://drift-e2e.github.io/

Figures & tables

Explore similar work

CardsList
  1. AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving

    Mar 16, 2026Wenhui Huang, Songyan Zhang, Qihang Huang +6Mixture-of-TransformersEnd-to-End Autonomous Driving

  2. NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving

    Mar 9, 2026Ximeng Tao, Pardis Taghavi, Dimitar Filev +2VLMs for Autonomous DrivingAutonomous Driving Planning

  3. VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving

    May 9, 2026Rui Zhao, Jianlin Yu, Zhenhai Gao +2VLMs for Autonomous DrivingEnd-to-End Autonomous Driving