AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

VLR-Driver: Large Vision-Language-Reasoning Models for Embodied Autonomous Driving

Fanjie Kong, Yitong Li, Weihuang Chen, Chen Min, Yizhe Li, Zhiqiang Gao, Haoyang Li, Zhongyu Guo, Hongbin Sun

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatiotemporal CoT reasoning guidance (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Driving Score: 57.17 -> 75.01Improved
add spatiotemporal CoT reasoning guidance (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Success Rate: 34.09 -> 50.00Improved
use the VLR model instead of a standard LLM module (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Driving Score: 46.39 -> 75.01Improved
use the VLR model instead of a standard LLM module (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Success Rate: 20.45 -> 50.00Improved
add VLR-Driver dataset reasoning data (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Driving Score: 52.85 -> 75.01Improved
add VLR-Driver dataset reasoning data (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Success Rate: 27.27 -> 50.00Improved
add Step-GRPO reinforcement learning after LoRA SFT (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Driving Score: 65.57 -> 75.01Improved
add Step-GRPO reinforcement learning after LoRA SFT (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Success Rate: 45.45 -> 50.00Improved
add Step-GRPO reinforcement learning after LoRA SFT (ablation)VLR-Driver · Bench2Drive (CARLA, 44 routes)Emergency Brake ability: 63.63 -> 72.72Improved
VLR-Driver versus best prior baselineVLR-Driver · Bench2Drive (CARLA, 44 routes)Driving Score / Success Rate: 63.81 -> 75.01 DS; 40.90 -> 50.00 SRImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy