AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Passing the Driving Knowledge Test

Maolin Wei, Wanzhou Liu, Eshed Ohn-Bar

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 2 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 DriveQA finetuning (ablation)Gemma-2 9B · DriveQA-T averageaccuracy: 76.91 -> 87.28Improved
add DriveQA finetuning (ablation)Llama-3.1 8B · DriveQA-T averageaccuracy: 60.79 -> 87.62Improved
add CoT and RAG context (ablation)Gemma-2 2B · DriveQA-T averageaccuracy: 44.15 -> 56.62Improved
add RAG context to CoT (ablation)Gemma-2 2B · DriveQA-T explanationsBLEU-4: 0.1098 -> 0.1704Improved
add RAG context to CoT after finetuning (ablation)Gemma-2 2B · DriveQA-T explanationsBLEU-4: 0.3623 -> 0.2934Hurt
finetune on DriveQA vs GPT-4o for explanationsGemma-2 9B · DriveQA-T explanationsROUGE-L: 0.5393 -> 0.5528Improved
add DriveQA finetuning (ablation)Mini-InternVL 2B · DriveQA-V averageaccuracy: 41.82 -> 86.59Improved
add DriveQA finetuning (ablation)LLaVA-1.5 7B · DriveQA-V averageaccuracy: 23.52 -> 69.67Improved
add negative-sampling hard distractors (ablation)GPT-4o · DriveQA-V (Signs)accuracy: 94.10 -> 79.40Hurt
add negative-sampling hard question set (ablation)Llama-3.1 8B · DriveQA-T hard subsetaccuracy: 55.89 -> 39.87Hurt
finetune on DriveQA, test on real Mapillary signsVILA-1.5 8B · Real-world Mapillary signsaccuracy: 34.38 -> 60.86Improved
pretrain on DriveQA for trajectory planning (ablation)InternVL-2.5-8B · nuScenesavg L2 (m): 3.06 -> 2.71Improved

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