AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving

Zhijian Huang, Chengjian Feng, Feng Yan, Baihui Xiao, Zequn Jie, Yujie Zhong, Xiaodan Liang, Lin Ma

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 54 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 QA augmentation (GPT-4o-mini paraphrasing and multiple-choice conversion) (ablation)RoboTron-Drive · Six AD datasets (average)Average: 55.54 -> 58.60Improved
Add QA augmentation on DriveLM (ablation)RoboTron-Drive · DriveLMAverage: 47.41 -> 59.67Improved
Add QA standardization on top of augmentation (ablation)RoboTron-Drive · NuInstructAverage: 34.77 -> 42.44Improved
Add QA standardization on CODA-LM (ablation)RoboTron-Drive · CODA-LMAverage: 63.93 -> 63.90No clear effect
Use curriculum learning versus mixed-complexity data from the start (ablation)RoboTron-Drive · Six AD datasets (average)Average: 55.71 -> 61.32Improved
Add more curriculum pre-training stages (S0 to S3) (ablation)RoboTron-Drive · Six AD datasets (average)Average: 58.63 -> 61.32Improved
Train on mixed six datasets instead of each individually (ablation)RoboTron-Drive · Six AD datasets (average)Average: 60.12 -> 61.32Improved
Add perspective-aware prompt (ablation)RoboTron-Drive · Six AD datasets (average)Average: 60.69 -> 61.32Improved
Add perspective-aware prompt on LingoQA (ablation)RoboTron-Drive · LingoQALingo-Judge: 70.20 -> 69.20Hurt
Train one generalist on all datasets instead of specialists, then test zero-shot on unseen datasetsRoboTron-Drive · DriveBench (zero-shot)GPT-Score: 54.48 -> 61.06Improved
Use AD fine-tuning instead of zero-shot modelRoboTron-Drive-Zero · NuInstructAverage: 0.00 -> 46.30Improved
Use RoboTron-Drive instead of Drive-OV (LLaVA-OV with same prompt and data) on LingoQARoboTron-Drive · LingoQALingo-Judge: 70.10 -> 69.20No clear effect

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