AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving

Ruifei Zhang, Wei Zhang, Xiao Tan, Sibei Yang, Xiang Wan, Xiaonan Luo, Guanbin Li

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning · 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 CCDP (ablation)VLDrive (LLaMA*) · LangAuto (25% data)DS: 35.5 -> 39.8Improved
add MEFA (ablation)VLDrive (LLaMA*) · LangAuto (25% data)DS: 35.9 -> 39.8Improved
add DDIA (ablation)VLDrive (LLaMA*) · LangAuto (25% data)DS: 36.3 -> 39.8Improved
add all three modules to the baseline (ablation)VLDrive (LLaMA*) · LangAuto (25% data)DS: 30.0 -> 39.8Improved
use CCDP instead of structural pooling (ablation)VLDrive · LangAuto (25% data)DS: 33.6 -> 39.8Improved
add token reconstruction to dynamic pruning (ablation)VLDrive · LangAuto (25% data)DS: 36.3 -> 39.8Improved
raise token retention ratio from 5% to 30% (ablation)VLDrive · LangAuto (25% data)DS: 33.4 -> 39.8Improved
raise token retention ratio from 30% to 50% (ablation)VLDrive · LangAuto (25% data)DS: 39.8 -> 39.8No clear effect
memory bank of 10 frames instead of 5 (ablation)VLDrive · LangAuto (25% data)DS: 37.1 -> 39.8Improved
increase memory bank from 10 to 20 frames (ablation)VLDrive · LangAuto (25% data)DS: 39.8 -> 38.3Hurt
replace 7B LLaVA-v1.5 LLM with lightweight 1.3B TinyLLaMA plus vision enhancementsVLDrive · LangAutoDS: 36.2 -> 43.8Improved
vanilla lightweight TinyLLaMA in LMDrive versus 7B LLaVA-v1.5LMDrive · LangAutoDS: 36.2 -> 25.2Hurt

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