AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

HiLM-D: Enhancing MLLMs with Multi-scale High-Resolution Details for Autonomous Driving

Xinpeng Ding, Jianhua Han, Hang Xu, Wei Zhang, Xiaomeng Li

IJCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 91 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 high-resolution spatial encoder (ablation)HiLM-D · DRAMA-ROLISPmIoU: 43.7 -> 60.5Improved
add query-aware detector (ablation)HiLM-D · DRAMA-ROLISPmIoU: 47.5 -> 60.5Improved
add P-Adapter (ablation)HiLM-D · DRAMA-ROLISPB4 and mIoU: 53.1 -> 56.3 B4; 53.8 -> 60.5 mIoUImproved
add spatial perception stream to BLIP-2BLIP-2 · DRAMA-ROLISPmIoU: 46.3 -> 59.8Improved
add spatial perception stream to Video-LLaMAVideo-LLaMA · DRAMA-ROLISPmIoU: 42.8 -> 59.3Improved
use last frame instead of first frame in spatial stream (ablation)HiLM-D · DRAMA-ROLISPAVG: 54.0 -> 58.4Improved
sample more frames (two or three) instead of one (ablation)HiLM-D · DRAMA-ROLISPB4 / mIoU: 60.5 -> 60.6 mIoU (two); 60.5 -> 60.9 (three)No clear effect
train detection and captioning jointly (ablation)HiLM-D · DRAMA-ROLISPB4 and mIoU: 54.3 -> 56.3 B4; 52.5 -> 60.5 mIoUImproved
use multi-scale features I1,I2,I3 instead of I1 only (ablation)HiLM-D · DRAMA-ROLISPIoU_S: 26.7 -> 33.5Improved
use three P-Adapters instead of one (ablation)HiLM-D · DRAMA-ROLISPmIoU: 52.6 -> 60.5Improved
add four P-Adapters instead of three (ablation)HiLM-D · DRAMA-ROLISPmIoU: 60.5 -> 60.4No clear effect
use alpha (ablation)HiLM-D · DRAMA-ROLISPB4 and mIoU: 54.7 -> 56.3 B4; 56.5 -> 60.5 mIoUImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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