AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Towards High-Resolution Visual Perception via Hierarchical Entity Exploration

Ziyu Ma, Shidong Yang, Yuxiang Ji, Yiming Hu, Tongwen Huang, Yong Wang, Jianfei Cai, Xiangxiang Chu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 0 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
replace uniform grid partitioning with entity-based exploration (ablation)HEE · Visual Probe Hardaccuracy: 37.7 -> 50.0Improved
add confidence-guided backtracking (ablation)HEE · Visual Probe Hardaccuracy: 41.5 -> 50.0Improved
add VLM confidence term M(r,q) to scoring (ablation)HEE · Visual Probe Hardaccuracy: 21.7 -> 50.0Improved
add SigLIP similarity term S(q,r) to scoring (ablation)HEE · Visual Probe Hardaccuracy: 43.4 -> 50.0Improved
increase entity clusters from 4 to 8 (ablation)HEE · Visual Probe Hardaccuracy: 50.0 -> 37.7Hurt
vary lambda from 0.2 to 0.7 vs 0.5 (ablation)HEE · Visual Probeaverage accuracy: 50.7 / 53.2 vs 54.7No clear effect
use DINO-X instead of YOLO-World detector (ablation)HEE · Visual Probe Easyaccuracy: 62.4 -> 67.4 (with SigLIP)Improved
use SigLIP instead of CLIP (ablation)HEE · Visual Probe Easyaccuracy: 62.4 -> 67.4Improved
apply HEE to Qwen2.5-VL-7BQwen2.5-VL-7B · Visual Probe Hardaccuracy: 23.9 -> 50.0Improved
apply HEE to InternVL2.5-8BInternVL2.5-8B · HR-Bench 8K Overallaccuracy: 54.8 -> 66.5Improved
HEE vs RAP and ZoomEyeQwen2.5-VL-7B · HR-Bench 4K Overallaccuracy and time: 73.9 vs 71.1/71.4; 24min vs 126/46minImproved
apply HEE to Qwen2.5-VL-7BQwen2.5-VL-7B · MME-RealWorld Avgaccuracy: 59.99 -> 63.38Improved

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