AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation

Haowen Gu, Gensheng Pei, Junzhu Mao, Qiong Wang, Mingwu Ren, Yazhou Yao

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 1 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 box guidance, SARP and R2V (ablation)MedREAL · MedRAVS-13K overallgIoU: 11.35 -> 68.49Improved
add SARP and R2V on top of box guidance (ablation)MedREAL · MedRAVS-13K overallgIoU: 45.02 -> 68.49Improved
add box guidance to SARP+R2V (ablation)MedREAL · MedRAVS-13K overallgIoU: 36.24 -> 68.49Improved
add SARP to box guidance + R2V (ablation)MedREAL · MedRAVS-13K overallgIoU: 23.22 -> 68.49Improved
add R2V to box guidance + SARP (ablation)MedREAL · MedRAVS-13K overallgIoU: 45.50 -> 68.49Improved
add R2V to box guidance + SARP (ablation)MedREAL · MedRAVS-13K overallcIoU: 46.96 -> 70.47Improved
add only R2V without SARP vs box guidance alone (ablation)MedREAL · MedRAVS-13K overallgIoU: 45.02 -> 23.22Hurt
scale MLLM backbone from Qwen3-VL-2B to 4BMedREAL · MedRAVS-13K overallgIoU: 68.49 -> 75.96Improved
scale MLLM backbone from Qwen3-VL-2B to 4BMedREAL · MedRAVS-13K overallcIoU: 70.47 -> 70.26No clear effect
replace LISA with MedREALLISA · MedRAVS-13K overallgIoU: 55.70 -> 68.49Improved
replace LISA with MedREALLISA · MedRAVS-13K BUSIgIoU: 41.76 -> 69.15Improved
replace oracle-prompted MedSAM3 with its agent version using autonomous promptsMedSAM3 · MedRAVS-13K overallgIoU: 70.99 -> 55.71Hurt

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