AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

CMID: Towards Medical Visual Question Answering via Contrastive Mutual Information Decoding

Zhihong Zhu, Yunyan Zhang, Fan Zhang, Bowen Xing, Xian Wu

AAAI 2026 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 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 attention shift correction (alpha term, focus-excluding contrast) (ablation)CMID · VQA-RAD openRecall: 36.57 -> 38.75Improved
add attention dispersion correction (beta term, focus-preserving contrast) (ablation)CMID · VQA-RAD openRecall: 37.12 -> 38.75Improved
add reliability gate R_PFA instead of fixed 1 (ablation)CMID · VQA-RAD openRecall: 36.89 -> 38.75Improved
use entropy-aware layer reweighting instead of naive averaging (ablation)CMID · VQA-RAD openRecall: 37.41 -> 38.75Improved
use contrastive deltas rather than directly injecting focus-view logits (ablation)CMID · PathVQA openRecall: 10.61 -> 11.41Improved
hard binary mask instead of soft mask (ablation)CMID PFA · VQA-RAD avgScore: 52.15 -> 52.81Improved
aggregate attention from all layers instead of a layer subset (ablation)CMID PFA · VQA-RAD avgScore: 51.34 (early) / 52.56 (middle) -> 52.81 (all)Improved
apply CMID to other medical LVLMsHuatuoGPT-V, Med-Flamingo, RadFM, MedVInT, LLaVA-Med · VQA-RAD, SLAKEScore: 48.08 -> 52.81 (LLaVA-Med VQA-RAD); 44.82 -> 47.26 (RadFM)Improved
general-domain contrastive decoding (M3ID, VCD) on Med-VQALLaVA-Med v1.5 · VQA-RAD openRecall: 34.39 -> 30.93 (M3ID); 34.39 -> 29.75 (VCD)Hurt
increase alpha or beta beyond optimum (ablation)CMID · PathVQAOverall ScoreHurt
add CMID to greedy decodingLLaVA-Med v1.5 · Inference costlatency ms/token: 121.48 -> 136.23Hurt

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