AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming

Jiaxiang Liu, Tianxiang Hu, Juwei Guan, Yujie Wu, Yusong Wang, Yao Mu, Zuozhu Liu, Mingkun Xu

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 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 confusion-aware attributes (negative expert text) (ablation)BioMedVR · 11 biomedical datasets avgaccuracy (%): 71.4 -> 76.4Improved
add confusion-suppression loss (ablation)BioMedVR · 11 biomedical datasets avgaccuracy (%): 73.6 -> 76.4Improved
add negative prompt expert (MoPE) (ablation)BioMedVR · 11 biomedical datasets avgaccuracy (%): 75.6 -> 76.4Improved
add negative prompt expert (MoPE) (ablation)BioMedVR · COVID-19accuracy (%): 74.3 -> 77.4Improved
use confusion-aware VR instead of AttrVRAttrVR · 11 biomedical datasets avgaccuracy (%): 73.0 -> 76.4Improved
use GPT-4.1 instead of GPT-5-mini/GPT-5 for attribute generation (ablation)BioMedVR · 11 biomedical datasets avgaccuracy (%): 76.4 -> 75.2No clear effect
use GPT-4o-mini instead of GPT-4.1 for attribute generation (ablation)BioMedVR · 11 biomedical datasets avgaccuracy (%): 76.4 -> 76.4No clear effect
apply BioMedVR to RN50 backboneAttrVR baseline · 11 biomedical datasets avg (RN50)accuracy (%): 49.0 -> 51.6Improved
apply BioMedVR to ViT-B/32 backboneAttrVR baseline · 11 biomedical datasets avg (ViT-B/32)accuracy (%): 59.0 -> 60.5Improved
add confusion-aware zero-shot scoringCLIP · 11 biomedical datasets avg (zero-shot)accuracy (%): 28.1 -> 31.6Improved
add confusion-aware zero-shot scoringCLIP · EuroSAT (zero-shot)accuracy (%): 21.2 -> 21.0No clear effect
doubling VR parameters with two expertsAttrVR · Training cost (BUSI)trainable parameters: 0.15M -> 0.30MHurt

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