AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis

Gui Wang, Zehao Zhong, YongSong Zhou, Yudong Li, Ende Wu, Wooi Ping Cheah, Rong Qu, Jianfeng Ren, Linlin Shen

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 17 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
scale InternVL from 8B to 32BInternVL · X-PCR progressive reasoningaverage stage accuracy (%): 64.60 -> 70.14Improved
go from commercial GPT-5 to open-source InternVL-32BMLLMs · X-PCR progressive reasoningaverage stage accuracy (%): 76.24 -> 70.14Hurt
increase task difficulty from resident to specialist levelGPT-5 · X-PCR progressive reasoningexpertise-stratified accuracy (%): 80.64 -> 62.92Hurt
move from IQA to clinical decision-making stageGPT-5 · X-PCR progressive reasoningstage accuracy (%): 98.90 -> 54.71Hurt
use multiple modalities (Group 1 hospital cases) instead of single-modality imagesGPT-5 · X-PCR cross-modalityaccuracy (%): 72.60 -> 59.60Hurt
use multiple modalities (Group 1 hospital cases) instead of single-modality imagesQwen3-VL-30B-A3B · X-PCR cross-modalityaccuracy (%): 64.33 -> 48.07Hurt
add more imaging modalities (from CFP/OCT to CFP/OCT/FFA/EP)GPT-5 · X-PCR hospital casesaccuracy (%): 59.60 -> 47.60Hurt
keep OCT image (remove it as ablation gives MCS 1.39) (ablation)GPT-5 · X-PCR hospital cases Group 1MCS (accuracy drop %): 1.39Improved
keep CFP image (removing it gives MCS 0.97) (ablation)GPT-5 · X-PCR hospital cases Group 1MCS (accuracy drop %): 0.97Improved
keep CFP image (removing it gives MCS -0.59) (ablation)Qwen3-VL-8B · X-PCR hospital cases Group 1MCS (accuracy drop %): -0.59Hurt
keep CFP in Group 3 (removing it gives MCS -5.08) (ablation)GPT-5 · X-PCR hospital cases Group 3MCS (accuracy drop %): -5.08Hurt
keep ICGA in Group 3 (removing it gives MCS -4.99) (ablation)GPT-5 · X-PCR hospital cases Group 3MCS (accuracy drop %): -4.99Hurt

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