AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration

Chenran Zhang, Ruiqi Wu, Tao Zhou, Yi Zhou

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models · 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
add MedKCO pretrainingCLIP · zero-shot avg (9 datasets)accuracy/AUC: 0.616 -> 0.693Improved
add MedKCO pretrainingFILIP · zero-shot avg (9 datasets)accuracy/AUC: 0.530 -> 0.640Improved
add MedKCO pretrainingCLIP · report generation avgavg score: 0.188 -> 0.198Improved
add label-level curriculum (ablation)CLIP · CFP ODIR200x3accuracy: 0.772 -> 0.847Improved
add description-level curriculum (ablation)CLIP + label curriculum · CFP avgavg: 0.820 -> 0.839Improved
add self-paced asymmetric loss (ablation)CLIP + both curricula · CFP avgavg: 0.839 -> 0.846Improved
add self-paced asymmetric loss (ablation)CLIP + both curricula · CFP ODIR200x3accuracy: 0.890 -> 0.863Hurt
use global linear schedule instead of segmented (ablation)MedKCO · CFP avgavg: 0.805 -> 0.846Improved
divide stages by distance rather than sample count (ablation)MedKCO · CFP avgavg: 0.820 -> 0.846Improved
use 2 instead of 3 or 4 description-level stages (ablation)MedKCO · CFP avgavg: 0.820 -> 0.846Improved
use CL-log or CL-logit curriculum instead of random orderCLIP · zero-shot avg (9 datasets)accuracy/AUC: 0.616 -> 0.600Hurt
add MedKCO pretrainingFILIP · ODIR200x3accuracy: 0.457 -> 0.833Improved

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