AI Paper Atlas

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

Fusing Pixels and Genes: Spatially-Aware Learning in Computational Pathology

Minghao Han, Dingkang Yang, Linhao Qu, Zizhi Chen, Gang Li, Han Wang, Jiacong Wang, Lihua Zhang

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 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
fine-tune PLIP with gene expression supervisionPLIP · DLPFC linear probingbalanced accuracy: 0.429 -> 0.476Improved
fine-tune CONCH with gene expression supervisionCONCH · DLPFC linear probingbalanced accuracy: 0.454 -> 0.481Improved
fine-tune CONCH with gene expression supervisionCONCH · HBC linear probingbalanced accuracy: 0.704 -> 0.811Improved
add spatial-aware CGR loss to gene encoder pretraining (ablation)STAMP_G · gene encoder pretraininglinear probing / clusteringImproved
use only IGR loss for gene encoder (ablation)STAMP_G · gene encoder pretraininglinear probing / clusteringHurt
add vanilla contrastive alignment of UNI with STAMP_G (L_P-S) (ablation)STAMP_V · DLPFClinear probingImproved
add region-gene loss L_R-S (ablation)STAMP · DLPFC and PSCdownstream tasksImproved
add patch-region intra-modal loss L_P-R (ablation)STAMP · DLPFC and PSCdownstream tasksImproved
add cross-scale patch positioning loss L_CSP (ablation)STAMP · DLPFC and PSCdownstream tasksImproved
use SpaVis-6M and stage 1 pretraining (ablation)STAMP · DLPFC and HBClinear probing and clusteringImproved
add alignment to gene encoder (STAMP_G dagger -> STAMP_G) (ablation)STAMP_G · DLPFC linear probingbalanced accuracy: 0.571 -> 0.658Improved
fuse gene and vision embeddings (STAMP_V -> STAMP_F)STAMP · DLPFC linear probingbalanced accuracy: 0.624 -> 0.721Improved

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