AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Turning Pre-Trained Vision Transformers into End-to-End Histopathology Whole Slide Image Models for Survival Prediction

Jiawen Li, Jiali Hu, Xitong Ling, Renao Yan, Yuxuan Chen, Tian Guan, Yonghong He

CVPR 2026 · Architectures and efficiency › Attention and transformers · approach: Token merging and masked pretraining

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
convert pre-trained ViT to end-to-end WSI model (E2E-ViT) instead of two-stage MILH0-mini · 5-dataset survival overallC-index: 0.6810 -> 0.7158Improved
convert pre-trained ViT to E2E-ViT instead of best two-stage MILCONCH · 5-dataset survival overallC-index: 0.6902 -> 0.6978Improved
convert ImageNet ViT-Small to E2E-ViT instead of two-stage MILViT-Small · 5-dataset survival overallC-index: 0.6386 -> 0.6667Improved
use E2E-ViT linear-probe slide features instead of slide foundation modelsE2E-ViT · 5-dataset survival overall (linear probe)C-index: H0-mini 0.6685, CONCH 0.6534, ViT-Small 0.5959 vs TITAN 0.6582Mixed
use E2E H0-mini instead of SFMs for slide encoding speedE2E H0-mini · Inference time, 10,000 tilesspeedup: 2.64x faster than CHIEF, 7.49x faster than FEATHERImproved
replace mean patch merging with max pooling (ablation)E2E-ViT · HNSC/LUAD/PDAC survivalC-index: CONCH HNSC 0.7421 -> 0.7387Hurt
replace mean patch merging with attention pooling (ablation)E2E-ViT · HNSC/LUAD/PDAC survivalC-index: CONCH HNSC 0.7421 -> 0.7321No clear effect
use ALiBi relative positional encoding instead of none (ablation)E2E CONCH · LUAD survivalC-index: 0.6350 -> 0.7077Improved
use ALiBi instead of learnable positional embedding (ablation)E2E-ViT · HNSC/LUAD/PDAC survival, 3 backbonesC-index: CONCH HNSC 0.6920 -> 0.7421; ViT-Small PDAC 0.6710 -> 0.6408Mixed
vary ratio of sequence length to tile number (ablation)E2E-ViT · HNSC, LUAD, PDAC, CCRCCC-indexNo clear effect
convert larger pathology ViTs (UNI, Prov-GigaPath, Virchow, PathOrchestra, UNI-2) instead of two-stage ABMILE2E-ViT · LUAD survival (fine-tuning)C-index: +1.03% to +3.87%Improved
convert larger ViTs under linear probing, versus TITANE2E-ViT · MBC survival (linear probe)C-index: TITAN 0.6624; Virchow, PathOrchestra, UNI-2 surpass itMixed

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