AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Scaling Whole-Slide Pathology Foundation Model Pretraining with Billions Off-the-Shelf Tokens

Honglin Li, Zhongyi Shui, Chenglu Zhu, Lin Yang

ECCV 2026 · Architectures and efficiency › Attention and transformers · approach: Token merging and masked pretraining · 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
replace CLS-only MIL with token-retention slide pretraining (UNI-1 features)ABMIL · BRACS tumor gradingF1: 0.692 -> 0.779Improved
replace CLS-only MIL with token-retention slide pretraining (UNI-1 features)ABMIL · TCGA-LUAD TP53 mutationAUC: 0.701 -> 0.763Improved
use TokRet spatial-token pretraining instead of UNI-2 with ABMILUNI-2 (ABMIL) · TCGA survival (5 cohorts average)C-index: 0.620 -> 0.716Improved
swap tile backbone from UNI-1 to Conch-1.5PathTokScale · TCGA survival (5 cohorts average)C-index: 0.716 -> 0.731Improved
PathTokScale (30k slides) vs TITAN (over 330k slides)TITAN · BCNB ER predictionAUC: 0.905 -> 0.898Mixed
PathTokScale (Conch-1.5) vs TITAN on TCGA-BLCA survivalTITAN · TCGA-BLCA survivalC-index: 0.657 -> 0.655No clear effect
retain few tokens per tile (K at most 4) instead of CLS (ablation)CLS-only baseline · BRACS tumor gradingperformanceHurt
retain more tokens per tile (K at least 8) via TokRet (ablation)TokRet · BRACS tumor gradingperformanceImproved
add TokRet top-20 spatial tokens versus CLS-only (ablation)CLS-only baseline · BRACS tumor gradingperformanceImproved
use greedy dissimilarity TokRet instead of attention top-K selection (ablation)attention Top-K · BRACS tumor gradingperformanceImproved
use TokRet token selection instead of average pooling of spatial tokens (ablation)avg-pool · BRACS tumor gradingperformanceImproved
scale pretraining tokens from CLS (0.1B) to 2B via TokRet (ablation)PathTokScale · BRACS tumor gradingperformanceImproved

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