DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance
Many high-performing pathology tile encoders are now foundation models with hundreds of millions to over a billion parameters. Encoding and storing the thousands of tiles in each whole-slide image with such models is costly on commodity hardware, so compact encoders that retain useful downstream performance are a valuable alternative. We present DistillPath-KS16, which starts from the existing 22M kaiko ViT-S/16 encoder and improves it by distilling from released pathology encoders used as frozen teachers. The recipe reads only the teachers' final class and patch tokens and trains on 6,000 pub
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 46%Introducing Gemma 4 12B: a unified, encoder-free multimodal model →
- LinkedLinked via arxiv author · 85%Ramon Kaspar →
“DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance”
- LinkedLinked via arxiv author · 85%Andrey Ignatov →
“DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance”
- LinkedLinked via arxiv author · 85%Valentina Boeva →
“DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance”