BatMIL uses hybrid hyperbolic-Euclidean geometry, an S4 state-space backbone, and chunk-level mixture-of-experts to outperform prior multiple-instance learning methods on seven whole-slide image datasets across six cancers.
Transmil: Transformer based correlated multiple instance learning for whole slide image classification.Advances in neural information processing systems, 34:2136–2147, 2021
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LoGo-MR uses neighbor-slice encoding and transformer-based multiple instance learning in three anatomical planes to predict 1-5 year breast cancer risk from MRI, achieving AUCs of 0.69-0.77 on a 7,500-patient cohort while providing interpretable risk maps.
SwiftRepertoire synthesizes compact adapters from prototype dictionaries conditioned on repertoire probes for few-shot adaptation of pretrained encoders in immune signature detection.
citing papers explorer
-
Geometry-Aware State Space Model: A New Paradigm for Whole-Slide Image Representation
BatMIL uses hybrid hyperbolic-Euclidean geometry, an S4 state-space backbone, and chunk-level mixture-of-experts to outperform prior multiple-instance learning methods on seven whole-slide image datasets across six cancers.
-
LoGo-MR: Screening Breast MRI for Cancer Risk Prediction by Efficient Omni-Slice Modeling
LoGo-MR uses neighbor-slice encoding and transformer-based multiple instance learning in three anatomical planes to predict 1-5 year breast cancer risk from MRI, achieving AUCs of 0.69-0.77 on a 7,500-patient cohort while providing interpretable risk maps.
-
SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes
SwiftRepertoire synthesizes compact adapters from prototype dictionaries conditioned on repertoire probes for few-shot adaptation of pretrained encoders in immune signature detection.