ReaMIL uses a hinge-based budgeted-sufficiency loss to select compact sets of informative tiles in histopathology slides, achieving high AUC with minimal evidence.
Towards a general-purpose foundation model for com- putational pathology.Nature Medicine, 30:154–165
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology
ReaMIL uses a hinge-based budgeted-sufficiency loss to select compact sets of informative tiles in histopathology slides, achieving high AUC with minimal evidence.