ReaMIL uses a hinge-based budgeted-sufficiency loss to select compact sets of informative tiles in histopathology slides, achieving high AUC with minimal evidence.
Is attention interpretable? InProceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2931–2951
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.