# Plug-and-Play Logit Fusion for Heterogeneous Pathology Foundation Models

arXiv: https://arxiv.org/abs/2604.07779 · HTML: https://mlsanity.com/paper/2604.07779/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology](https://mlsanity.com/paper/2505.20202/) (2025)
- [Towards Large-Scale Training of Pathology Foundation Models](https://mlsanity.com/paper/2404.15217/) (2024)
- [Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysis](https://mlsanity.com/paper/2510.27237/) (2025)
- [Ensemble learning of pathology foundation models for precision oncology](https://mlsanity.com/paper/2508.16085/) (2025)

## Built on by (most cited first, 1 of 1)

- [FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology](https://mlsanity.com/paper/2609.27710/) (2026)

## Abstract (arXiv)

Pathology foundation models (FMs) have become central to computational histopathology, offering strong transfer performance across a wide range of diagnostic and prognostic tasks. The rapid proliferation of pathology foundation models creates a model-selection bottleneck: no single model is uniformly best, yet exhaustively adapting and validating many candidates for each downstream endpoint is prohibitively expensive. We address this challenge with a lightweight and novel model fusion strategy, LogitProd, which treats independently trained FM-based predictors as fixed experts and learns sample-adaptive fusion weights over their slide-level outputs. The fusion operates purely on logits, requiring no encoder retraining and no feature-space alignment across heterogeneous backbones. We further provide a theoretical analysis showing that the optimal weighted product fusion is guaranteed to perform at least as well as the best individual expert under the training objective. We systematically evaluate LogitProd on 22 benchmarks spanning WSI-level classification, tile-level classification, gene mutation prediction, and discrete-time survival modeling. LogitProd ranks first on 20/22 tasks and improves the average performance across all tasks by ~3% over the strongest single expert. LogitProd enables practitioners to upgrade heterogeneous FM-based pipelines in a plug-and-play manner, achieving multi-expert gains with ~12× lower training cost than feature-fusion alternatives.