Medical Vision-language models (VLMs) have shown remarkable performances in various medical imaging domains such as histo\-pathology by leveraging pre-trained, contrastive models that exploit visual and textual information. However, histopathology images may exhibit severe domain shifts, such as staining, contamination, blurring, and noise, which may severely degrade the VLM's downstream performance. In this work, we introduce Histopath-C, a new benchmark with realistic synthetic corruptions designed to mimic real-world distribution shifts observed in digital histopathology. Our framework dynamically applies corruptions to any available dataset and evaluates Test-Time Adaptation (TTA) mechanisms on the fly. We then propose LATTE, a transductive, low-rank adaptation strategy that exploits multiple text templates, mitigating the sensitivity of histopathology VLMs to diverse text inputs. Our approach outperforms state-of-the-art TTA methods originally designed for natural images across a breadth of histopathology datasets, demonstrating the effectiveness of our proposed design for robust adaptation in histopathology images. Code and data are available at https://github.com/Mehrdad-Noori/Histopath-C.
@article{arxiv.2601.12493,
title = {Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation},
author = {Mehrdad Noori and Gustavo Adolfo Vargas Hakim and David Osowiechi and Fereshteh Shakeri and Ali Bahri and Moslem Yazdanpanah and Sahar Dastani and Ismail Ben Ayed and Christian Desrosiers},
journal= {arXiv preprint arXiv:2601.12493},
year = {2026}
}