Jessica Loo, Theodoros Pissas, Byunghak Kang, Vincent A. Ella, Xiaoyan Zhang, Kevin Sweeney, Walter Georgescu, Prateek Katiyar, Julie Boisclair, Holger Hoefling · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26586 · cited by 0 works (OpenAlex) · open-access PDF
Ici, nous présentons TOX-FM, une famille de PFM non cliniques formés sur des ensembles de données d'histopathologie diversifiées à grande échelle de plus d'un million d'images en diapositive entières composées de plus de 60 organes sur six espèces animales provenant de plus de 14 000 études de toxicologie sur six décennies. Nous introduisons un critère de référence complet de 18 tâches non cliniques en aval, incorporons un critère établi de 9 tâches cliniques en aval, et évaluons TOX-FM contre les PFM cliniques de pointe dans les domaines non cliniques et cliniques.
Machine translation (Meta M2M100); the English original follows.
Here, we present TOX-FM, a family of non-clinical PFMs trained on large-scale diverse histopathology datasets of over one million whole slide images consisting of over 60 organs across six animal species from over 14,000 toxicology studies across six decades. We introduce a comprehensive benchmark of 18 non-clinical downstream tasks, incorporate an established benchmark of 9 clinical downstream tasks, and evaluate TOX-FM against state-of-the-art clinical PFMs across both non-clinical and clinical domains. Notably, we explore open questions surrounding domain-specific training and cross-domain generalization, offering insights into the opportunities and challenges of applying PFMs in the non-clinical domain.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Benchmark (surveying), Foundation (evidence), Computer science, Downstream (manufacturing), Engineering, Medical physics
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26586, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange