{"ID":22918800,"CreatedAt":"2026-09-17T01:02:08.507062015Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.17868","arxiv_id":"2609.17868","title":"Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology","abstract":"Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathology vision-language model can instead be assembled by parameter-efficient alignment of frozen unimodal foundation models, leaving their pretrained representations untouched. Here we present Lumen, which aligns frozen Virchow2 and BioMedBERT backbones using rank-4 adapters and projection heads, training only 0.40% of the total parameters on the public QUILT-1M corpus. Across nine public zero-shot patch benchmarks, Lumen achieved the highest mean chance-corrected balanced accuracy, 0.546 versus 0.461 for the strongest baseline (paired difference 0.086, 95% CI 0.042-0.136). On lymph-node metastasis detection, Lumen reached an AUROC of 0.964 (95% CI 0.956-0.971) on 4,214 held-out internal slides and 0.955 (95% CI 0.942-0.966) on 2,368 slides across nine external cohorts and six organs. At the internally calibrated threshold, it outperformed all vision-language baselines, with a balanced accuracy of 0.909 (95% CI 0.896-0.923) internally and 0.915 (95% CI 0.902-0.929) externally. Lumen performed competitively across the evaluations, with the exception of cross-modal retrieval, where it ranked third behind CONCH and PathGen-L/14. Fully fine-tuning both encoders gave Lumen no consistent benefit over low-rank adaptation, although it improved retrieval. Aligning frozen unimodal foundation models therefore yields strong and transferable performance at patch and slide level while training only a small fraction of the parameters.","short_abstract":"Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathology vision-language model can instead be assembled by parameter-efficient alignment of frozen unimodal foundation models, leaving their pretrained representations untou...","url_abs":"https://arxiv.org/abs/2609.17868","url_pdf":"https://arxiv.org/pdf/2609.17868v1","authors":"[\"Kiarash Tajbakhsh\",\"Abdelrahman Faqieh\",\"Michael Jopiti\",\"Javier Garcia-Baroja\",\"Philipp Zens\",\"Branislav Zagrapan\",\"Yuri Tolkach\",\"Martin D. Berger\",\"Aurel Perren\",\"Bastian Dislich\",\"Inti Zlobec\",\"Amjad Khan\"]","published":"2026-09-15T21:47:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}