Metraipolis › archive › dc_64db66ec708c

Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology — arXiv:2609.17868

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17868
License (as archived)
CC0-1.0
Archived
2026-10-15T16:16:14.200Z
SHA-256 of the archived text
1372b88e06938e1a3c0b47ce8f5a5a47a2c23065d09c3a5e2c5d4aaf8af91eae
Stable URL of this page
https://metraipolis.com/documento/dc_64db66ec708c

How to cite

Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology — arXiv:2609.17868 — arXiv (en), https://arxiv.org/abs/2609.17868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64db66ec708c (Metraipolis archive dc_64db66ec708c, sha256 1372b88e06938e1a3c0b47ce8f5a5a47a2c23065d09c3a5e2c5d4aaf8af91eae)
BibTeX
@misc{dc64db66ec708c,
  title = {Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology — arXiv:2609.17868},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17868},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64db66ec708c; sha256 1372b88e06938e1a3c0b47ce8f5a5a47a2c23065d09c3a5e2c5d4aaf8af91eae},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.17868 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T15:45:19.731Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).