Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.17868v1 Announce Type: new 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 unimo…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv cs.CV
Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology