Metraipolis › archive › dc_c57d5bfbeeb4
V-REX: Efficient Specialist VLM Training for Veterinary X-Rays — arXiv:2608.20069
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20069
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:04:45.726Z
- SHA-256 of the archived text
306b584944ef6bd61f2a50ccc834d9a7668f23666db8893441160424be6250ad- Stable URL of this page
https://metraipolis.com/documento/dc_c57d5bfbeeb4
How to cite
V-REX: Efficient Specialist VLM Training for Veterinary X-Rays — arXiv:2608.20069 — arXiv (en), https://arxiv.org/abs/2608.20069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c57d5bfbeeb4 (Metraipolis archive dc_c57d5bfbeeb4, sha256 306b584944ef6bd61f2a50ccc834d9a7668f23666db8893441160424be6250ad)
BibTeX
@misc{dcc57d5bfbeeb4,
title = {V-REX: Efficient Specialist VLM Training for Veterinary X-Rays — arXiv:2608.20069},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20069},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c57d5bfbeeb4; sha256 306b584944ef6bd61f2a50ccc834d9a7668f23666db8893441160424be6250ad},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While generalist VLMs are expensive to train, creating domain experts is widely assumed to require fine-tuning increasingly large foundation models. We show that, in veterinary radiology, this assumption is misguided. By rethinking the entire VLM pipeline - from text tokenisation and pre-training to grounding and inference - we demonstrate that careful engineering can yield models that outperform much larger foundation models from scratch, without relying on any other data. Our approach introduces new strategies for generative pre-training and grounding that improve training efficiency, increasing data utilisation and downstream performance. Using only a fraction of the parameters, data, and compute of contemporary generalist models, we develop the first VLM capable of generating diagnostic reports for veterinary radiographs, surpassing open foundation models on this task by significant margin. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.20069 — 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 2026-10-18T12:01:57.733Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).