V-REX: Efficient Specialist VLM Training for Veterinary X-Rays
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, increa
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%Fine-tuning →
- LinkedLinked via arxiv author · 85%Tim Elsner →
“V-REX: Efficient Specialist VLM Training for Veterinary X-Rays”
- LinkedLinked via arxiv author · 85%Nicole McNally →
“V-REX: Efficient Specialist VLM Training for Veterinary X-Rays”
- LinkedLinked via arxiv author · 85%Andre Dourson →
“V-REX: Efficient Specialist VLM Training for Veterinary X-Rays”
- LinkedLinked via arxiv author · 85%Michael Fitzke →
“V-REX: Efficient Specialist VLM Training for Veterinary X-Rays”