A new surgical VQA benchmark with 167,384 questions shows generalist VLMs handle basic surgical perception but fall to near-random on medical-knowledge questions, and medical VLMs underperform generalist models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Challenging Vision-Language Models with Surgical Data: A New Dataset and Broad Benchmarking Study
A new surgical VQA benchmark with 167,384 questions shows generalist VLMs handle basic surgical perception but fall to near-random on medical-knowledge questions, and medical VLMs underperform generalist models.