SurgEye: Instruction Tuning-Free Perception-Reasoning Framework for Surgical Scene Understanding
arXiv:2611.04012v1 Announce Type: new Abstract: Surgical scene understanding is pivotal for computer-assisted intervention, yet demands compositional reasoning across instruments, anatomy, and workflow. Existing surgical vision-language models rely on instruction tuning with large-scale question-an…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-04 05:00 · arXiv cs.CV
SurgEye: Instruction Tuning-Free Perception-Reasoning Framework for Surgical Scene Understanding