Surgical foundation model SURGE maps the limits of annotation gains

CAMMA's SURGE, a surgical foundation model pretrained on 30M+ frames, shows perception tasks saturate with just one annotated video while reasoning tasks keep improving, and safety-check tasks remain stubbornly hard regardless of annotation volume.

2026-10-14 ~ 2026-10-14 · 3 related posts

• SURGE Surgical Foundation Model: Perception Saturates After Just One Labeled Video — maier_ak · 2026-10-14
• SURGE Reasoning Tasks Keep Improving Through 14 Labeled Videos; CVoS Resists Pretraining — maier_ak · 2026-10-14
• Surgical foundation model SURGE maps its own limits: safety checks resist pretraining and labels — maier_ak · 2026-10-14