3 papers
cs.CV2026
When Adaptation Hurts: Connecting Representational Drift to OOD Failures in MedSAM Fine-Tuning
Marko Haralović, Sounic Akkaraju, Carlo Baretta +2
Foundation models for medical image segmentation, like prompt-based MedSAM, generalize well across domains and modalities, often in zero or few-shot setups. However, their performa…
cs.CV2026
G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding
Marko Haralović, Akash Ramakrishnan, Estefania Talavera Martinez
Egocentric action understanding is often addressed using large video models pretrained on extensive exocentric datasets. However, many first-person actions depend on a small number…
cs.CV2026
Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment
Marko Haralović, Zhiqi Miao, Alexander Machiel Bont +3
Surgical performance assessment in minimally invasive surgery largely relies on manual expert review, making it time-consuming, subjective, and difficult to scale. While existing s…