AI RESEARCH
MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
arXiv CS.CV
•
ArXi:2605.18176v1 Announce Type: new This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participants must answer 185 closed-form questions over the CASTLE 2024 dataset. In contrast to prior single-video egocentric benchmarks, CASTLE requires reasoning over four days of activity, 15 synchronized perspectives, official transcripts, and multiple auxiliary modalities, including personal photos, auxiliary videos, gaze, thermal imagery, and heartrate measurements.