cs.CV

IRIS: Intent Resolution via Inference-time Saccades for Open-Ended VQA in Large Vision-Language Models

arXiv:2602.16138v2 Announce Type: replace
Abstract: We introduce IRIS (Intent Resolution via Inference-time Saccades), a novel training-free approach that uses eye-tracking data in real-time to resolve ambiguity in open-ended VQA. Through a comprehens…