Preprint
Aug 2026
EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input
EgoGazeLite, a lightweight dual-process gaze predictor for egocentric video understanding with MLLMs that removes the need for eye-tracking hardware for token-efficient, gaze-conditioned egocentric video understanding with MLLMs.
Matteo Stoiber, Niels Buus Lassen
· 0 citations