arXiv: AI for sleep / behavior / health coaching
EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input
EgoGazeLite: 토큰 효율적인 멀티모달 LLM 비디오 입력을 위한 기기 내 자기중심 시선 예측
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.