3 papers
cs.CV2026
DiLA: Disentangled Latent Action World Models
Tianqiu Zhang, Muyang Lyu, Yufan Zhang +2
Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trad…
cs.CV2025
An Egocentric Vision-Language Model based Portable Real-time Smart Assistant
Yifei Huang, Jilan Xu, Baoqi Pei +16
We present Vinci, a vision-language system designed to provide real-time, comprehensive AI assistance on portable devices. At its core, Vinci leverages EgoVideo-VL, a novel model t…
cs.CV2024
Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model
Yifei Huang, Jilan Xu, Baoqi Pei +15
We introduce Vinci, a real-time embodied smart assistant built upon an egocentric vision-language model. Designed for deployment on portable devices such as smartphones and wearabl…