Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model

TL;DR

Vinci is a real-time, portable egocentric vision-language assistant that enables seamless, hands-free interaction, providing contextual responses, task planning, and visual demonstrations based on continuous environment observation.

Contribution

It introduces Vinci, a novel real-time embodied AI system for portable devices that combines egocentric vision, natural language understanding, and visual task demonstrations.

Findings

Operates in real-time on portable devices.

Provides contextual and historical environment understanding.

Generates visual step-by-step task demonstrations.

Abstract

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 wearable cameras, Vinci operates in an "always on" mode, continuously observing the environment to deliver seamless interaction and assistance. Users can wake up the system and engage in natural conversations to ask questions or seek assistance, with responses delivered through audio for hands-free convenience. With its ability to process long video streams in real-time, Vinci can answer user queries about current observations and historical context while also providing task planning based on past interactions. To further enhance usability, Vinci integrates a video generation module that creates step-by-step visual demonstrations for tasks that require detailed guidance. We hope that Vinci can establish a robust framework for portable, real-time egocentric AI systems, empowering users with contextual and actionable insights. We release the complete implementation for the development of the device in conjunction with a demo web platform to test uploaded videos at https://github.com/OpenGVLab/vinci.