i-Code Studio: A Configurable and Composable Framework for Integrative AI

TL;DR

The paper introduces i-Code Studio, a flexible framework that orchestrates multiple pre-trained models for complex multimodal tasks without finetuning, advancing the development of integrative AI towards Artificial General Intelligence.

Contribution

It presents a configurable, composable platform for integrating models to perform diverse multimodal tasks efficiently without additional training.

Findings

Achieves strong zero-shot performance on multimodal tasks

Enables rapid development of multimodal agents

Demonstrates versatility across various modalities

Abstract

Artificial General Intelligence (AGI) requires comprehensive understanding and generation capabilities for a variety of tasks spanning different modalities and functionalities. Integrative AI is one important direction to approach AGI, through combining multiple models to tackle complex multimodal tasks. However, there is a lack of a flexible and composable platform to facilitate efficient and effective model composition and coordination. In this paper, we propose the i-Code Studio, a configurable and composable framework for Integrative AI. The i-Code Studio orchestrates multiple pre-trained models in a finetuning-free fashion to conduct complex multimodal tasks. Instead of simple model composition, the i-Code Studio provides an integrative, flexible, and composable setting for developers to quickly and easily compose cutting-edge services and technologies tailored to their specific requirements. The i-Code Studio achieves impressive results on a variety of zero-shot multimodal tasks, such as video-to-text retrieval, speech-to-speech translation, and visual question answering. We also demonstrate how to quickly build a multimodal agent based on the i-Code Studio that can communicate and personalize for users.