GATS: Gather-Attend-Scatter

As the AI community increasingly adopts large-scale models, it is crucial to develop general and flexible tools to integrate them. We introduce Gather-Attend-Scatter (GATS), a novel module that enables seamless combination of pretrained foundation models, both trainable and frozen, into larger multi...

Full description

Saved in:
Bibliographic Details
Main Authors Zolna, Konrad, Cabi, Serkan, Chen, Yutian, Lau, Eric, Fantacci, Claudio, Pasukonis, Jurgis, Springenberg, Jost Tobias, Colmenarejo, Sergio Gomez
Format Journal Article
LanguageEnglish
Published 16.01.2024
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Computer Science - Robotics
Online AccessGet full text

Cover

More Information
Summary:As the AI community increasingly adopts large-scale models, it is crucial to develop general and flexible tools to integrate them. We introduce Gather-Attend-Scatter (GATS), a novel module that enables seamless combination of pretrained foundation models, both trainable and frozen, into larger multimodal networks. GATS empowers AI systems to process and generate information across multiple modalities at different rates. In contrast to traditional fine-tuning, GATS allows for the original component models to remain frozen, avoiding the risk of them losing important knowledge acquired during the pretraining phase. We demonstrate the utility and versatility of GATS with a few experiments across games, robotics, and multimodal input-output systems.
DOI:10.48550/arxiv.2401.08525