Genixer : Empowering multimodal Large Language Models as a powerful data generator

• Main Authors: ZHAO, Henry Hengyuan, ZHOU, Pan, SHOU, Mike Zheng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Large Language Models; LLMs; Data generation pipeline; Data generators; MLLMs; Multimodal Large Language Models; Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/9600; https://ink.library.smu.edu.sg/context/sis_research/article/10600/viewcontent/Genixer.pdf
• Institution: Singapore Management University

Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but few research studies aim to gauge the ability to generate visual instruction tuning data. This paper proposes to explore the potential of empowering MLLMs to generate data independently without relying...