MLMG-VLCR: A Multimodal LLM Guided Zero-shot Method for Visio-linguistic Compositional Reasoning with Autoregressive Generative Language Model

Open Webpage

Ziyu Gong, Chengcheng Mai, Yihua Huang

Published: 01 Jan 2024, Last Modified: 02 Aug 2025ICMR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0