Saved in:
Bibliographic Details
Main Authors: Wu, Junda, Zhang, Zhehao, Xia, Yu, Li, Xintong, Xia, Zhaoyang, Chang, Aaron, Yu, Tong, Kim, Sungchul, Rossi, Ryan A., Zhang, Ruiyi, Mitra, Subrata, Metaxas, Dimitris N., Yao, Lina, Shang, Jingbo, McAuley, Julian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15310
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910617874464768
author Wu, Junda
Zhang, Zhehao
Xia, Yu
Li, Xintong
Xia, Zhaoyang
Chang, Aaron
Yu, Tong
Kim, Sungchul
Rossi, Ryan A.
Zhang, Ruiyi
Mitra, Subrata
Metaxas, Dimitris N.
Yao, Lina
Shang, Jingbo
McAuley, Julian
author_facet Wu, Junda
Zhang, Zhehao
Xia, Yu
Li, Xintong
Xia, Zhaoyang
Chang, Aaron
Yu, Tong
Kim, Sungchul
Rossi, Ryan A.
Zhang, Ruiyi
Mitra, Subrata
Metaxas, Dimitris N.
Yao, Lina
Shang, Jingbo
McAuley, Julian
contents Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods that enable better alignment between visual encoders and backbone LLMs, concerning MLLM's visual grounding, object referring, and compositional reasoning abilities. In addition, we provide a summary of model training and in-context learning methods to improve MLLM's perception and understanding of visual prompts. This paper examines visual prompting methods developed in MLLMs and provides a vision of the future of these methods.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15310
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Visual Prompting in Multimodal Large Language Models: A Survey
Wu, Junda
Zhang, Zhehao
Xia, Yu
Li, Xintong
Xia, Zhaoyang
Chang, Aaron
Yu, Tong
Kim, Sungchul
Rossi, Ryan A.
Zhang, Ruiyi
Mitra, Subrata
Metaxas, Dimitris N.
Yao, Lina
Shang, Jingbo
McAuley, Julian
Machine Learning
Computer Vision and Pattern Recognition
Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods that enable better alignment between visual encoders and backbone LLMs, concerning MLLM's visual grounding, object referring, and compositional reasoning abilities. In addition, we provide a summary of model training and in-context learning methods to improve MLLM's perception and understanding of visual prompts. This paper examines visual prompting methods developed in MLLMs and provides a vision of the future of these methods.
title Visual Prompting in Multimodal Large Language Models: A Survey
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.15310