Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pei, Jiahuan, Viola, Irene, Huang, Haochen, Wang, Junxiao, Ahsan, Moonisa, Ye, Fanghua, Yiming, Jiang, Sai, Yao, Wang, Di, Chen, Zhumin, Ren, Pengjie, Cesar, Pablo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910474209067008
author Pei, Jiahuan
Viola, Irene
Huang, Haochen
Wang, Junxiao
Ahsan, Moonisa
Ye, Fanghua
Yiming, Jiang
Sai, Yao
Wang, Di
Chen, Zhumin
Ren, Pengjie
Cesar, Pablo
author_facet Pei, Jiahuan
Viola, Irene
Huang, Haochen
Wang, Junxiao
Ahsan, Moonisa
Ye, Fanghua
Yiming, Jiang
Sai, Yao
Wang, Di
Chen, Zhumin
Ren, Pengjie
Cesar, Pablo
contents Autonomous artificial intelligence (AI) agents have emerged as promising protocols for automatically understanding the language-based environment, particularly with the exponential development of large language models (LLMs). However, a fine-grained, comprehensive understanding of multimodal environments remains under-explored. This work designs an autonomous workflow tailored for integrating AI agents seamlessly into extended reality (XR) applications for fine-grained training. We present a demonstration of a multimodal fine-grained training assistant for LEGO brick assembly in a pilot XR environment. Specifically, we design a cerebral language agent that integrates LLM with memory, planning, and interaction with XR tools and a vision-language agent, enabling agents to decide their actions based on past experiences. Furthermore, we introduce LEGO-MRTA, a multimodal fine-grained assembly dialogue dataset synthesized automatically in the workflow served by a commercial LLM. This dataset comprises multimodal instruction manuals, conversations, XR responses, and vision question answering. Last, we present several prevailing open-resource LLMs as benchmarks, assessing their performance with and without fine-tuning on the proposed dataset. We anticipate that the broader impact of this workflow will advance the development of smarter assistants for seamless user interaction in XR environments, fostering research in both AI and HCI communities.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13034
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality
Pei, Jiahuan
Viola, Irene
Huang, Haochen
Wang, Junxiao
Ahsan, Moonisa
Ye, Fanghua
Yiming, Jiang
Sai, Yao
Wang, Di
Chen, Zhumin
Ren, Pengjie
Cesar, Pablo
Computation and Language
Artificial Intelligence
Human-Computer Interaction
Autonomous artificial intelligence (AI) agents have emerged as promising protocols for automatically understanding the language-based environment, particularly with the exponential development of large language models (LLMs). However, a fine-grained, comprehensive understanding of multimodal environments remains under-explored. This work designs an autonomous workflow tailored for integrating AI agents seamlessly into extended reality (XR) applications for fine-grained training. We present a demonstration of a multimodal fine-grained training assistant for LEGO brick assembly in a pilot XR environment. Specifically, we design a cerebral language agent that integrates LLM with memory, planning, and interaction with XR tools and a vision-language agent, enabling agents to decide their actions based on past experiences. Furthermore, we introduce LEGO-MRTA, a multimodal fine-grained assembly dialogue dataset synthesized automatically in the workflow served by a commercial LLM. This dataset comprises multimodal instruction manuals, conversations, XR responses, and vision question answering. Last, we present several prevailing open-resource LLMs as benchmarks, assessing their performance with and without fine-tuning on the proposed dataset. We anticipate that the broader impact of this workflow will advance the development of smarter assistants for seamless user interaction in XR environments, fostering research in both AI and HCI communities.
title Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2405.13034