跳到主要导航 跳到搜索 跳到主要内容

Learning Personalized Agent for Real-Time Face-to-Face Interaction in VR

  • Beijing Institute of Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Interactive agents in virtual reality (VR) are anticipated to make decisions and provide feedback based on the user's inputs. Despite recent advancements in large language models (LLMs), employing LLMs in real-time face-to-face interactions decision-making, and delivering personalized feedback in VR remains challenging. To address this, our proposed system involves generating and labeling symbolic data, pre-training a real-time network, collecting personalized data, and fine-tuning the network. Utilizing inputs such as interaction distances, head orientations, and hand poses, the agents can provide personalized feedback. User experiments show significant advantages in both pragmatic and hedonic aspects over LLM-based agents, suggesting potential applications across diverse interactive domains.

源语言英语
主期刊名Proceedings - 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2024
出版商Institute of Electrical and Electronics Engineers Inc.
页759-760
页数2
ISBN(电子版)9798350374490
DOI
出版状态已出版 - 2024
活动2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2024 - Orlando, 美国
期限: 16 3月 2024 → 21 3月 2024

丛书

姓名Proceedings - 2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2024

会议

会议2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2024
国家/地区美国
市Orlando
时期16/03/24 → 21/03/24

学术指纹

探究 'Learning Personalized Agent for Real-Time Face-to-Face Interaction in VR' 的科研主题。它们共同构成独一无二的学术指纹。

引用此