BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023302Z
LOCATION:G502\, G Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T132000
DTEND;TZID=Asia/Tokyo:20241205T134000
UID:siggraphasia_SIGGRAPH Asia 2024_sess295_edu_131@linklings.com
SUMMARY:Embodied AI-Guided Interactive Digital Teacher for Education
DESCRIPTION:Educator's Forum\n\nZhuoran Zhao, Zhizhuo Yin, Jia Sun, and Pa
 n Hui (Hong Kong University of Science and Technology, Guangzhou)\n\nTradi
 tional education is considered incapable of providing prompt feedback, fac
 ilitating proactive learning, and giving indiscriminate responses. This ha
 s been observed in both in-person classes and online courses, especially w
 hen students' questions fall outside the instructors' knowledge base or ar
 e considered trivial by instructors. Nowadays, the advent of large languag
 e models (LLMs) has revolutionized knowledge acquisition. The LLM-based ch
 atbots enable fast learning through interactive question-answering, which 
 serves as an effective supplement to traditional educational approaches an
 d even shows potential for replacement. To utilize such advancements in ed
 ucation, we propose MAGI, a novel system providing Embodied AI-Guided Inte
 ractive digital teachers for education, which integrates LLM-based chatbot
  technology. To ensure MAGI generates answers without hallucination, we em
 ploy a novel retrieval-augmented generation (RAG) paradigm to organize and
  retrieve useful educational documents for the LLM. Moreover, we create an
 imatable 3D avatars powered by text-to-speech and audio-to-motion models t
 o provide students with interactive conversation experiences. We highlight
  the possibility of MAGI to enhance education accessibility and improve th
 e overall learning experience.\n\nRegistration Category: Enhanced Access, 
 Full Access, Full Access Supporter\n\nLanguage Format: English Language\n\
 nSession Chair: xuejun xuan (China Academy of Art, School of Animation and
  Games)
URL:https://asia.siggraph.org/2024/program/?id=edu_131&sess=sess295
END:VEVENT
END:VCALENDAR