서브메뉴
검색
Having Personalized, Situated, and Grounded Conversations With Human, Like Human
Having Personalized, Situated, and Grounded Conversations With Human, Like Human
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105241
- ISBN
- 9798291569290
- DDC
- 004
- 저자명
- Bao, Yuwei.
- 서명/저자
- Having Personalized, Situated, and Grounded Conversations With Human, Like Human
- 발행사항
- [Sl] : University of Michigan, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 131 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
- 주기사항
- Advisor: Chai, Joyce.
- 학위논문주기
- Thesis (Ph.D.)--University of Michigan, 2025.
- 초록/해제
- 요약Language is a powerful abstraction and adaptive tool that enables humans to communicate efficiently across diverse environments, audiences, and multisensory experiences. Learning language involves encoding the noisy, sensory rich world into compact abstract representations, while using language requires decoding those representations back into multisensory experiences, flexibly combining learned knowledge to express intentions, and adapting communication based on context and audience. Despite recent advances, AI still struggles with language acquisition that is truly grounded in the multimodal world, efficient for lifelong learning, and adaptable to different situations and individuals-capabilities that are central to natural communication.This dissertation centers on developing AI systems inspired by human cognition and behavior to support more grounded, situated, and personalized language interactions. By studying language used in real-world, situated settings, I identify persistent challenges that current foundational models still struggle to overcome. From there, I will introduce our model development efforts aimed at facilitating personalized communication by addressing the speaker-listener disparity, and enabling proactive intervention through an understanding of temporal dynamics and timing. Finally, inspired by early human language acquisition, I will present a framework to tackle two key challenges: multimodal grounding and developmental learning. This spans from word acquisition in synthetic environment to learning sentence structure and grounding in more realistic, single-pass multimodal inputs. By integrating perception, continual learning, situated and personalized adaptations, my work bridge the gap between human and AI communication, bringing AI closer to the natural, adaptable, and context-aware reasoning that characterizes human language communication.
- 일반주제명
- Computer science
- 일반주제명
- Developmental psychology
- 일반주제명
- Cognitive psychology
- 기타저자
- University of Michigan Computer Science & Engineering
- 기본자료저록
- Dissertations Abstracts International. 87-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359958
■00520260202105241
■006m o d
■007cr#unu||||||||
■020 ▼a9798291569290
■035 ▼a(MiAaPQ)AAI32272004
■035 ▼a(MiAaPQ)umichrackham006522
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aBao, Yuwei.
■24510▼aHaving Personalized, Situated, and Grounded Conversations With Human, Like Human
■260 ▼a[Sl]▼bUniversity of Michigan▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a131 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: B.
■500 ▼aAdvisor: Chai, Joyce.
■5021 ▼aThesis (Ph.D.)--University of Michigan, 2025.
■520 ▼aLanguage is a powerful abstraction and adaptive tool that enables humans to communicate efficiently across diverse environments, audiences, and multisensory experiences. Learning language involves encoding the noisy, sensory rich world into compact abstract representations, while using language requires decoding those representations back into multisensory experiences, flexibly combining learned knowledge to express intentions, and adapting communication based on context and audience. Despite recent advances, AI still struggles with language acquisition that is truly grounded in the multimodal world, efficient for lifelong learning, and adaptable to different situations and individuals-capabilities that are central to natural communication.This dissertation centers on developing AI systems inspired by human cognition and behavior to support more grounded, situated, and personalized language interactions. By studying language used in real-world, situated settings, I identify persistent challenges that current foundational models still struggle to overcome. From there, I will introduce our model development efforts aimed at facilitating personalized communication by addressing the speaker-listener disparity, and enabling proactive intervention through an understanding of temporal dynamics and timing. Finally, inspired by early human language acquisition, I will present a framework to tackle two key challenges: multimodal grounding and developmental learning. This spans from word acquisition in synthetic environment to learning sentence structure and grounding in more realistic, single-pass multimodal inputs. By integrating perception, continual learning, situated and personalized adaptations, my work bridge the gap between human and AI communication, bringing AI closer to the natural, adaptable, and context-aware reasoning that characterizes human language communication.
■590 ▼aSchool code: 0127.
■650 4▼aComputer science
■650 4▼aDevelopmental psychology
■650 4▼aCognitive psychology
■653 ▼aMultimodal grounding
■653 ▼aDevelopmental learning
■653 ▼aPersonalized situated communication
■653 ▼aCognitive inspired learning
■653 ▼aLanguage acquisition
■690 ▼a0984
■690 ▼a0800
■690 ▼a0620
■690 ▼a0633
■71020▼aUniversity of Michigan▼bComputer Science & Engineering.
■7730 ▼tDissertations Abstracts International▼g87-03B.
■790 ▼a0127
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359958▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
