Jooyeon Kim
· 2020: Ph.D., KAIST, School of Computing
· 2016: M.S., KAIST, School of Computing
· 2014: B.S., The University of Tokyo, Systems Innovations
· 2021~2023: Postdoctoral researcher, RIKEN AIP
· 2020~2021: Researcher, Microsoft Research Cambridge (MSR)
· 2019: Naver Ph.D. fellowship (2019)
· 2009~2014: The Korea-Japan joint government scholarship program
Interacitve Machine Intelligence
우리는 대화형 및 자율 학습 경험에서 인간과 같은 기계 지능을 도출하기 위해 노력합니다. 우리는 기계 지능이 딥 러닝 모델 및 프레임워크와 함께 보이지 않는 데이터/환경에 적응하고 일반화할 수 있는 원칙적인 방법을 제공하는 베이지안 학습의 장점을 활용/발견하는 데 중점을 둡니다. 우리는 인간과 기계(AI 에이전트)가 언어 및 비언어적 의사 소통 신호를 통해 협력하고 조정하는 대화형 시스템을 구축하고 촉진하는 데 중점을 둡니다. 이러한 대화형 시스템의 멀티모달적 특성 때문에 우리는 생성 모델링, 자연 언어 처리(NLP), 데이터 마이닝, 인간-컴퓨터 상호 작용(HCI) 및 최적화를 포함한 연구 영역을 다양하게 커버합니다.
We strive to derive human-like machine intelligence from interactive and autonomous learning experiences. We focus on exploiting/uncovering the merits of Bayesian learning that provides a principled way of allowing machine intelligence to adapt and generalize to unseen data/environments in conjunction with deep learning models and frameworks. We focus on building and promoting interactive systems within which humans and machines (AI agents) collaborate, cooperate, and coordinate through verbal and non-verbal communicative signals. The multi-modal nature of such interactive systems leads our research trajectory to revolve around the research areas including generative modeling, natural language processing (NLP), data mining, human-computer interaction (HCI), and optimization.
We strive to derive human-like machine intelligence from interactive and autonomous learning experiences. We focus on exploiting/uncovering the merits of Bayesian learning that provides a principled way of allowing machine intelligence to adapt and generalize to unseen data/environments in conjunction with deep learning models and frameworks. We focus on building and promoting interactive systems within which humans and machines (AI agents) collaborate, cooperate, and coordinate through verbal and non-verbal communicative signals. The multi-modal nature of such interactive systems leads our research trajectory to revolve around the research areas including generative modeling, natural language processing (NLP), data mining, human-computer interaction (HCI), and optimization.
Generative modeling, Multi-agent RL, model-based RL, collaboration, cooperation, Bayesian machine learning, natural language processing, HCI, data min
Generative modeling, Multi-agent RL, model-based RL, collaboration, cooperation, Bayesian machine learning, natural language processing, HCI, data min
Generative modeling, Multi-agent RL, model-based RL, collaboration, cooperation, Bayesian machine learning, natural language processing, HCI, data min
Generative modeling, Multi-agent RL, model-based RL, collaboration, cooperation, Bayesian machine learning, natural language processing, HCI, data min
Generative modeling, Multi-agent RL, model-based RL, collaboration, cooperation, Bayesian machine learning, natural language processing, HCI, data mining, Graph neural networks, recommender systems, fake news
Generative modeling, Multi-agent RL, model-based RL, collaboration, cooperation, Bayesian machine learning, natural language processing, HCI, data min
국가과학기술표준분류
EE. 정보/통신 > EE01. 정보이론 > EE0108. 인공지능
· NeurIPS. Emergent communication under varying sizes and connectivities. Jooyeon Kim and Alice Oh, 2020
· KDD. CoRGi: Content-Rich Graph Neural Networks with Attention. Jooyeon Kim et al., 2020
· WSDM. Leveraging the crowd to detect and reduce the spread of fake news and misinformation. Jooyeon Kim et al., 2018