PhD student, Korea University (korea.ac.kr), 2024 – Present. Researcher, Kakao Brain (kakaobrain.com), 2020 – Present. MS student, Hanyang University.

AI Researcher at kakao brain · 경력: 카카오브레인 - kakaobrain · 학력: 한양대학교 · 지역: 서울 인천 지역 · LinkedIn의 1촌 286명. LinkedIn에서 Daejin Jo님 ...

Reinforcement Learning from Human Feedback (RLHF) leverages human preference data to train language models to align more closely with human essence.

Daejin Jo | IEEE Xplore Author Details. Daejin Jo. Affiliation. Kakao Brain, Seongnam, South Korea. Publication Topics. Additional Tasks,Autoregressive Model ...

Daejin Jo's 9 research works with 12 citations, including: TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback.

View the profiles of professionals named "Daejin Jo" on LinkedIn. There are 3 professionals named "Daejin Jo", who use LinkedIn to exchange information, ...

Daejin Jo has work experience as an AI Researcher at kakaobrain since December 2020. Prior to that, they worked as an AI Researcher at NCSOFT from September ...

Papers by DaeJin Jo with links to code and results.

daejin jo & martin.git twidddj. Follow · 13 followers · 3 following · @kakaobrain. Seoul, Korea. Achievements · Achievement: Starstruck · Achievements.

hanbum.ko95@gmail.com. GitHub. Eunbi Yoon. yon6286@gmail.com. Yuheon Song. yuheone@gmail.com. GitHub. Daejin Jo. twidddj@gmail.com. GitHub · LinkedIn. Master S ...