Scholar
Jihwan Jeong
Google Scholar ID: XvKkcC4AAAAJ
Google Research
Citations & Impact
Citations
1,023
H-index
7
i10-index
7
Publications
20
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- 1. Published a paper at ICLR-23 exploring the use of Bayesian models for robust planning and policy learning.
- 2. First-authored a paper during his internship at Google Research, highlighting the effective fine-tuning of LLMs for accurate and personalized recommendations.
- 3. Involved in multiple model-based offline reinforcement learning projects.
Research Experience
- 1. Student Research Program, Google Research (June 2023 - Present): Contributed to the submission of two papers, applying RLAIF to advance language models for personalized recommendations and significantly contributed to the development of the PAX pipeline.
- 2. Research Intern, Vector Institute (June 2022 - September 2022): Worked with Professor Pascal Poupart on a model-based offline reinforcement learning project (under review).
- 3. Research Intern, LG AI Research (June 2021 - October 2021): Worked on a model-based offline reinforcement learning project (ICLR-23).
- 4. Ph.D. Candidate, University of Toronto (September 2019 - Present): Research focuses on leveraging learned models for enhanced decision-making.
Education
- 1. Ph.D. Candidate in Information Engineering, University of Toronto (Advisor: Scott Sanner)
- 2. M.S. in Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), 2019
- 3. B.S. in Chemistry, Korea Advanced Institute of Science and Technology (KAIST), 2015
Background
- Ph.D. candidate at the University of Toronto, actively contributing to the D3M (Data-Driven Decision-making) lab under the mentorship of Professor Scott Sanner. His interest in AI and ML is rooted in their potential to revolutionize decision-making, particularly in offline model-based reinforcement learning.
Miscellany
- Interests include offline & model-based reinforcement learning, uncertainty quantification in neural networks, RL for Large Language Models, and decision-aware model learning.
