Changhun Lee
Postdoctoral Scientist, Columbia University & UNIST
cl4670@cumc.columbia.edu, changhun@unist.ac.kr
Bio
I am a postdoctoral research scientist at Columbia University. I received my Ph.D degree in Industrial Engineering, UNIST, and won the best researcher award for my thesis titled "Tackling Three Problems in Controlled Sequence Generations: Bridging Reinforcement Learning with Language Models.".
My research interest encompasses LLM, RL, Agentic AI, and their application in AI4Healthcare & AI4Business. Currently at Columbia University, I am conducting research on:
-
- How to design micro-coaching chatbot to support users' healthcare decision-making by orchestrating LLM agents seamlessly based on multi-agentic framework.
- How to optimize human-chatbot interaction under constraints such as the limited number of back-and-forth communication and the shortage of information.
- How to reinforce long-term memories of chatbot through a sequence of contextually-connected but technically-disconnected short-term interactions.
Publications
Most recent publications on Google Scholar.
‡ indicates equal contribution.
Towards Pareto-Efficient RLHF: Paying Attention to a Few High-Reward Samples with Reward Dropout
Changhun Lee, Chiehyeon Lim
Findings of the Association for Computational Linguistics: EMNLP 2024
Repurformer: Transformers for Repurposing-Aware Molecule Generation
Changhun Lee, Gyumin Lee
Language + Molecules @ ACL 2024 (Oral)
Recommendation in Offline Stores: A Gamification Approach for Learning the Spatiotemporal Representation of Indoor Shopping
Jongkyung Shin‡, Changhun Lee‡, Chiehyeon Lim, Yunmo Shin, Junseok Lim
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (Oral)
MIND dataset for diet planning and dietary healthcare with machine learning: Dataset creation using combinatorial optimization and controllable generation with domain experts
Changhun Lee‡, Soohyeok Kim‡, Sehwa Jeong, Jayun Kim, Yeji Kim, Chiehyeon Lim, Minyoung Jung
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021)
Diet Planning with Machine Learning: Teacher-forced REINFORCE for Composition Compliance with Nutrition Enhancement
Changhun Lee, Soohyeok Kim, Chiehyeon Lim, Jayun Kim, Yeji Kim, Minyoung Jung
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
From technological development to social advance: A review of Industry 4.0 through machine learning
Changhun Lee, Chiehyeon Lim
Technological Forecasting and Social Change, 167, 120653.
Repurformer: Transformers for Repurposing-Aware Molecule Generation
Changhun Lee, Gyumin Lee
Language + Molecules @ ACL 2024 (Oral)
Recommendation in Offline Stores: A Gamification Approach for Learning the Spatiotemporal Representation of Indoor Shopping
Jongkyung Shin‡, Changhun Lee‡, Chiehyeon Lim, Yunmo Shin, Junseok Lim
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (Oral)
Challenges of Diet Planning for Children using Artificial Intelligence
Changhun Lee‡, Soohyeok Kim, Jayun Kim, Chiehyeon Lim, Minyoung Jung
Nutrition Research and Practice. 2022; 16.
MIND dataset for diet planning and dietary healthcare with machine learning: Dataset creation using combinatorial optimization and controllable generation with domain experts
Changhun Lee‡, Soohyeok Kim‡, Sehwa Jeong, Jayun Kim, Yeji Kim, Chiehyeon Lim, Minyoung Jung
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021)
Diet Planning with Machine Learning: Teacher-forced REINFORCE for Composition Compliance with Nutrition Enhancement
Changhun Lee, Soohyeok Kim, Chiehyeon Lim, Jayun Kim, Yeji Kim, Minyoung Jung
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
Human dietitians vs. Artificial intelligence: Which diet design do you prefer for your children?
Min Jung, Chiehyeon Lim, Changhun Lee, Soohyeok Kim, Jayun Kim
Journal of Allergy and Clinical Immunology, 147(2), AB117.
Towards Pareto-Efficient RLHF: Paying Attention to a Few High-Reward Samples with Reward Dropout
Changhun Lee, Chiehyeon Lim
Findings of the Association for Computational Linguistics: EMNLP 2024
Repurformer: Transformers for Repurposing-Aware Molecule Generation
Changhun Lee, Gyumin Lee
Language + Molecules @ ACL 2024 (Oral)
Towards Pareto-Efficient RLHF: Paying Attention to a Few High-Reward Samples with Reward Dropout
Changhun Lee, Chiehyeon Lim
Findings of the Association for Computational Linguistics: EMNLP 2024
Repurformer: Transformers for Repurposing-Aware Molecule Generation
Changhun Lee, Gyumin Lee
Language + Molecules @ ACL 2024 (Oral)
Recommendation in Offline Stores: A Gamification Approach for Learning the Spatiotemporal Representation of Indoor Shopping
Jongkyung Shin‡, Changhun Lee‡, Chiehyeon Lim, Yunmo Shin, Junseok Lim
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (Oral)
Challenges of Diet Planning for Children using Artificial Intelligence
Changhun Lee‡, Soohyeok Kim, Jayun Kim, Chiehyeon Lim, Minyoung Jung
Nutrition Research and Practice. 2022; 16.
MIND dataset for diet planning and dietary healthcare with machine learning: Dataset creation using combinatorial optimization and controllable generation with domain experts
Changhun Lee‡, Soohyeok Kim‡, Sehwa Jeong, Jayun Kim, Yeji Kim, Chiehyeon Lim, Minyoung Jung
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks 2021)
Diet Planning with Machine Learning: Teacher-forced REINFORCE for Composition Compliance with Nutrition Enhancement
Changhun Lee, Soohyeok Kim, Chiehyeon Lim, Jayun Kim, Yeji Kim, Minyoung Jung
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
From technological development to social advance: A review of Industry 4.0 through machine learning
Changhun Lee, Chiehyeon Lim
Technological Forecasting and Social Change, 167, 120653.
Human dietitians vs. Artificial intelligence: Which diet design do you prefer for your children?
Min Jung, Chiehyeon Lim, Changhun Lee, Soohyeok Kim, Jayun Kim
Journal of Allergy and Clinical Immunology, 147(2), AB117.
Co-work Opportunities
I am currently a postdoctoral research scientist at Columbia University, living in New York City and looking for opportunities to collaborate in the fields of AI/ML, NLP, and RL. I am also open to AI4Health/AI4Business reserach. If you are interested, please feel free to contact me at cl4670@cumc.columbia.edu or changhun@unist.ac.kr.
Vitæ
You can download my CV here in PDF format.
Acknowledgement
This website uses the website design and template by Martin Saveski