AI Research team @Riiid (I am on the LHS).
Seunghyun Lee
I am a research scientist @Riiid working on various AI-powered modules for developing efficient and/or creative learning environments.
Prior to joining Riiid, I completed my Master's degree @ALIN lab, under the supervision of Jinwoo Shin. Even before that, I received my Bachelor's degree in Mathematical Sciences @KAIST.
Contact: seunghyun [dot] lee [at] riiid [dot] co
Work Experience
Senior Research Scientist (AI Team Lead)
Riiid (2021.08 ~)
(Current) Speech Synthesis & Voice Conversion
Multi-lingual TTS model capable of synthesizing code-mixed speech
Expressive/Conversational TTS
Efficient deployment of TTS and VC models
Other projects I worked on and frequently go back to:
Subject-driven Image Generation
Speech Assessment
LLM-based Tutoring
Transcript-based video clip Retrieval System
Knowledge Tracing (KT), Computerized Adaptive Testing (CAT)
Internship
Algorithmic Intelligence Laboratory (2018.09 ~ 2019.08)
I developed Korean Computer Scientist Search (KCSS) during my undergraduate internship at ALIN lab, with Junho Han and Jinwoo Shin.
Publications
(C: conference / W: workshop / J: journal / P: preprint) (* equal contribution)
2024
[C7] BIPED: Pedagogically Informed Tutoring System for ESL Education
Soonwoo Kwon*, Sojung Kim*, Minju Park, Seunghyun Lee, Kyuseok Kim
Annual Meeting of the Association for Computational Linguistics (ACL) 2024
[W2] Empowering Personalized Learning through a Conversation-based Tutoring System with Student Modeling [pdf]
Minju Park, Sojung Kim, Seunghyun Lee, Soonwoo Kwon, Kyuseok Kim
Conference on Human Factors in Computing Systems (CHI) Late-Breaking Work 2024
2023
[C6] Addressing Negative Transfer in Diffusion Models [pdf]
Hyojun Go*, JinYoung Kim*, Yunsung Lee*, Seunghyun Lee*, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi
Conference on Neural Information Processing (NeurIPS) 2023
[C5] Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach [pdf]
Soonwoo Kwon*, Sojung Kim*, Seunghyun Lee, Jin-Young Kim, Suyeong An, Kyuseok Kim
Conference on Information and Knowledge Management (CIKM) 2023
[C4] Towards Practical Plug-and-Play Diffusion Models [pdf] [code]
Hyojun Go*, Yunsung Lee*, Jin-Young Kim*, Seunghyun Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi
Conference on Computer Vision and Pattern Recognition (CVPR) 2023
2022
[C3] Evaluating the Knowledge Depencency of Questions [pdf]
Hyeongdon Moon*, Yoonseok Yang*, Jamin Shin*, Hangyeol Yu, Seunghyun Lee, Myeongho Jeong, Juneyoung Park, Minsam Kim, Seungtaek Choi
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2022
2021
[C2, W1] Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble [pdf] [code]
Seunghyun Lee*, Younggyo Seo*, Kimin Lee, Pieter Abbeel, and Jinwoo Shin
Conference on Robot Learning (CoRL) 2021
Previous version [pdf] was presented at NeurIPS Workshop on Offline RL 2020 (Oral Presentation) & NeurIPS Workshop on Deep RL 2020
2020
[C1] Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning [pdf] [code] [site]
Kimin Lee*, Younggyo Seo*, Seunghyun Lee, Honglak Lee, and Jinwoo Shin
Education
M.S. in Artificial Intelligence, KAIST, Daejeon, Korea (2021)
B.S. in Mathematical Sciences (summa cum laude), KAIST, Daejeon, Korea (2019)
Rangitoto College, Auckland, New Zealand (2012)
Teaching
TA, AI602 Advanced Deep Learning, Spring 2021, KAIST
TA, GCT634/AI613 Musical Applications of Machine Learning, Fall 2020, KAIST
TA, AI605 Deep Learning for Natural Language Processing, Spring 2020, KAIST
TA, AI602 Advanced Deep Learning, Fall 2019, KAIST
TA, HSS436 Philosophy of Mind, Spring 2015, KAIST
Academic Services
I served as a reviewer for ICML2021.