Ju-Seung Byun

Postdoc, LG Corporation

Joined

May 2021

Names

Ju-Seung Byun (Preferred)

JU-SEUNG BYUN

Emails

****@osu.edu (Confirmed)

****@gmail.com (Confirmed)

****@lgresearch.ai (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Postdoc

LG Corporation (lgresearch.ai)

2025 – 2026

PhD student

Ohio State University (osu.edu)

2019 – 2024

Intern

Google (google.com)

2022 – 2022

MS student

University of Southern California (usc.edu)

2017 – 2019

Undergrad student

Inha University (inha.edu)

2010 – 2017

Advisors, Relations & Conflicts

PhD Advisor

Andrew Perrault

2021 – 2024

Expertise

Agentic AI

2025 – Present

Reinforcement Learning

2018 – Present

Publications

Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback
Jingyi Chen, Ju-Seung Byun, Micha Elsner, Pichao WANG, Andrew Perrault
- SpeechAI TTIC 2025 OralorPoster
- Readers: Everyone
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
Ju-Seung Byun, Andrew Perrault
- ICML 2025 poster
- Readers: Everyone
DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Models
Jingyi Chen, Ju-Seung Byun, Micha Elsner, Andrew Perrault
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
Ju-Seung Byun, Andrew Perrault
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Normality-Guided Distributional Reinforcement Learning for Continuous Control
Ju-Seung Byun, Andrew Perrault
- Accepted by TMLR
- Readers: Everyone
Training Transition Policies via Distribution Matching for Complex Tasks
Ju-Seung Byun, Andrew Perrault
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- ICLR 2022
- Readers: Everyone
Normality-Guided Distributional Reinforcement Learning for Continuous Control
Ju-Seung Byun, Andrew Perrault
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- CoRR 2022
- Readers: Everyone
Training Transition Policies via Distribution Matching for Complex Tasks
JU-SEUNG BYUN, Andrew Perrault
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 Poster
- Readers: Everyone
Training Transition Policies via Distribution Matching for Complex Tasks
Ju-Seung Byun, Andrew Perrault
- 2021 (modified: 03 Mar 2022)
- CoRR 2021
- Readers: Everyone
Proximal Policy Gradient: PPO with Policy Gradient
Ju-Seung Byun, Byungmoon Kim, Huamin Wang
- Published: 01 Jan 2020, Last Modified: 12 May 2023
- CoRR 2020
- Readers: Everyone