Same Data, More Learning: Curriculum RL and Supervised Guidance for GUI Grounding
EACL 2027 (Findings)
Ju-Seung Byun
I am an Applied Researcher at Capital One AI Foundations. Previously, I was a Postdoctoral Researcher in the Advanced Agent Lab at LG AI Research, working with Prof. Honglak Lee. I received my Ph.D. in Computer Science and Engineering from The Ohio State University, advised by Prof. Andrew Perrault.
My research interests are in deep reinforcement learning with a focus on computer use agents.
Before my Ph.D., I earned my Master’s degree from the University of Southern California (2019) and my Bachelor’s degree from Inha University (2017) in South Korea, both in Computer Science.
Publications
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
Normality-Guided Distributional Reinforcement Learning for Continuous Control
Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback
Interspeech 2025 (Oral)Paper
SalsaBot: Towards a Robust and Generalizable Embodied Agent
Embodied AI Workshop at CVPR 2023Paper (Short)
Alexa Prize SimBot Challenge Proceedings 2023Paper (Long)
Training Transition Policies via Distribution Matching for Complex Tasks
* Equal contribution.