Taehyun Cho

I am a PhD student at the Cognitive Machine Learning Laboratory, part of the Department of Electrical and Computer Engineering at Seoul National University. My PhD advisor is Jungwoo Lee. I have a BS in Mathematics from Korea University.

E-mail: talium@cml.snu.ac.kr

GitHub  /  Google Scholar  /  LinkedIn  /  CV

Research Interest

My academic research centers on sequential decision-making under uncertainty, particularly in the context of human feedback. I have extensively studied distributional reinforcement learning (distRL), reinforcement learning from human feedback (RLHF), and regret analysis, aiming to bridge theory and practice. Inspired by how humans make decisions, I seek to mathematically model and optimize human-in-the-loop systems, uncovering both theoretical insights and practical algorithms for robust decision-making. I’m currently interested in reasoning LLM agents and regret-based decision theory.
I’m seeking postdoctoral opportunities in theoretical foundations of reinforcement learning or reasoning-oriented LLM research.

Preprints

An Axiomatization of Process Score Model: Your Process-level Feedback is Not a Reward

Off-policy Direct Preference Optimization with Monotonic Improvement Guarantee

Policy Optimization with Process Regret Model

International Conference

Policy-labeled Preference Learning: Is Preference Enough for RLHF?

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees

Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

On the Convergence of Continual Learning with Adaptive Methods

Adaptive Methods for Nonconvex Continual Learning

Perturbed Quantile Regression for Distributional Reinforcement Learning

Chebyshev polynomial codes: Task entanglement-based coding for distributed matrix multiplication

International Journal

Optimized shallow neural networks for sum-rate maximization in energy harvesting downlink multiuser NOMA systems

An Efficient Neural Network Architecture for Rate Maximization in Energy Harvesting Downlink Channels

Design and source code from Jon Barron's website