Yoonseok Yeom
Seoul, South Korea
I am an AI Researcher / AI Engineer at LG CNS, where I have been part of the Agentic AI Business Team since January 2026. I conduct AI research across academia and industry and build agentic AI products, including general-purpose prebuilt agents and MCP tools.
I completed my M.S. in Data Science at Seoul National University (Feb 2026) in the Causality Lab under the supervision of Prof. Sanghack Lee. My research focused on Causal AI, including causal inference using causal generative models for time-series data, scalable causal discovery, and causal discovery informed by prior knowledge from LLMs. Much of this work was conducted in collaboration with LG AI Research. I previously received a B.S. in Engineering from Korea University (Feb 2024), majoring in Biomedical Engineering and completing an interdisciplinary major in Artificial Intelligence.
Research
Time-Series Causal Normalizing Flows
UAI 2026
A framework that extends causal normalizing flows to time-series, enabling simulation-based interventional density estimation over time.
Breaking Bad: Component-Wise Parent Deletion
UAI 2026
A novel, simple, yet powerful operator for score-based causal discovery, which is theoretically sound and compatible with existing score-based methods.
LLM Priors for Causal Discovery
IEEE Access
A framework that integrates LLM-based causal reasoning into data-driven causal discovery, resulting in improved and robust performance.
Projects
Meta-Reviewer Helper
2024.09 – 2024.12
An LLM-based framework that generates meta-reviews of academic papers — summarizing reviews, reviewer disagreements, and author–reviewer discussions.