Seohui Bae

I'm a research scientist at LG AI Research in South Korea.

At LG AI Research, I've worked on reasoning, out-of-distribution extrapolation, and neural functionals. I completed my bachelor's and master's studies at KAIST, where I was fortunate to be advised by Prof. Eunho Yang.

Email  /  Google Scholar  /  LinkedIn

News

• I will be attending ICML 2025 this July. See you in Vancouver 🇨🇦

Research

I work at the intersection of reasoning, adaptation, and learning under distribution shifts. My research interests include the following topics:

• Online RL for Vision/Language Agents and Exploratory Decision Making in Embodied Environments
• Align as Act: Innovation-Based Policy Optimization for LLM Agents
• Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agents
• Model-based RL and Multimodal Forecasting under Distribution Shifts
• Language-Agent Forecasting with World-Model Surrogates under Delayed Feedback
• Adaptive Information Routing for Multimodal Time Series Forecasting
• Robust Generalization under Distribution Shifts
• Geometry-Aware Normalization for Imbalanced Time-series Forecasting
• ShERPA: Shifting basin for Enhanced Robustness via Permuted Activations
• Gradient Surgery for One-shot Unlearning on Generative Model
• GTA: Graph Truncated Attention for Retrosynthesis

I regularly contribute to academic publications and collaborative research projects. I’m especially interested in bridging industrial challenges with generalizable solutions in: inference-time scaling, long-tail generalization, and extrapolation

Interests

• reasoning, RL & optimization
• causal forecasting & out-of-distribution generalization
• large-model systems & inference-time efficiency

Education

• M.S. in Artificial Intelligence, Mar 2020-Feb 2022
  Korea Advanced Institute of Science and Technology (KAIST)
• B.S. in Biological Science, Computer Science (minor), Mar 2015-Feb 2020
  Korea Advanced Institute of Science and Technology (KAIST)
• Korea Science of Academy of KAIST, Mar 2012-Feb 2015

Selected Publications

keyword: epistemic exploration, language model agent, test-time adaptation

keyword: forecasting, language agent, world-model surrogate

keyword: time-series, heavy-tail distribution, normalization

Projects

LG AI Research

• EXAONE-Futurecast
• Demand Forecasting

Ongoing Research

• Online Rule Learning in Vision–Language Agents: continually turns implicit interaction rules into actionable policies.
• Decision Tree-Based Model Adaptation: using symbolic structure to guide low-cost adaptation of pretrained agents.

Education

M.S. in Graduate School of Artificial Intelligence, Mar 2020–Feb 2022

• Korea Advanced Institute of Science and Technology (KAIST)
• Machine Learning and Intelligence Lab
• Advisor: Eunho Yang

B.S. in Biological Science, Computer Science (minor), Mar 2015–Feb 2020

• Korea Advanced Institute of Science and Technology (KAIST)

Korea Science Academy of KAIST, Mar 2012–Feb 2015

Academic Service

Conference / Journal Reviewer

• Conferences: NeurIPS[24-26], ICLR[26], AAAI[26], AISTATS[25-26]
• Workshops / Shorts: AAAI[23], ICLR[24], ICML[23]
• Journals: ACM Computing Surveys[24]

Last date of update: 2025-10-05 / template