7 papers
Controlled Evaluation of EEG Foundation Models: Random Initialisation, Band-Power and Validation-Selected Probes
Mingyu Jeon, Suwan Cho, Jae Young Suh
EEG foundation models report downstream gains, yet their protocols seldom include three controls. These are the same encoder untrained, spectral features fitted on the same data, a…
A JEPA Recipe for Tabular Foundation Models
Mingyu Jeon, Suwan Cho, Jae Young Suh
Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeCun, 2022; Assran et al., 202…
LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents
Mingyu Jeon, Bokyeong Kim, Suwan Cho +2
Reviewing nuclear regulatory documents requires multi-hop reasoning across tens of thousands of pages, where judgments depend on evidence assembled across multiple chapters. We fra…
PPoGA: Predictive Plan-on-Graph with Action for Knowledge Graph Question Answering
MinGyu Jeon, SuWan Cho, JaeYoung Shu
Large Language Models (LLMs) augmented with Knowledge Graphs (KGs) have advanced complex question answering, yet they often remain susceptible to failure when their initial high-le…
Schema Matching on Graph: Iterative Graph Exploration for Efficient and Explainable Data Integration
Mingyu Jeon, Jaeyoung Suh, Suwan Cho
Schema matching is a critical task in data integration, particularly in the medical domain where disparate Electronic Health Record (EHR) systems must be aligned to standard models…
DELTA: Language Diffusion-based EEG-to-Text Architecture
Mingyu Jeon, Hyobin Kim
Electroencephalogram (EEG)-to-text remains challenging due to high-dimensional noise, subject variability, and error accumulation in autoregressive decoding. We introduce DELTA, wh…
How Far Can LLMs Emulate Human Behavior?: A Strategic Analysis via the Buy-and-Sell Negotiation Game
Mingyu Jeon, Jaeyoung Suh, Suwan Cho +1
With the rapid advancement of Large Language Models (LLMs), recent studies have drawn attention to their potential for handling not only simple question-answer tasks but also more…