7 papers
RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation
Juhyeon Lee, Wonduk Seo, Junseo Koh +3
Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most existing methods rely mainly…
Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
Wonduk Seo, Wonseok Choi, Junseo Koh +7
Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured…
MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
Wonduk Seo, Juhyeon Lee, Junseo Koh +6
Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as…
Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models
Megha Thukral, Cyrus Tanade, Simon A. Lee +10
Wearable foundation models have the potential to transform digital health by learning transferable representations from large-scale biosignals collected in everyday settings. While…
SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science
Wonduk Seo, Juhyeon Lee, Yanjun Shao +3
Large Language Models (LLMs) have enabled dynamic reasoning in automated data analytics, yet recent multi-agent systems remain limited by rigid, single-path workflows that restrict…
HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series
Simon A. Lee, Cyrus Tanade, Hao Zhou +13
Wearable sensors provide abundant physiological time series, yet the principles governing their predictive utility remain unclear. We hypothesize that temporal resolution is a fund…