Si Jun Yang
Yonsei University · 情報科学
研究室紹介
Professor Si Jun Yang's research lab specializes in interdisciplinary data science and intelligent systems, focusing on large-scale health analytics, multimodal AI for historical and visual understanding, and advanced optical signal processing. The lab develops cutting-edge computational frameworks for real-world challenges—from modeling global obesity trends using massive population data to designing self-supervised tabular learning models and vision-language models for ancient scripts. It also explores fundamental photonic phenomena such as spatio-spectral coupling in fiber lasers, bridging physics and engineering innovation. The lab emphasizes data-driven solutions with strong societal impact, particularly in healthcare, digital humanities, and next-generation AI systems.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
13and lacks a granular and systematic analysis of its dynamics. We used 4,050 population-based studies with measured height and weight data on 232 million participants to assess the worldwide dynamics of obesity from 1980 to 2024. The rise in obesity decelerated in school-aged children and adolescents throughout the 1990s in many high-income countries, and subsequently plateaued in most at age-standardized prevalences spanning 20 percentage points, from 3-4% for girls in Japan, Denmark and France
Service discovery is a fundamental process in wireless networks, enabling devices to find and communicate with services dynamically, and is critical for the seamless operation of modern systems like 5G and IoT.This paper introduces PriSrv+, an advanced privacy and usability-enhanced service discovery protocol for modern wireless networks and resource-constrained environments.PriSrv+ builds upon PriSrv (NDSS'24), by addressing critical limitations in expressiveness, privacy, scalability, and effi
Tabular data forms the backbone of high-stakes decision systems in finance, healthcare, and beyond. Yet industrial tabular datasets are inherently difficult: high-dimensional, riddled with missing entries, and rarely labeled at scale. While foundation models have revolutionized vision and language, tabular learning still leans on handcrafted features and lacks a general self-supervised framework. We present MaskTab, a unified pre-training framework designed specifically for industrial-scale tabu
Spatio-spectral coupling in spatio-temporally mode-locked fiber laser: supplement
We experimentally and numerically reveal a spatio-spectral coupling (SSC) mechanism mediated by spatially dependent gain in the spatio-temporally mode-locked fiber laser. In experiment, the spectral tuning is observed to be accompanied by the change of the spatial mode content. To further elucidate this relation between the spectral and spatial properties of the three-dimensional (3D) dissipative soliton, gain spectrum and its field attract are theoretically analyzed. The underlying mechanism th
We experimentally and numerically reveal a spatio-spectral coupling (SSC) mechanism mediated by spatially dependent gain in the spatio-temporally mode-locked fiber laser. In experiment, the spectral tuning is observed to be accompanied by the change of the spatial mode content. To further elucidate this relation between the spectral and spatial properties of the three-dimensional (3D) dissipative soliton, gain spectrum and its field attract are theoretically analyzed. The underlying mechanism th
Spatio-spectral coupling in spatio-temporally mode-locked fiber laser: supplement
Vision Large Language Models (VLLMs) have achieved remarkable success in modern text-rich visual understanding. However, their perceptual robustness in the face of the continuous morphological evolution of historical writing systems remains largely unexplored. Existing ancient text datasets typically focus on isolated historical periods, failing to capture the systematic visual distribution shifts spanning thousands of years. To bridge this gap and empower Digital Humanities, we introduce Chroni
Spatio-spectral coupling in spatio-temporally mode-locked fiber laser: supplement
BACKGROUND: While physical activity (PA) has protective effects in mitigating dementia progression among individuals with mild cognitive impairment (MCI), suboptimal exercise adherence remains a critical barrier. Mobile health technology, when integrated with preference-based personalization strategies, may enhance adherence through tailored interventions. However, empirical evidence validating the feasibility of exercise preference-driven mobile solutions for populations with MCI remains limite
Cardiovascular disease remains the leading cause of global mortality, yet scalable cardiac monitoring is hindered by the gap between diagnostic-rich ECG and ubiquitous wearable PPG. Bridging this gap requires representations that are compact, transferable across modalities and devices, and deployable without task-specific retraining. Here we introduce biosignal fingerprints: compact latent representations of cardiovascular state derived from a cross-modal foundation model, the Multi-modal Masked