🚀 Leading Edge Research

Welcome to Machine Learning Lab

AdvancingLLMs & AI Agents

Pioneering breakthrough discoveries in artificial intelligence, machine learning, and deep learning that revolutionize industries worldwide.

Research Areas

publications

Global

collaborations

Discover Our Research

1 / 4

Innovating Since 2003

Welcome to Machine Learning Lab

Established in 2003 under the visionary leadership of Prof. Dr. Yung-Cheol Byun, our lab at Jeju National University pioneers breakthrough research in artificial intelligence, machine learning, and innovative technology solutions that transform industries and improve lives across the globe.

AI-Powered

Cutting-edge artificial intelligence and machine learning innovations driving the future

Research Driven

Pushing boundaries with innovative solutions across LLMs & AI agents, clean energy, and computer vision

Global Impact

Transforming industries with breakthrough AI research and real-world applications worldwide

Technologies & Research Domains

Solar PV SegmentationSatellite Solar MappingGlobal MPPTProbabilistic ForecastingPhysics-Informed AIMeta-LearningConformal PredictionUncertainty QuantificationGrid-State ForecastingEnergy Demand ForecastingVision-Language ModelsReal-Time Video SegmentationKnowledge DistillationSuper-ResolutionEdge AIAdaptive RAGReinforcement LearningExplainable AISmart Farming AISolar PV SegmentationSatellite Solar MappingGlobal MPPTProbabilistic ForecastingPhysics-Informed AIMeta-LearningConformal PredictionUncertainty QuantificationGrid-State ForecastingEnergy Demand ForecastingVision-Language ModelsReal-Time Video SegmentationKnowledge DistillationSuper-ResolutionEdge AIAdaptive RAGReinforcement LearningExplainable AISmart Farming AI

Driving Real-World Impact

Two decades of AI research, translated into publications, projects, and global collaboration.

Publications

Research Projects

Years of Excellence

Citations

Research Areas

We advance knowledge at the forefront of artificial intelligence through diverse research domains

Solar Energy & Photovoltaic AI

AI for the full solar pipeline: segmenting PV panels across image resolutions with multi-agent, uncertainty-aware frameworks, mapping rooftop installations from satellite and aerial imagery with minimal labelled data, and tracking the true global power peak in module-level solar optimizers.

PV SegmentationSolar MappingMPPT

Probabilistic Energy & Grid Forecasting

Reliable, uncertainty-aware forecasting for power systems: physics-guided and physics-informed deep learning, meta-learning for unseen operating regimes, conformal calibration of prediction intervals, and explainable multivariate time-series models for generation, demand and grid state.

Probabilistic ForecastingPhysics-Informed MLUncertainty Quantification

Efficient Vision & Edge AI

Real-time, edge-deployable computer vision: confidence-guided hybrid architectures for language-guided video segmentation, and lightweight, distilled models that judge the analytical value of satellite imagery onboard to cut unnecessary data transmission.

Video SegmentationVision-Language ModelsKnowledge Distillation

Trustworthy LLMs & Adaptive RAG

Making generative AI reliable: adaptive retrieval-augmented generation that chooses retrieval channels per query, answers or abstains based on visual evidence and confidence, and selectively revises responses as video and sensor observations change.

Adaptive RAGMultimodal LLMsReliable AI

Explore Research

Latest Research

Featured Publications

Recent breakthroughs and innovative research from our lab

2026

Featured

MTML-EV: Multi-target meta-learning for cross-zone urban electric vehicle charging infrastructure management

Muhammad Waqar, Yong-Woon Kim +1 more

Sustainable Cities and Society

A multi-target meta-learning framework that jointly predicts EV charging occupancy, energy demand and electricity price in unseen urban zones, using BiGRU representations with FOMAML adaptation.

PV-JSSR: Joint super-resolution and segmentation with cross-task interaction for photovoltaic panel mapping from multi-resolution imagery

Amreen Batool, Yong-Woon Kim +1 more

Applied Energy

Joint super-resolution and semantic segmentation for photovoltaic panel mapping, with GSD-aware embedding and bidirectional cross-task interaction, achieving 0.865 IoU and 0.919 Dice.

Dual teacher multiscale distillation for lightweight solar cell defect classification

Hasnain Hyder, Yong-Woon Kim +2 more

Solar Energy

Distills ViT-Base and Swin-Large into a lightweight MobileNetV3 through dual-teacher multi-scale knowledge distillation, reaching 97.5% accuracy with only 3.26M parameters for embedded inspection.

Impact Factor

7.9

View All Publications

Leadership