جست‌وجوی استاد و پژوهشگر

Bin Renمشاهده پروفایل

استادیار

• Parallel Computing
• High-Performance Computing
• Compiler Techniques
• +۷ مورد دیگر

Bin Ren is an Assistant Professor in the Department of Computer Science at the College of William & Mary, where he has been a faculty member since Fall 2016. He holds a Ph.D. in Computer Science and Engineering from The Ohio State University (2014) and was a postdoctoral research associate at Pacific Northwest National Laboratory from 2014 to 2016. Research Interests: His work centers on high-performance computing, compiler techniques, and machine learning systems, with a focus on enabling real-time and energy-efficient deep neural network execution on mobile and edge devices. He explores compiler optimizations, DNN pruning, neural architecture search, and GPU memory management to improve system performance and efficiency. Publication Trends: His recent publications (2023–2025) reveal a strong focus on compiler-aware deep learning systems, mobile and edge AI, and performance optimization across heterogeneous platforms. Key themes include DNN acceleration, memory efficiency, real-time inference, and hardware-software co-design. His work frequently appears in top-tier venues such as ASPLOS, SC, CVPR, and PLDI. Scientific Awards: NSF CAREER Award, 2021 Best Paper Award, SC 2020 Best Student Paper Nomination, SC 2020 Jeffress Trust Award, 2020 ISLPED Design Contest First Place, 2020 Student Cluster Reproducibility Challenge Paper, SC 2019 Best Paper Award, CGO 2013 SIGPLAN Research Highlights, 2013 Advising and Grants: Bin Ren has advised numerous Ph.D. and master’s students, many of whom have co-authored influential papers. His research has been supported by competitive grants, including the NSF CAREER Award. He actively mentors students in areas of parallel computing, compiler design, and machine learning systems. He has also received funding from the Jeffress Trust Awards and other sources to support interdisciplinary research. Professional Service: He has served in leadership roles such as Program Co-Chair for PPoPP'25 and HIPS'21, Track Co-Chair for ICPP'24 and HiPC'24, and Artifact Evaluation Co-Chair for PPoPP'24 and ALENEX'25. He is a frequent reviewer for top journals and conferences including TPDS, TACO, NeurIPS, and SC. Teaching: He teaches courses such as CS304 (Computer Organization) and CS642 (Compiler Techniques for High Performance Computing), contributing to both undergraduate and graduate education in systems and programming. Lab and Team: His research group focuses on system-software co-design for efficient AI deployment. Collaborators include researchers from institutions like Pacific Northwest National Laboratory and The Ohio State University. His team works on real-world applications in healthcare, autonomous systems, and scientific computing.

• Scientific Computing
• Numerical Analysis of PDEs
• High-Performance Computing
• +۷ مورد دیگر

PD Dr. Florian Frank is Privatdozent (senior lecturer with full teaching licence) for Applied Mathematics at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) and heads the Bavarian research project „Parallel mesh loading and partitioning for large-scale simulation“ . His expertise spans high-performance computing, phase-field and discontinuous Galerkin methods, digital-rock physics, and reactive transport in porous media. Education & career 2022 – Venia legendi (private lecturer), Mathematics, FAU 2019 – Dr. habil., Mathematics, FAU 2013 – Dr. rer. nat., Applied Mathematics, FAU 2008 – Graduate Mathematician, University of Frankfurt 2021-2022 (acting) W2 Professor Scientific Computing, FAU 2018-2021 (acting) W2 Professor Mathematical Modelling, FAU 2017-2018 Senior Postdoc, CAAM, Rice University, USA 2014-2017 Postdoc, CAAM, Rice University, USA Research interests Frank focuses on the development and analysis of numerical schemes for partial differential equations that govern multiphase, multicomponent and reactive processes in porous or biological media. Key themes include discontinuous Galerkin and finite-volume methods , physics-preserving discretizations , high-performance computing , and digital-rock-based pore-scale simulations . He couples phase-field approaches with (Navier–)Stokes, Cahn–Hilliard, Nernst–Planck and density-gradient equations to quantify flow, transport, colloid dynamics and interfacial phenomena. Recent publications reveal a clear trend toward data-driven modelling : convolutional neural networks are trained with direct numerical simulation data to predict permeability and diffusion coefficients from 3-D micro-CT images, while advanced preconditioners and regularization techniques accelerate multiphase thermodynamic computations. Awards & recognition 2020 – Emmy-Noether-Prize der Naturwissenschaftlichen Fakultät, FAU 2017 – Promotion to Senior Postdoctoral Research Associate , George R. Brown School of Engineering, Rice University Projects, tools & supervision Frank currently leads a Bavarian state-funded project on parallel mesh handling for large-scale simulations. Together with collaborators he maintains the open-source MATLAB/GNU Octave toolbox FESTUNG for discontinuous Galerkin methods. Since 2018 he has (co-)supervised ten BSc and MSc theses on topics ranging from Stokes preconditioning to enriched Galerkin shallow-water solvers, regularly serves as reviewer for more than a dozen international journals, and is guest editor of special issues in Computational Geosciences and Oil & Gas Science and Technology .

• Computer vision and pattern recognition
• Digital image processing
• Medical image processing
• +۴ مورد دیگر

Santa Di Cataldo is an Associate Professor at the Department of Control and Computer Engineering (DAUIN) of Politecnico di Torino. His research focuses on computer vision, pattern recognition, digital image processing, and medical image processing, with applications in industrial systems and AI for manufacturing. Scientific Branch: IINF-05/A - Information Processing Systems ERC Sectors: PE6_8 - Computer graphics, computer vision, multi media, computer games ERC Sectors: PE6_11 - Machine learning, statistical data processing His work includes developing AI-driven anomaly detection frameworks, physics-informed neural networks for additive manufacturing optimization, and neuro-symbolic approaches for Industry 4.0 applications. He supervises PhD students in Artificial Intelligence and Computer Engineering programs, collaborating on projects like BIG (Blue Is Green) and PNRR-Complementary Plan. Premio Donna Innovazione (2010) He leads courses such as Machine Learning in Applications and Applied AI and Machine Learning , while contributing to bioinformatics and robotics-related teaching. His research is supported by IAM@PoliTo and EDA groups, utilizing LADISPE laboratory facilities.

KÜBRA UYARمشاهده پروفایل

مدرس

• Artificial Intelligence
• Computer Vision
• Medical Image Analysis
• +۲ مورد دیگر

KÜBRA UYAR is a Lecturer at Alanya Alaaddin Keykubat University's Rafet Kayış Faculty of Engineering, Department of Computer Engineering. She previously worked as a Research Assistant at Selçuk University's Faculty of Technology (2022-2023) and continues her academic contributions in image processing and artificial intelligence. PhD in Computer Engineering (2022), Selçuk University MSc in Computer Engineering (2017), Selçuk University BSc in Computer Engineering (2014), Melikşah University Double Major in Mathematics (2014), Melikşah University Her research focuses on Artificial Intelligence , Computer Vision , and Medical Image Analysis , with a strong emphasis on Machine Learning and Image Processing . Current work includes developing explainable AI models for retinopathy diagnosis and optimizing CNN architectures for biomedical applications. Recent publications highlight trends in Deep Learning for agriculture (chestnut classification), Medical Imaging (retinopathy, leukocyte detection), and Optimization (CNN hyperparameters, B-spline algorithms). Her work bridges Computer Science with Healthcare and Industrial Applications . Key projects include the Data-Intensive and Computer Vision Research Laboratory Infrastructure Project (2020-2021) and the Selçuk University Weather Monitoring System (2018-2020), both funded by higher education institutions.

Ciarán Doneganمشاهده پروفایل

پژوهشگر ارشد

• Regulatory Genomics
• Explainable AI
• Geometric Deep Learning
• +۱ مورد دیگر

Ciarán Donegan is a Research Fellow in the Machine Learning group at the Technical University of Berlin and BIFOLD (Berlin Institute for the Foundations of Learning and Data), with a concurrent guest researcher position in the Ohler Lab at the Max Delbrück Center for Molecular Medicine. His primary research focuses on applying deep learning methodologies to elucidate gene regulation mechanisms within molecular biology. Education: M.A.I. in Electronic & Computer Engineering from Trinity College Dublin (2021) B.A.I. in Electronic & Computer Engineering from Trinity College Dublin (2020) His research program integrates Regulatory Genomics with cutting-edge machine learning techniques, emphasizing Explainable AI frameworks and Geometric Deep Learning architectures. This interdisciplinary approach targets complex biological systems, particularly in modeling transcriptional regulation and epigenetic modifications through neural network interpretability. Applications extend to disease mechanism analysis and therapeutic target identification in life sciences contexts. Publication trends reveal dual-domain expertise: the 2022 sports broadcasting paper demonstrates real-time computer vision capabilities for automated production systems, while the 2021 VPU-specific CNN research pioneers hardware-aware neural architecture search. These works collectively underscore a methodological thread in optimizing deep learning for constrained environments—whether computational (edge devices) or operational (live sports)—while maintaining biological research as his core focus area. No scientific awards were documented in the source materials. Advisory activities and grant funding details remain unspecified in available records. He operates within collaborative research ecosystems spanning TU Berlin's Machine Learning group, BIFOLD's interdisciplinary data science initiatives, and the Ohler Lab's genomic regulatory studies at the Max Delbrück Center, facilitating cross-institutional innovation in AI-driven life sciences.

Moran Artziمشاهده پروفایل

استاد

• Medical Imaging
• Machine Learning
• Deep Learning
• +۵ مورد دیگر

Prof. Moran Artzi is a faculty member at the Sagol School of Neuroscience, Tel Aviv University, specializing in advanced computer vision and machine learning applications for medical imaging. Her research focuses on leveraging MRI data to improve diagnosis and clinical follow-up of central nervous system pathologies through AI-driven diagnostic tools. Research Interests Her work spans: Medical Imaging and Computer Vision Deep Learning for Healthcare Applications Radiomics and Image Segmentation/Classification Brain Tumor Analysis (Glioblastoma, Metastases, Optic Pathway Gliomas) Clinical Integration of AI Diagnostic Systems Emphasis is placed on bridging computational methods with clinical practice from study design through implementation. Publication Trends Between 2018-2021, Artzi's publications demonstrate consistent focus on applying deep learning (CNNs, EfficientNet) and radiomics to differentiate neurological pathologies using MRI. Key themes include tumor classification by molecular characteristics, segmentation of pediatric/adult brain tumors, and therapy response monitoring, with strong clinical validation components across all studies. Scientific Awards No scientific awards were mentioned in the provided text. Advising and Grants The available documentation does not specify graduate students, postdoctoral advisees, or grant funding details. Her collaborative publications indicate clinical partnerships but no formal advising structure is described. Labs and Teams Research is conducted within the Sagol School of Neuroscience framework at Tel Aviv University, involving interdisciplinary teams of computer scientists, neurologists, and oncologists focused on translating AI methodologies into clinical neuroimaging workflows.

Yuqi Songمشاهده پروفایل

استادیار

• Machine Learning
• Deep Learning
• Data Mining
• +۳ مورد دیگر

Yuqi Song is an Assistant Professor in the Department of Computer Science at the University of Southern Maine (USM), where she joined in August 2023 after completing her Ph.D. at the University of South Carolina. Her interdisciplinary research bridges machine learning with materials science, tourism, and recommender systems. Her educational background includes: Ph.D. in Computer Science, University of South Carolina (2023), supervised by Dr. Jianjun Hu M.S. and B.S. in Computer Science, Chongqing University, supervised by Dr. Ming Gao Dr. Song's research focuses on applying state-of-the-art deep learning techniques—including generative adversarial networks, graph neural networks, and transformer models—to solve real-world problems. She develops AI-driven solutions for materials discovery (predicting crystal structures and properties) and tourism applications (employee turnover prediction systems). Her work uniquely combines computational methods with domain-specific challenges, emphasizing practical implementation through user-friendly tools like her materials informatics web platform MaterialsAtlas.org. Analysis of her recent publications (2023-2025) reveals three dominant research thrusts: (1) materials informatics using transformer-based generative models for crystal structure prediction, (2) robust recommender systems security against data hybrid attacks, and (3) computer vision innovations in depth estimation and medical image analysis. Her work consistently leverages attention mechanisms and cross-disciplinary data integration. Dr. Song actively mentors graduate students, currently advising Reihaneh Maarefdoust (Complex Learning and Machine Learning) and Zahra JahediBashiz (NLP, Generative AI). She teaches core courses including Software Engineering (COS 430) and Artificial Intelligence (COS 470), emphasizing practical programming skills. Her lab seeks motivated students for projects in materials discovery and tourism analytics. She leads a research group focused on interdisciplinary AI applications, collaborating with materials scientists and hospitality industry partners to develop deployable solutions. Current initiatives include deep learning models for predicting piezoelectric properties and generative design of 2D materials, alongside tools for tourism workforce analytics.

Nejat YUMUŞAKمشاهده پروفایل

استاد

• Artificial Intelligence
• Machine Learning
• Bioinformatics
• +۵ مورد دیگر

Prof. Nejat YUMUŞAK is a full Professor in the Department of Computer Engineering at Sakarya University's Faculty of Computer and Information Sciences, where he has built his academic career since 1995. His progression includes roles as Research Assistant (1993-1998), Assistant Professor (1998-2004), Associate Professor (2005-2011), and Professor (2011-present). Education PhD in Electrical-Electronics Engineering, Sakarya University (1995-1998) Thesis: Analysis of Power System Circuit Elements Using Artificial Neural Networks MSc in Electrical-Electronics Engineering, Dumlupinar University (1994-1995) Thesis: Calculation and Measurement of Transformer Parameters at High Frequencies BSc in Electrical-Electronics Engineering, Istanbul Technical University (1989-1993) Research Focus Prof. YUMUŞAK's research integrates artificial intelligence with multidisciplinary applications. Primary domains include: Bioinformatics & Medical AI : Developing deep learning models for COVID-19 mutation prediction, leukemia classification via blood smear analysis, and gastrointestinal anomaly detection using endoscopic data. Signal Processing & Security : Advancing acoustic event detection for security systems and vulnerability testing through intelligent fuzzing techniques. Optimization & Industrial Applications : Creating metaheuristic algorithms (e.g., enhanced Wild Horse Optimizer) for energy efficiency and Industry 4.0 digitalization. Publication Trends His recent articles (2022-2025) demonstrate strong emphasis on transformer architectures for virology, ensemble methods for medical diagnostics, and CNN/LSTM networks for genomic and acoustic data analysis. Over 50% of recent works focus on healthcare applications, particularly cancer and pandemic-related prediction models. Contact & Recognition Contact via nyumusak@sakarya.edu.tr or phone (0264) 264 58 94. His work has received 793 citations (Web of Science) with an H-index of 14.

• Virtual Reality
• Extended Reality (XR)
• Computer Graphics
• +۵ مورد دیگر

Prof. Dr. Kiran Varanasi serves as a Professor in Virtual and Extended Reality at the Faculty of Computer Science and Media, Leipzig University of Applied Sciences. His research focuses on 3D shape processing, real-time facial animation, and convolutional neural network applications in computer vision. University: Leipzig University of Applied Sciences School: Faculty of Computer Science and Media Academic Rank: Professor Research Interests: Varanasi's work bridges virtual reality , machine learning , and interactive systems . Key areas include: 3D reconstruction using deep learning Facial animation pipelines Light field data processing Surface defect classification with CNNs Interactive character control Publication Trends (2018–2021): His recent articles emphasize monocular 3D reconstruction , real-time feature extraction , and immersive VR environments , often leveraging convolutional networks and geometric warping techniques. Advising and Grants: No specific students or advisory roles are listed in the provided text. The faculty participates in collaborative projects like website redesign for the Egyptian Museum, though Varanasi's direct involvement isn't specified. Labs and Teams: The faculty includes multimedia labs and research groups in digital transformation, but Varanasi's direct affiliations with these units are not explicitly stated.

Guangxing Wangمشاهده پروفایل

استاد

• Remote Sensing
• Geographic Information Systems (GIS)
• Spatial Statistics
• +۴ مورد دیگر

Guangxing Wang is a Professor in Remote Sensing and GIS at Southern Illinois University Carbondale's Department of Geography and Environmental Resources. His research focuses on integrating geospatial technologies with environmental monitoring, particularly in carbon sequestration modeling, vegetation disturbance analysis, and terrain-based hydrology studies. Ph.D., Remote Sensing of Forest Resources, University of Helsinki (1996) M.Sc., Forest Biometrics, Central South University of Forestry and Technology, China (1985) B.S., Forestry, Central South University of Forestry and Technology, China (1982) His work emphasizes spatial statistics, sampling design optimization, and quality assessment of remote sensing/GIS products. Key applications include desertification monitoring, wetland classification, and military land condition analysis using LiDAR and satellite data. Recent publications highlight advancements in deep learning for drainage crossing detection (2023-2025), spectral unmixing techniques (2025), and enhanced carbon density mapping methodologies (2024). Earlier works (2015-2021) established foundational frameworks for forest biomass estimation and soil moisture modeling. Grants: PI for UAS vegetation mapping (2018-2022, $185,969); Permafrost monitoring in Alaska (2017-2020, $159,489) Courses Taught: Introduction to GIS, Advanced Remote Sensing, Spatial Analysis, Cartographic Design

Mehmet Can Yavuzمشاهده پروفایل

استادیار

• Machine Learning
• Artificial Intelligence
• Human-Computer Interaction
• +۳ مورد دیگر

Mehmet Can Yavuz is an Assistant Professor at Işık University's Faculty of Engineering and Natural Sciences, Department of Computer Engineering. As Principal Investigator of the Multimedia Lab, he bridges machine learning with artistic expression through projects like Arky Multimedia, ConvergedMachine, and Duyukoru. His research spans biomedical imaging, human-computer interaction, and cross-modal analysis of multimedia storytelling. 2019-2023: PhD in Computer Science & Engineering, Sabancı University 2010-2016: MS in Physics, Boğaziçi University 2006-2010: BS in Physics, Işık University 2004-2010: BS in Electrical-Electronics Engineering, Işık University Current research explores: Advanced machine learning architectures (Variational Contrastive Learning, Cross-D Convolution) Biomedical imaging applications for disease detection Computational analysis of dramatic/literary works through graph theory and sentiment analysis AI-driven threat detection systems using sensor fusion Creative technology intersections in multimedia production His lab develops frameworks for: Noisy data processing in semi-supervised learning Cross-dimensional knowledge transfer Ensemble approaches in 2D/3D medical imaging Temporal-sentiment analysis of urban events Document embedding-based character analysis Projects include: ARKY MULTIMEDIA - Combining creative exploration with ML DUYUKORU - Machine learning-enhanced sensor threat detection CONVERGEDMACHINE - Multimodal ML research repository He oversees the Işık University Multimedia Lab , which integrates medical image computing with animation production, pushing boundaries in both scientific and artistic domains.

Oluwaseun Priscilla OLAWALEمشاهده پروفایل

مدرس

• Software Engineering
• Artificial Intelligence
• Machine Learning
• +۵ مورد دیگر

Oluwaseun Priscilla Olawale is a Lecturer in Software Engineering at Near East University (Nicosia, Cyprus), where she is concurrently pursuing her master's degree in Software Engineering. She previously served as a teaching assistant at the same institution. Her academic background includes a Bachelor's degree in Computer Science from Bowen University, Nigeria, complemented by professional experience as an IT Specialist at the Standards Organisation of Nigeria and Software Developer at Royal Niger Company. Research Focus: Her work centers on developing reliable software solutions with emphasis on artificial intelligence applications. Primary domains include healthcare technology (medical imaging, remote healthcare, IoHT security), industrial systems (Industry 4.0 automation), cybersecurity (blockchain integration, anomaly detection), and educational technology (post-pandemic learning environments). She demonstrates consistent interest in interdisciplinary AI implementations bridging theoretical models and practical challenges. Publication Trends: Recent articles (2020-2025) reflect a progression from foundational surveys in data mining and blockchain verification toward applied AI solutions. Emerging themes include disaster prediction systems, audio-visual signal processing, and security-enhanced healthcare networks. Her technical approach frequently employs deep learning architectures (CNNs, VGG-16), blockchain frameworks, and signal processing techniques to address real-world problems across diverse sectors.

• Computer Science
• Cybersecurity
• Internet of Things
• +۵ مورد دیگر

Gang Tan is an Associate Professor at the Pennsylvania State University's College of Engineering, Department of Computer Science and Engineering. He also holds the James F. Will Career Development Professorship and is affiliated with the Institute for Computational and Data Sciences (ICDS). His research focuses on binary reverse engineering , cybersecurity , Internet of Things (IoT) security , machine learning fairness , and information flow security . He has led numerous NSF-funded projects, including work on precise binary analysis, IoT policy enforcement, and automated fairness repair in AI systems. Recent work trends include memory safety validation , pseudocode extraction , and control-flow integrity mechanisms. His 127+ research outputs reflect deep engagement with static program analysis , cache side-channel detection , and secure kernel-driver interfaces . Scientific Awards: James F. Will Career Development Professorship Gang Tan has secured multiple grants from the National Science Foundation (NSF) and U.S. Navy for projects like Sliver (information flow verification) and Semantics-Directed Binary Reverse Engineering . His work involves advising teams on IoT safety, and he has 19 active or completed grants since 2008.

Michael Ryooمشاهده پروفایل

دانشیار

• Deep Learning
• Computer Vision
• Robotics
• +۳ مورد دیگر

Michael Ryoo serves as a SUNY Empire Innovation Associate Professor in the Department of Computer Science at Stony Brook University while concurrently working as a Research Scientist with Google Brain's "Robotics at Google" team. Previously, he held positions as an Assistant Professor at Indiana University Bloomington and a Staff Researcher at NASA's Jet Propulsion Laboratory. His academic background includes a Ph.D. from the University of Texas at Austin (2008) and a B.S. from Korea Advanced Institute of Science and Technology (KAIST) in 2004. Ryoo's research centers on deep learning and computer vision with specific focus on convolutional neural network (CNN) models for video semantic understanding. His work bridges visual perception and robotic action through applications in robot perception, robot learning, and human-robot interaction. Key innovations involve developing efficient architectures for processing multimodal data and translating visual understanding into robotic control systems. Analysis of his 15 most recent publications reveals strong emphasis on multimodal AI integration, particularly vision-language models applied to robotics. His 2025 work shows significant advancement in token-efficient video representation, motion-controllable diffusion models, and zero-shot learning frameworks specifically designed for robotic control systems. The research trajectory demonstrates consistent focus on making video understanding more accessible and applicable to real-world robotic scenarios. Scientific awards: No awards were mentioned in the provided source material. Regarding academic advising, the source text does not list any students or mentoring activities. Similarly, no grant funding information is provided, though his dual academic-industry role suggests substantial research support. His Google Brain affiliation likely involves industry-sponsored research initiatives. Ryoo maintains active laboratory affiliations through Stony Brook's AI Innovation Institute and Google's Robotics team. His prior work at NASA JPL indicates experience with space robotics systems, while his current Google role focuses on large-scale robot learning infrastructure. The LAM SIMULATOR project represents his current focus on advancing data generation techniques for training large action models.

• Computer Graphics
• VR/AR/MR
• Physics-Based Animation
• +۷ مورد دیگر

Oh-Young Song is a Professor in the Department of Software at Sejong University's Ocean Humanities College, where he has been a faculty member since 2006. He also serves as a Researcher at the eXtended Reality Research Center and directs the Sejong University Graphics Lab, which focuses on natural phenomena simulation and related applications in special effects and animation. Sejong University, Department of Software (2006-present) Adobe Systems, Visiting Professor (2013-2014) Seoul National University, Automation and Systems Research Institute (2004-2006) Song earned his educational credentials from Seoul National University: B.S. (1998), M.S. (2000), and Ph.D. (2004), all in Electrical Engineering and Computer Science. His research spans computer graphics, VR/AR/MR, physics-based animation, fluid simulation, and deep learning . His work bridges theoretical computer graphics with practical applications in healthcare, IoT, and special effects. Song has developed physics-based animation techniques used in movies and games, with particular expertise in fluid simulation where he holds a US patent for simulating detailed fluid movements using derivative particles. His recent research increasingly integrates AI and deep learning approaches with traditional computer graphics techniques. Analysis of his 15 most recent publications (2021-2024) reveals a strategic expansion of his research into healthcare applications, with significant work in medical image analysis, gastrointestinal disease detection, and secure patient data transmission. His research shows strong interdisciplinary collaboration, particularly between computer graphics and medical informatics, with consistent publication in high-impact journals across computer science and healthcare domains. Song's scholarly achievements include 49 research outputs with 1922 citations and an h-index of 20. His most notable scientific achievement is the US-patented technique for simulating detailed fluid movements using derivative particles, with related papers published in ACM Transactions on Graphics. US Patent for Method of Simulating detailed movements of fluids using derivative particles 49 research publications across computer graphics, VR/AR, and medical AI domains 1922 total citations with h-index of 20 As an educator, Song teaches courses including Advanced Computer Graphics, Algorithms and Practice, and Physics Coding for General Public. He advises graduate students through Master's thesis research and Graduation Research and Career courses. His lab, the Sejong University Graphics Lab, actively collaborates with industry on physics-based animation techniques for special effects and animation in movies and games. Current research directions indicate growing emphasis on integrating extended reality technologies with healthcare applications, particularly in medical simulation and diagnostic support systems.