Find Academic Supervisors

• Parallel Computing
• Compiler Optimization
• Performance Tuning
• +3 more

Dr. Mary Hall is a Professor in the School of Computing at the University of Utah, specializing in compiler optimization, parallel computing, and high-performance computing (HPC). Her work focuses on autotuning techniques, compiler-driven performance optimization, and minimizing data movement in computations to enhance efficiency. She has contributed significantly to frameworks like Bricks and Peak , advancing code generation for GPUs and block-structured grids. Her research also addresses educational initiatives, such as improving student retention in introductory computing courses and fostering diversity in the computing workforce through NSF-funded programs. Her research interests span compiler technology, stencil computations, and energy-efficient HPC applications. Key projects include optimizing geometric multigrid methods, developing communication-avoiding algorithms, and integrating machine learning into autotuning. She has led efforts to streamline performance portability across heterogeneous architectures and has published extensively on scheduling languages and compiler-driven optimizations. Mary Hall’s contributions include advancing data layout strategies for sparse tensors and DNNs, as well as fostering reproducibility in computational research through collaborative NSF REU programs. Her work emphasizes practical tools like ytopt and Rigel , which automate performance tuning for scientific applications. She remains active in both academic and industrial HPC communities, addressing challenges in extreme heterogeneity and scalable computing.

• Database Systems
• Data Analytics
• Machine Learning in Databases
• +3 more

Jignesh M. Patel is a Professor at the University of Wisconsin, Madison, WI, USA , with over 25 years of contributions to database systems, data analytics, and hardware-aware query processing. His work bridges theoretical advancements with practical systems engineering. Research Interests span: Database systems optimization (query processing, transaction management) Hardware acceleration for analytics (eBPF, PIM, GPUs) Machine learning integration in databases (feature selection, model optimization) Efficient data structures (hashing, encoding, indexing) Multi-tenant and cloud database management Recent Work focuses on kernel-embedded databases (BPF-DB, 2025), memory-efficient dataframe processing (SplitDF, 2024), and algorithmic-hardware co-design for dense retrieval (DReX, 2025). He has pioneered techniques for adapting to data skew (VIP Hashing, 2022), leveraging static analysis in R optimization (ROSA, 2017), and rethinking benchmarking paradigms. Collaborations include key partnerships with: Systems researchers (Andrew Pavlo, José F. Martínez) Machine learning experts (Arun Kumar, Kevin Skadron) Education-focused colleagues (Adalbert Gerald Soosai Raj, Richard Halverson) Industry leaders (David J. DeWitt, Microsoft Research)

Crystal FausettView profile

Assistant Professor

• Human-Centered Cybersecurity
• Human-Computer Interaction
• Research Methods
• +6 more

Dr. Crystal Fausett is an Assistant Professor in the School of Information at San José State University. Her academic work bridges human factors, cybersecurity, and human-computer interaction, with a strong focus on how individuals and teams interact with technology in high-stakes environments such as healthcare, emergency services, and cyber operations. She teaches courses including ISDA 121 – Human Centered Cybersecurity and ISDA 130 – User Centered Interface Architecture and Prototyping, reflecting her interdisciplinary expertise. Ph.D. in Human Factors, Embry-Riddle Aeronautical University (2024) M.S. in Human Factors, Embry-Riddle Aeronautical University (2022) B.A. in Psychology, San José State University (2020) A.A. in Social and Behavioral Sciences, Santa Barbara City College (2018) Her research interests include human-centered cybersecurity, human-computer interaction, usability and UX design, teamwork and transactive memory systems, training methodologies (particularly simulation-based), and information behavior across diverse user groups such as healthcare providers, cyber defenders, and naval personnel. She applies both qualitative and quantitative methods, including expert interviews, board game simulations, and meta-analytic techniques. The recent publications highlight a strong trend in applying human factors principles to cybersecurity team performance, adaptive training, and healthcare safety. Her work increasingly explores innovative methods such as gamified simulations to study team dynamics and cognitive load in complex operational environments. There is a consistent emphasis on improving system efficiency, safety, and collaboration through human-centered design. Dr. Fausett has no listed scientific awards in the provided text. She has served as an Instructor of Record in Human Factors and Behavioral Neurobiology at Embry-Riddle Aeronautical University (2023–2024) prior to her current role. There is no mention of current grant funding or student advising in the provided materials. Her research often involves collaboration with experts in human factors and healthcare, particularly Dr. Joseph R. Keebler and Dr. E. Salas, suggesting active participation in research teams focused on team performance and safety-critical systems. She is involved in research labs or teams centered on human factors in cybersecurity and healthcare, particularly through collaborative projects involving simulation-based training and team cognition studies. Her use of board games like [d0x3d!] as experimental testbeds indicates innovative lab-based methodologies for studying real-world team interactions in controlled environments.

• Research Software Engineering
• Software Architecture
• Grid Computing
• +3 more

Stephen Crouch serves as a Software Architect within the School of Electronics and Computer Science at the University of Southampton, where he actively contributes to the Web and Internet Science research group and the Southampton Research Software Group (SRSG). His role bridges technical software development with academic research infrastructure, focusing on creating robust solutions that enhance research capabilities across scientific domains while emphasizing sustainability and reproducibility in software practices. His research spans Research Software Engineering, Software Architecture, Grid Computing, Data Management, Reproducible Research, and High Performance Computing. Crouch has been instrumental in major projects including IGE (funded by the European Union's FP7 program) which developed integrated educational frameworks for research software engineering, and UNIVERSE-HPC (EPSRC-funded) addressing educational strategies in high-performance computing. His work consistently targets the intersection of software engineering principles and scientific research needs, particularly in creating maintainable systems for evolving research workflows. Analysis of his publication trajectory from 2007-2025 reveals a clear evolution from foundational grid computing research toward contemporary challenges in research software sustainability and reproducibility. Early work focused on grid interoperability and job scheduling, while recent contributions emphasize institutional strategies for research software engineering, data evolution pathways, and sustainable software practices. This progression demonstrates his adaptation to shifting research computing paradigms while maintaining core expertise in software architecture for scientific applications. Crouch has secured significant funding from the European Union and EPSRC, supporting his work in research software infrastructure. Within the Southampton Research Software Group, he plays a key role in developing institutional capacity for research software engineering, providing expertise that enables researchers across disciplines to implement reliable, efficient computational solutions. His collaborative approach is evident through extensive co-authorship with national and international research software engineering initiatives.

Andrés BruhnView profile

Professor

• Computer Vision
• Optical Flow
• Scene Flow
• +5 more

Andrés Bruhn is a Professor for Intelligent Systems and Dean of Computer Science Studies at the University of Stuttgart, where he leads research in the Institute for Visualization and Interactive Systems (VIS). His academic career spans over a decade with significant contributions to computer vision, particularly in optical flow, scene flow, and motion estimation. As Dean of Studies, he oversees academic programs while maintaining an active research agenda focused on cutting-edge computer vision problems. Bruhn's research interests center around computer vision with emphasis on optical flow estimation, scene flow, motion analysis, and adversarial machine learning. His work bridges theoretical foundations with practical applications, developing algorithms that address real-world challenges in motion estimation, image processing, and visual understanding. His research group has pioneered approaches that combine variational methods with deep learning, creating robust systems for motion analysis that can withstand adversarial attacks and challenging environmental conditions. The publication record demonstrates a strong focus on advancing the state-of-the-art in motion estimation, with recent work exploring adversarial attacks on optical flow systems, high-resolution datasets for benchmarking, and multi-frame fusion techniques. His research shows consistent innovation, moving from traditional variational methods to modern deep learning approaches while maintaining mathematical rigor. The work spans both theoretical contributions and practical implementations with real-world applicability. Bruhn has mentored numerous researchers who appear as first authors on publications, including Jenny Schmalfuss, Lukas Mehl, and Azin Jahedi, indicating his commitment to developing the next generation of computer vision researchers. His leadership role as Dean of Studies demonstrates institutional recognition of his expertise and administrative capabilities.

• Database Systems
• Privacy-Preserving Computation
• Indexing Techniques
• +3 more

Dong Xie is an Assistant Professor in the field of Computer Science and Engineering , with a focus on database systems and privacy-preserving computation. His work spans indexing techniques, oblivious RAM, and high-throughput data processing. Key Research Areas: Encrypted databases, access pattern privacy, dynamic data structures, spatial analytics. Collaborations: Active in database optimization and security, with external partnerships reflected in recent publications. Over the past decade, Dong Xie has contributed to advancements in oblivious query processing , index dynamization , and spatial data management . His research addresses challenges in secure data access , concurrent updates , and storage efficiency , particularly for cloud and distributed environments. Recent publications highlight his work on low-latency transaction scheduling (2025), dynamic sampling indexes (2023), and SSD-based storage optimization (2022). His articles explore intersections of privacy , performance , and scalability .

Giorgio ScorzelliView profile

Researcher

• Extreme Data Management
• Scientific Visualization
• Computational Topology
• +6 more

Giorgio Scorzelli is a researcher at the University of Utah, serving as Director of Software Development for the Center for Extreme Data Management, Analysis, and Visualization (CEDMAV) and the National Science Data Fabric (NSDF) . He specializes in extreme data management, scientific visualization, and computational topology, with a focus on scalable solutions for climate science, materials science, and neuroscience datasets. His work emphasizes democratizing data access through platforms like OpenVisus , enabling efficient analysis of petascale and exascale data. Key contributions include orchestrating cyberinfrastructure, optimizing parallel I/O, and developing real-time visualization systems for heterogeneous resources. Notable scientific contributions include the NSF Grant #2127548 for NSDF development . His projects integrate cloud computing, geo-distributed storage, and FAIR digital objects to lower barriers to data democratization. Giorgio's research spans multi-resolution algorithms , computational topology , and 3D geometric modeling , with applications in infrastructure security, archaeological reconstruction, and biomedical imaging. His work bridges abstract mathematical frameworks (e.g., Boolean algebras, chain complexes) with practical software solutions.

Zhiyuan LiView profile

Professor

• Program Analysis
• Compiler Design
• Parallel Computing
• +6 more

Zhiyuan Li is a Professor in the Department of Computer Sciences at Purdue University's College of Engineering. His primary research and teaching focus on program analysis, transformation, and run-time management for high-performance computing and multicore systems, as well as reliable software for networked embedded systems. Professor Li teaches graduate-level courses including CS502: Compiling and Programming Systems and CS591RS1: Research Seminar for First-year Graduate Students. Office: LWSN 3154H Contact: li@cs.purdue.edu Phone: +1 765-494-7822 Professor Li's research spans multiple areas within computer science, with particular emphasis on compiler design, program analysis, and parallel computing. His work addresses fundamental challenges in enabling efficient execution of applications on modern parallel architectures, including multicore processors and large-scale distributed systems. He has made significant contributions to techniques for data dependence analysis, loop parallelization, array privatization, and memory optimization in compilers. His research also extends to reliable software development for embedded and sensor network systems, where resource constraints and reliability requirements present unique challenges. Professor Li's publication record demonstrates consistent contributions to top-tier conferences and journals in computer science, particularly in the areas of parallel computing, compiler optimization, and high-performance numerical methods. His work shows a progression from foundational compiler techniques to applications in scientific computing domains such as computational fluid dynamics for jet engine noise simulation. This interdisciplinary approach connects low-level program analysis with real-world engineering applications requiring petascale computing resources. Principal Investigator for NSF/PetaApps project on jet engine noise simulation Principal Investigator for Intel-sponsored research on data dependence profiling Extensive service on program committees for major conferences including ICS, PPoPP, and LCTES Professor Li has been actively involved in mentoring graduate students through research projects and course instruction. His jet engine noise simulation project specifically mentions training three Ph.D. graduate students and involving undergraduate research assistants. As coordinator for the first-year graduate research seminar, he plays a significant role in guiding new students through the transition to graduate research work in computer science. His laboratory work focuses on developing compiler techniques and runtime systems for parallel and high-performance computing. The research infrastructure includes implementations in GCC for fast data dependence profiling and support for SIMD/SSE instructions, demonstrating practical applications of theoretical compiler techniques.

• Electronic Design Automation
• VLSI Design
• Computer Systems
• +7 more

Shinji Kimura is a Professor at Waseda University's Faculty of Science and Engineering, specializing in VLSI design and electronic systems. He holds a Doctor of Engineering from Kyoto University and has been with Waseda since 2002, previously serving as Associate Professor at Nara Institute of Science and Technology (1993–2002) and Assistant Professor at Kobe University (1985–1993). Kimura's research spans low-power circuit design , approximate computing , FPGA optimization , video coding (HEVC) , and hardware acceleration for AI . His work focuses on energy-efficient architectures for applications like neural networks, computer vision, and ultra-high-definition video processing. Recent publications emphasize hardware-efficient multipliers, neural network compression, and 3D-stacked memory systems. Awards include the LSI IP Design Award (2000, 1999) and the Information Processing Society of Japan Encouragement Award (1993). He leads projects on HEVC encoding/decoding, non-volatile memory optimization, and 3D integrated circuits, with VLSI implementations achieving real-time 8K video processing.

Sebastian AngelView profile

Associate Professor

• Systems
• Security
• Privacy
• +4 more

Sebastian Angel is an Associate Professor and Chair of Undergraduate Curriculum in the Department of Computer and Information Science at the University of Pennsylvania . He leads research in systems, security, privacy, and networking, with a focus on privacy-preserving systems, accountability in online services, consistency in distributed systems, and next-generation operating systems. Research Areas: Systems, Security, Privacy, Networking, Distributed Systems, Operating Systems Labs & Teams: Distributed Systems Laboratory, Security and Privacy Laboratory, Warren Center for Network and Data Sciences Education: Ph.D. in Computer Science from the University of Texas at Austin (2018), ACM SIGOPS Dennis M. Ritchie Dissertation Award, Bert Kay Best Dissertation Award Recent Publications (2025–2022) span serverless computing, zero-knowledge proofs, distributed transactions, privacy-preserving ad tech, and verifiable execution. His 2025 work includes serverless workflow optimization and structural logic verification, while 2024 focuses on caching frameworks and stateful serverless. Earlier 2023–2022 projects include secure federated learning, confidential cloud services, and private information retrieval. Scientific Awards: NSF CAREER Award (2021) JPMorgan Faculty Award (2021) ACM SIGOPS Dennis M. Ritchie Dissertation Award (2018) Bert Kay Best Dissertation Award (2018) ACM SIGMOD Research Highlights Award (2024) VLDB 2024 Best Paper Award Nominee Advising: Current PhD Students: Elizabeth Margolin, Jess Woods, Yuxuan Zhang Current Masters Students: Felix Adena, Sydnie Shea Cohen Alumni: Eleftherios Ioannidis (2025), Yiping Ma (2025), Haoran Zhang (2024), Ke Zhong (2024), Selin Butun (2025), Martin Sander (2025), Seungmin Han (2024), Andrew Beams (2022), Yifeng Mao (2021), Varad Deshpande (2020) Current Courses: CIS 4510/5510: Computer and Network Security (Fall 2025). He also organizes conferences like S&P, OSDI, SOSP, PETS, and EuroSys.

Gagan AgrawalView profile

Professor

• Parallel Computing
• High-Performance Computing (HPC)
• Data Analytics
• +5 more

Gagan Agrawal is the UGA Foundation Professorship in Computing and a Professor at the School of Computing, University of Georgia. He serves as Director of the School and is affiliated with the Franklin College of Arts & Sciences. Agrawal holds a PhD and MS in Computer Science from the University of Maryland (1994-1996). His research focuses on high-performance computing, parallel algorithms, compiler optimization for deep learning, GPU acceleration, and interdisciplinary applications in health informatics. Notable contributions include frameworks like ForensiBlock (blockchain for data forensics) and DELITE (tensorized instruction compilation). Agrawal has secured over $2.5M in NSF grants for projects addressing extreme-scale computing challenges. Recent grants include: SHF: Small: Memory Hierarchy Optimizations Meet Transformers (MITTEN) ($600K, 2024-2027) DELITE compilation system for deep learning models ($600K, 2023-2026) Publications span parallel computing methodologies, cybersecurity frameworks, and health outcomes analysis. His work on social determinants of health in cancer survival has been systematically reviewed in top-tier medical journals. Agrawal leads UGA's computing initiatives, emphasizing interdisciplinary research and student mentorship in HPC and AI domains.

Ehat ErcanliView profile

Teaching Professor

• Computer Architecture
• Embedded System Design
• System Verification
• +3 more

Ehat Ercanli is an Associate Teaching Professor at Syracuse University, serving as the Associate Chair of Education and Operations. He holds a Ph.D. in Computer Engineering from Case Western Reserve University. His research focuses on optimizing embedded systems, computer architecture, system verification, and VLSI design automation. He has contributed to advancements in memory management, compiler optimization, and energy-efficient computing. Key research interests include embedded system design, task recomputation techniques for memory utilization, and database systems optimization. His work emphasizes practical applications in multi-core systems, low-power electronics, and compiler-driven performance improvements. His publications highlight trends in system-on-chip (SoC) optimization, shared private memory management, and energy consumption reduction strategies. Notably, his 2007 paper was ranked #3 in the ACM Digital Library’s Most Popular Papers. Dr. Ercanli’s contributions also extend to automated code generation for database applications and custom processor synthesis for image processing.

Torsten HoeflerView profile

Professor

• Deep learning Systems
• Parallel programming models
• High performance and datacenter networking
• +8 more

Torsten Hoefler is a Full Professor of Computer Science at ETH Zurich, Switzerland, with an adjunct appointment in Electrical Engineering. He previously held roles at the National Center for Supercomputing Applications (University of Illinois at Urbana-Champaign) and Indiana University. Full Professor of Computer Science, ETH Zurich (2020–present) Adjunct Professor of Electrical Engineering, ETH Zurich (2020–present) Member at Large, ACM SIGHPC Executive Committee (2013–present) Leadership roles in the MPI Forum and Blue Waters project His research focuses on performance-centric system design , with emphasis on scalable networking, parallel programming models, and performance modeling. Key contributions include the Slim Fly network topology, Data-Centric Python framework, and innovations in parallel graph computations and RDMA-based systems. Recent publications span topics like LLM training networks , quantization geometry , chiplet interconnects , and AI-driven climate modeling , reflecting his interdisciplinary approach combining HPC, AI, and hardware-software co-design. ACM Gordon Bell Prize (2019) ERC Consolidator Grant (2020) IEEE TCSC Award for Excellence (2019) SIAM SIAG/SC Junior Scientist Prize (2012) Latsis Prize of ETH Zurich (2015) He has received multiple best paper awards at top conferences (SC10, SC13, SC14, SC19, IPDPS'15, HPDC'15, OOPSLA'16) and contributed to MPI-3 standardization.

Roberto CalandraView profile

Professor

• Robotics
• Machine Learning
• Tactile Sensing
• +3 more

Roberto Calandra is a Full (W3) Professor at Technische Universität Dresden, where he leads the Learning, Adaptive Systems and Robotics (LASR) Lab. Previously, he served as a Research Scientist at Meta AI (formerly Facebook AI Research) and a Postdoctoral Scholar at UC Berkeley’s BAIR Lab under Sergey Levine. His academic journey includes a PhD in Robotics from TU Darmstadt, an M.Sc. in Machine Learning from Aalto University, and a B.Sc. in Computer Science from Università di Palermo. His research bridges Robotics and Machine Learning, focusing on tactile sensing, Bayesian Optimization, and model-based reinforcement learning. He pioneered the DIGIT tactile sensor , now the most widely used tactile sensor in robotics, and advocates for a computational field of Touch Processing to advance haptic understanding. His work emphasizes data-efficient learning, real-world dexterous manipulation, and multimodal perception. Recent publications highlight breakthroughs in tactile sensor design, in-hand object manipulation, and multimodal integration. He organizes workshops on robotics and machine learning (e.g., at NeurIPS, ICRA) and promotes open-source tools like PyTouch and TACTO .

• Networked Systems
• Computer Networking
• Communications Engineering
• +4 more

Professor Mark Handley is a Professor of Networked Systems in the Department of Computer Science at University College London. His research focuses on network architecture, protocols, and systems with a particular emphasis on low-latency networking, datacenter networks, and network security. Education: Doctor of Philosophy, University College London (1997) Bachelor of Science (Honours), University College London (1988) Professor Handley's research spans multiple areas of computer networking with a focus on practical, deployable solutions. His work addresses fundamental challenges in network architecture, including low-latency routing, congestion control, network security, and datacenter networking. He has made significant contributions to Multipath TCP, congestion control algorithms, and network security protocols. His research often bridges theoretical foundations with practical implementation, ensuring real-world applicability of his innovations. His recent publications demonstrate a continued focus on cutting-edge networking challenges, particularly in low-latency routing, datacenter networks, and network security. The trend shows increasing attention to space-based networking, in-switch processing, and novel approaches to congestion control. His work consistently addresses the fundamental tension between theoretical network design and practical deployment constraints. Scientific Awards: IEEE Internet Award (2012) Usenix NSDI Best Paper Award (2011) ACM SIGCOMM Test of Time Award (2011) Roger Needham Award (2007) Professor Handley has served on numerous program committees including ACM SIGCOMM and Usenix NSDI. His work has influenced both academic research and industry standards, with contributions to IETF RFCs including Multipath TCP and TCP encryption. He has mentored numerous students and researchers who have gone on to make significant contributions in the networking field. His research group at UCL focuses on next-generation network architectures, with particular expertise in low-latency routing, datacenter networks, and network security. The group maintains strong collaborations with industry partners to ensure practical relevance of their research.