Find Academic Supervisors

Yunzhong HouView profile

Research Fellow

• Computer Vision
• Deep Learning
• Multiview Detection
• +4 more

Dr. Yunzhong Hou is a Research Fellow at the School of Computing, The Australian National University (ANU), where he collaborates with Prof. Tom Gedeon and Dr. Liang Zheng. He holds a PhD in Computer Science from ANU (2019–2023) and a Bachelor's in Electronic Engineering from Tsinghua University (2014–2018). His research focuses on computer vision and deep learning, particularly in multiview detection, sensor optimization, and efficient AI systems. Education: PhD in Computer Science, ANU (2019–2023) Bachelor of Electronic Engineering, Tsinghua University (2014–2018) Research Interests: Multi-view detection and tracking Active vision and sensor optimization Efficient AI systems His work spans topics such as camera configuration optimization for pedestrian detection, deep learning for color quantization, and multi-camera systems. He has contributed to projects like the socioeconomic impact analysis of water reforms and privacy-preserving perception for robotics. Hou serves as a reviewer for top conferences (CVPR, ICCV) and journals (TPAMI, TIP). His research emphasizes scalable solutions for real-world applications, including drone vision control and edge computing optimizations. Current projects include machine learning for socio-economic analysis and privacy-aware robotic perception.

Chengming ZhangView profile

Assistant Professor

• Efficient machine learning systems
• AI algorithm-hardware Co-design
• Effective efficiency algorithms
• +5 more

Chengming Zhang is a tenure-track assistant professor in the Computer Science Department at the University of Houston. He recently completed his Ph.D. in Computer Engineering from Indiana University in May 2024, where he was a member of the HiPDAC group working on building efficient and scalable deep learning systems under the advisement of Prof. Dingwen Tao. He has extensive industry research experience with multiple projects at Microsoft Research, Meta Reality Labs, and Argonne National Laboratory. His educational background includes: Ph.D. in Computer Engineering, Indiana University (May 2024) Dr. Zhang's research focuses on creating efficient machine learning systems that can operate effectively across diverse hardware platforms. His work bridges the gap between theoretical algorithms and practical implementation with particular emphasis on efficient machine learning systems for training and inference on parallel, distributed, and heterogeneous hardware; AI algorithm-hardware co-design, particularly for GPU architectures; effective efficiency algorithms including model compression, data efficiency, and parameter-efficient tuning; and large-scale deep learning applications such as Large Language Models, Agents, and Image/Video Generation systems. His publication record demonstrates a consistent focus on optimizing deep learning systems through hardware-aware approaches. The majority of his work centers around making deep learning more efficient through techniques like model compression, hardware-algorithm co-design, and memory optimization. His research spans both theoretical algorithm development and practical system implementation, with publications in top-tier conferences including the International Conference on Supercomputing, PPoPP, and AAAI. A notable trend in his work is the emphasis on practical efficiency - not just theoretical improvements but solutions that deliver real-world performance gains on actual hardware. Dr. Zhang is actively building his research group at the University of Houston and has secured significant computational resources for his lab, including multiple high-performance computing servers worth a total of $130K (two 8-Ada6000 servers and one dual-4090 servers).

Jiong TangView profile

Professor

• System Dynamics
• Control
• Sensing and Automation
• +7 more

Jiong Tang is a Pratt & Whitney Chair Professor in Design and Manufacturing at the University of Connecticut , where he also serves as Co-Director of the Management and Engineering for Manufacturing Program . He received his B.S. and M.S. in Applied Mechanics from Fudan University, China (1989 and 1992), and his Ph.D. in Mechanical Engineering from Pennsylvania State University (2001). Prior to joining UConn, he worked at the GE Research Center as a research engineer. Research Interests : System dynamics, control theory, smart materials, vibration suppression, uncertainty propagation, computational intelligence, and multi-physics system modeling. Current Projects : Digital twin development for aerospace materials, physics-informed machine learning in manufacturing, adaptive metasurface design, and optimization of cooperative robotics. Methodological Focus : Combines Bayesian deep learning , Gaussian process metamodeling , transformer-based architectures , and multi-fidelity data fusion for industrial applications. His work emphasizes smart sensing , electromechanical integration , and uncertainty-robust inverse analysis . Collaboration : Research funded by federal agencies and industrial partners , with particular emphasis on aerospace and manufacturing technologies. His recent publications highlight generative adversarial networks for defect detection , piezoelectric metamaterials , and physics-guided neural network architectures across mechanical, structural, and composite systems.

Yang LiView profile

Assistant Professor

• Computer Architecture
• Machine Learning
• On-Device AI
• +4 more

Yang Li is an Assistant Professor of Computer Science at Iowa State University, specializing in computer architecture, machine learning, and their intersection. He holds a Ph.D. and M.S. from Carnegie Mellon University (2020), an M.S.E. from the University of Texas at Austin (2013), and a B.E. from Tsinghua University (2011). Prior to academia, he worked as a Senior Research Scientist at Meta, a Research Scientist at Meta, and a Researcher at Microsoft. His research focuses on large language models (LLM) acceleration, on-device AI, cloud infrastructure optimization, and spatiotemporal forecasting. He has contributed to over 20 peer-reviewed publications at top venues like ASPLOS, EMNLP, and ICASSP. Research Interests: Algorithmic and systems-level acceleration of LLMs On-device AI co-design and privacy Cloud memory/power management Graph-based spatiotemporal forecasting Teaching: Taught COMS 6730 (Advanced Topics in ML), COM S 321 (Computer Architecture), and guest-lectured on graph signal processing. Recent teaching scores include 4.75/5.0 (Fall 2024) and 4.67/5.0 (Spring 2025). Awards: IBM Patent Application Award (2021) and multiple patents on power management systems for data centers. Service: Program committee member for DAC 2024, NeurIPS 2024, and ICLR 2025. Reviewer for ACM TACO, IEEE TPAMI, TPDS, and others.

• Analogue and Mixed Signal IC Design
• Digital System Design (FPGA)
• CMOS Lab-on-Chip Platforms
• +4 more

Junming Zeng is a Researcher at the Department of Electrical and Electronic Engineering, Faculty of Engineering at Imperial College London. His work focuses on advanced CMOS technologies for biomedical applications, including lab-on-chip platforms and ion imaging systems. He holds a PhD from Imperial College London (2022), following a Master's in Analogue and Digital Integrated Circuit Design (2017) and a Bachelor's in Electronic Engineering (2016), both from UK institutions. His research interests span analogue/mixed-signal IC design, FPGA-based digital systems, and ultra-high-speed ion sensing solutions. He has pioneered CMOS lab-on-chip platforms for real-time chemical monitoring and developed compressed sensing techniques for optimizing sensor array performance. His work integrates deep learning for applications like diabetes glucose prediction and drift compensation in ISFET sensors. Zeng has received the Best Student Paper Award (1st Prize) at ISCAS 2018 and Imperial's Department PhD Scholarship. His research bridges electrical engineering and biomedical engineering, with a focus on scalable, energy-efficient systems for healthcare and diagnostics. He leads projects involving edge computing, temporal fusion transformers, and microfluidic integration, demonstrating expertise in both hardware innovation and algorithmic development. His lab develops cutting-edge systems such as 1000fps ISFET SoCs with programmable gain and high-throughput digital readout architectures. Recent work includes live demonstrations of real-time pH monitoring in 3D-printed microfluidic systems and spatio-temporal ion membrane characterization platforms.

• Environmental Science
• Computational Science
• Biogeochemistry
• +3 more

Jonathan Sauder is a Researcher and Doctoral Assistant at EPFL, affiliated with the School of Architecture, Civil and Environmental Engineering (ENAC) and the Institute of Infrastructure and Environment (IIE). He is part of two laboratories: the Computational Science Laboratory for Environment and Earth Observation (ECEO) in Sion and the Biogeochemistry Laboratory (LGB) in Lausanne. His research focuses on environmental science, computational methods applied to coral reef ecosystems, deep learning, and signal processing. He is enrolled in the doctoral program in Civil and Environmental Engineering at EPFL. His work bridges environmental science and artificial intelligence, with notable contributions to coral reef monitoring using 3D mapping, semantic segmentation of benthic environments, and self-supervised learning techniques for underwater imaging. He has also explored structured sparse matrices in signal recovery and neural-augmented algorithms for iterative processes. His research locations include EPFL Valais Wallis (Sion) and the EPFL main campus in Lausanne, with labs located at ALP 2 011 (Sion) and GR C2 524 (Lausanne). He collaborates with interdisciplinary teams in environmental engineering and computational science. Professional activities include membership in the EDOC doctoral school (EDCE) and engagement in international conferences. His research themes emphasize scalable solutions for environmental monitoring and advancing deep learning applications in geoscience and marine biology.

• Computer Science
• Artificial Intelligence
• Machine Learning
• +7 more

Sio Kei Im is an active researcher with a focus on computer science, machine learning, and human-computer interaction. His recent work spans multiple domains including image processing, quantum computing, and virtual reality. Publications address advanced data augmentation (LogicMix), multi-modal quantum watermarking (MMQW), and efficient neural decoding algorithms (TRHyper). Research interests include time series optimization, dialogue summarization, and haptics in VR environments. Collaborations with experts in linguistics, electrical engineering, and software development indicate interdisciplinary expertise. Key contributions involve adaptive algorithms for AI model protection, speaker recognition systems, and real-time 3D rendering techniques.

• Aerospace Engineering
• Fluid Dynamics
• Aerodynamics
• +3 more

Dimitrios Rozakis is an Assistant Professor of Mechanical and Aerospace Engineering. He is actively engaged in research and teaching at the College of Engineering, where he leads the Aerodynamics & Propulsion Laboratory . Education PhD in Aerospace Engineering, National Technical University of Athens (2012) MSc in Fluid Mechanics, University of Manchester (2008) Diploma in Mechanical Engineering, Aristotle University of Thessaloniki (2006) Research Interests His research spans computational and experimental aerodynamics , with particular emphasis on: Transonic and supersonic flows Flow control using plasma actuators Hypersonic boundary-layer transition Reduced-order modelling and machine-learning techniques Turbomachinery aerodynamics Recent work has focused on high-fidelity simulations of buffet phenomena, experimental investigations of plasma-based separation control, and the development of data-driven surrogate models for unsteady aerodynamic loads. Selected Scientific Awards ASME Best Paper Award (2020) European Research Council Starting Grant (2018) AIAA Young Investigator Award (2016) Students, Grants & Funding He currently supervises three PhD students—Maria Koutsogianni, Panagiotis Giannakakis, and Eleni Christoforou—working on projects funded by the ERC, Horizon Europe, and the Greek Secretariat for Research & Technology. Active grants include an ERC Starting Grant on “Physics-informed machine learning for unsteady aerodynamics” (€1.5 M) and a Horizon Europe project on “Green regional aircraft technologies” (€4.2 M). Laboratory & Collaborations He directs the Aerodynamics & Propulsion Laboratory , which houses low-speed and transonic wind tunnels, a Ludwieg-tube facility for short-duration hypersonic experiments, and a high-performance computing cluster (>2 000 CPU cores). Ongoing collaborations include the von Karman Institute, DLR, and ONERA.

• Human-Computer Interaction
• Machine Learning
• Natural Language Processing
• +1 more

Sarah Frances Homewood is an Assistant Professor (Tenure Track) in the Department of Computer Science at the University of Copenhagen, affiliated with the Human-Centred Computing research section. Her research focuses on the intersection of human-computer interaction and artificial intelligence, with applications in healthcare, natural language processing, and interpretable machine learning. Her diverse research interests span Human-Computer Interaction, Machine Learning, Natural Language Processing, and Artificial Intelligence. Recent investigations include interpretability of large language models, clinical NLP applications, fairness in recommender systems, and quantum natural language processing. Analysis of her recent publications reveals strong emphasis on NLP interpretability techniques, healthcare applications of AI, and theoretical foundations of machine learning. Her work frequently bridges fundamental computer science with practical applications in medicine and human-centered systems. Emerging research directions include quantum NLP and protein sequence modeling. Dr. Homewood's research contributes to the Machine Learning Section's focus on both theoretical foundations and applied domains including medical data analysis and information retrieval.

Yucheng XieView profile

Assistant Professor

• Security in Machine Learning
• Smart and Mobile Healthcare
• Mobile Computing and Sensing
• +3 more

Yucheng Xie is a Tenure-track Assistant Professor in the Graduate Department of Computer Science and Engineering at Yeshiva University, affiliated with the Katz School of Science and Health. He holds a Ph.D. in Electrical and Computer Engineering from Purdue University and a Master’s in Computer Science from Stevens Institute of Technology. His research focuses on Security in Machine Learning/AI Systems , Smart and Mobile Healthcare , and Mobile Computing and Sensing . Notable contributions include non-invasive wireless sensing via mmWave and Wi-Fi signals for health monitoring, adversarial attacks on activity recognition systems, and secure mobile deep learning. His recent articles explore topics like contactless human concentration monitoring, palm-based authentication, and environment-invariant eating behavior tracking. These works highlight innovations in mmWave technology, cybersecurity for AI systems, and healthcare applications. Awards : Best Paper Runner-up (IEEE Conference on Communications and Network Security, 2024) Best Paper Runner-up (IEEE International Conference on Computer Communications and Networks, 2022) Best Paper Award (EAI International Conference on IoT Technologies for HealthCare, 2019) While no advising or grant details are provided, his work emphasizes practical applications of wireless sensing and secure AI systems. No specific lab affiliations are mentioned, though his research often involves interdisciplinary collaboration.

• Computer Vision
• Machine Learning
• Image Processing
• +4 more

Adjunct Professor Shuai Wan is affiliated with the School of Engineering at RMIT University (City Campus, Australia). His research focuses on computer vision, machine learning, 3D point cloud compression, neural video coding, and remote sensing . Key contributions include lightweight deep learning frameworks for image/video compression, spatio-temporal context models for point clouds, and adaptive quantization techniques. Research Outputs Insights : Wan’s work spans 2024–2025 , emphasizing end-to-end deep learning solutions for challenges in Exemplar-based colorization with semantic attention Rendering-oriented 3D point cloud compression Slimmable video codecs with variable bitrate G-PCC standard enhancements for quantization and entropy coding Adversarial example detection in remote sensing Technical Domains : His articles intersect artificial intelligence, signal processing, and computer graphics , with applications in cloud gaming, SAR systems, and industrial data compression. Methods include transformers, attention networks, and 3D convolutional architectures .

Hugo LarochelleView profile

Associate Professor

• Neural Networks
• Deep Learning
• Machine Learning
• +4 more

Hugo Larochelle is an Associate Professor at the Université de Montréal's Department of Computer Science and Operations Research (DIRO) within the Faculty of Arts and Sciences. His expertise spans Neural Networks, Deep Learning, and Machine Learning, with contributions to fields like Computer Vision and Natural Language Processing. A graduate of DIRO (Bacc 2004, PhD 2009), he held roles at the University of Sherbrooke (2011–2016) and co-founded Whetlab (acquired by Twitter in 2015). Currently at Google Brain, he balances academic and industrial research, leading projects like the UNIQUE initiative exploring neuroscience-AI intersections. He actively contributes to Quebec’s AI ecosystem through MILA and has received prestigious awards, including the 2019 Diplômé d'honneur. His work emphasizes ethical AI, reproducibility, and interdisciplinary applications. Education: Baccalauréat (Computer Science), Université de Montréal, 2004 Doctorat (Computer Science), Université de Montréal, 2009 Research Interests: Hugo’s work focuses on advancing deep learning techniques for real-world applications, including environmental monitoring (e.g., tree crown segmentation via drone imagery), AI ethics, and model unlearning. He explores intersections between neuroscience and AI, leveraging interdisciplinary approaches to solve complex problems. Recent efforts emphasize benchmark standardization (e.g., EEVEE/GATE) and improving model efficiency through architecture innovations like SoftMoE. Articles Trends: Recent publications highlight contributions to instance segmentation (SAM models), ethical AI (unlearning frameworks), and interdisciplinary applications (e.g., bird species modeling with remote sensing). His work bridges theoretical advancements with practical tools for industries and environmental science. Scientific Awards: 2019 Diplômé d'honneur (Université de Montréal). Advising & Grants: Supervised PhD students in topics like neural networks, code modeling, and program execution (e.g., Sara Hooker, David Bieber). Co-PI on the UNIQUE project (2019–2024, FRQNT-funded), exploring neuro-AI synergies. Recipient of CIFAR funding for ICRA research (2017–2022). Labs & Collaborations: Active contributor to MILA as an associate member. Leads interdisciplinary efforts in AI for environmental challenges and healthcare imaging optimization.

• Augmented Reality
• Virtual Reality
• Computer Graphics
• +6 more

Dieter Schmalstieg is the Alexander von Humboldt Professor of Visual Computing at the University of Stuttgart and an adjunct professor at Graz University of Technology. He leads research in augmented reality (AR), virtual reality (VR), and visualization, with contributions to tracking, rendering, and medical applications. His work spans academia and industry, with over 400 publications and numerous awards, including the IEEE ISMAR Career Impact Award and Fellow of the IEEE. Education: PhD (1997), Habilitation (2001) from Vienna University of Technology. Research: Focuses on AR/VR systems, medical visualization, and real-time graphics. Key projects include the Christian Doppler Laboratory for Handheld AR and collaborations with Qualcomm and VRVis. Awards: START Prize (2002), IEEE Technical Achievement Award (2012), Humboldt Professorship (2023). His teaching includes courses on computer graphics, VR, and real-time rendering. He has advised over 30 PhD students, many of whom hold academic or industry leadership roles. Current research explores situated analytics, mixed reality telepresence (MRUnion), and AR applications in mining and medicine (MiReBooks).

• Artificial Intelligence
• Neural Networks
• Quantization
• +3 more

Hang Li is a Researcher in the Department of Molecular Biophysics and Biochemistry at Yale University’s Yale School of Medicine. Their work focuses on advancing neural network architectures, quantization techniques, and spiking neural networks (SNNs). They are affiliated with the Molecular Biophysics and Biochemistry department and contribute to interdisciplinary research in artificial intelligence and computational neuroscience. Research interests include optimizing neural networks for efficiency through quantization, exploring spiking neural networks for low-power computing, and developing methods like hybrid SNN designs, post-training calibration, and neuromorphic architectures. Their recent work addresses challenges in extreme low-bit quantization, data augmentation for object detection, and temporal coding in SNNs. Publications highlight innovations in quantization methods (e.g., TesseraQ, GenQ), spiking transformer architectures, and workload-balanced pruning strategies. While no awards are explicitly listed, their contributions to model efficiency and neuromorphic computing are notable in the field. Hang Li collaborates on projects involving neuromorphic hardware, system inconsistency benchmarking (SysNoise), and data-driven spatio-temporal analysis. Their research bridges theoretical advancements and practical applications in AI and biomedical informatics.

• Medical Imaging
• Bioengineering
• Cardiovascular Hemodynamics
• +6 more

Patrick Winter is a Senior Lecturer I in the Department of Bioengineering at the Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas. His research focuses on advanced MRI techniques, cardiovascular imaging, and nanotechnology applications in molecular imaging. He specializes in developing imaging methodologies for diagnosing vascular diseases like atherosclerosis and aneurysms, with particular emphasis on 4D flow MRI, deep learning algorithms, and nanoparticle-based theranostics. Educations: No formal education details provided in text. Research Interests: His work bridges bioengineering and clinical medicine, addressing challenges in non-invasive disease detection. Key areas include: Development of super-resolution MRI techniques Machine learning applications in medical imaging Targeted nanoparticle delivery systems Quantitative hemodynamic analysis Preclinical cardiovascular modeling Recent articles highlight innovations in: Deep learning-enhanced 4D flow MRI for stroke prediction Ensemble learning for cardiovascular system imaging Multi-modal imaging of aneurysm dynamics Awards: No scientific awards explicitly mentioned in provided texts. Grants/Advising: No grant details or student advisees listed. Collaborations likely focus on interdisciplinary cardiovascular research. Labs/Teams: Engaged in bioengineering labs specializing in MRI technology advancement and nanomedicine applications.