Find Academic Supervisors

Erik B. SudderthView profile

Professor

• Machine Learning
• Computer Vision
• Statistical Inference
• +3 more

Erik B. Sudderth is a Professor of Computer Science and Statistics and Chancellor's Fellow at the University of California, Irvine (UCI). He leads the Learning, Inference, & Vision Group and directs multiple research centers, including the UCI Center for Machine Learning and Intelligent Systems and the HPI Research Center in Machine Learning and Data Science. He previously served as an Associate Professor at Brown University. Education: B.S. (summa cum laude) in Electrical Engineering from UC San Diego (1999), M.S. and Ph.D. in EECS from MIT (2002, 2006). His research focuses on statistical methods for scalable machine learning, Bayesian nonparametrics, probabilistic graphical models, and applications in computer vision, AI, and environmental science. Key areas include nonparametric clustering, deep generative models, and particle-based inference algorithms. Research interests span diverse topics: advancing Bayesian nonparametric models for medical time series, scalable variational inference, and AI ethics. Notable contributions include the NET-VISA seismic monitoring system (ISBA Mitchell Prize, 2014), the BNPy toolbox (NSF CAREER Award), and work on diverse particle max-product algorithms for continuous inference. Scientific awards include the NSF CAREER Award, ISBA Mitchell Prize, and recognition as one of "AI's 10 to Watch" (IEEE). He has served as editor for top journals (JMLR, IEEE PAMI) and conference chairs (NeurIPS, CVPR). His work bridges theory and practice, with applications in robotics, climate science, and healthcare. Labs/Teams: UCI Learning, Inference, & Vision Group; UCI Center for Machine Learning; CREATE Technology Center. Grants include NSF funding for visually impaired collaboration tools and soil biogeochemical modeling.

• Machine Learning
• Deep Learning
• Theoretical Foundations of AI
• +11 more

Mikhail (Misha) Belkin is a Professor at the Halicioglu Data Science Institute (HDSI) at the University of California San Diego , with an affiliated appointment in the Department of Computer Science and Engineering . He is also an Amazon Scholar , reflecting his impactful industry collaboration. Since January 2024, he has served as the Editor-in-Chief of the SIAM Journal on Mathematics of Data Science (SIMODS) . Research Interests: Belkin's research centers on the theoretical foundations of machine learning, particularly the mathematical understanding of modern deep learning. His work investigates interpolation , over-parameterization , and feature learning in neural networks. He is renowned for introducing the double descent risk curve, which reconciles classical bias-variance trade-offs with the success of overfitted models. His recent work identifies the Average Gradient Outer Product (AGOP) as a fundamental mechanism of feature learning, applicable across architectures like CNNs and transformers. Scientific Contributions and Trends: His recent publications, appearing in Science , PNAS , and NeurIPS , demonstrate a strong trend toward unifying theories of generalization and optimization in over-parameterized systems. He explores how interpolating models can be statistically optimal, how gradient descent converges in non-convex landscapes via the PL* condition, and how kernel methods can be enhanced to perform feature learning. ACM Fellow (2023) Editor-in-Chief, SIAM Journal on Mathematics of Data Science (2024–present) Advising and Grants: Belkin actively mentors students and collaborators such as Adityanarayanan Radhakrishnan , Daniel Beaglehole , and Chaoyue Liu , who are frequent co-authors. He is a Principal Investigator (PI) in the Collaboration on the Theoretical Foundations of Deep Learning , funded by the NSF and Simons Foundation. He is also an external collaborator with the Eric and Wendy Schmidt Center at the Broad Institute and part of the NSF-funded TILOS AI Institute . Laboratories and Teams: While not explicitly named, his research group at UCSD is deeply involved in theoretical machine learning, focusing on the intersection of statistics, optimization, and deep learning. His work often involves large-scale collaborations and is closely tied to initiatives like SIMODS and TILOS.

Nanpeng YuView profile

Professor

• Smart Grid
• Power Systems
• Data-Driven Optimization
• +7 more

Dr. Nanpeng Yu is a Full Professor at the University of California, Riverside , serving as Vice Chair and Graduate Advisor in the Department of Electrical and Computer Engineering . He maintains cooperative faculty affiliations with the Department of Computer Science and Department of Statistics , and directs the Energy, Economics, and Environment Research Center at UCR. Education : B.S. in Electrical Engineering from Tsinghua University (2006), M.S. in Electrical Engineering and Economics, and Ph.D. from Iowa State University (2010) Prior Industry Experience : Senior Power System Planner and Project Manager at Southern California Edison (2011-2014) Dr. Yu’s research bridges smart grid technologies , data-driven optimization , and machine learning for energy systems. Key areas include voltage control , renewable energy integration , transportation electrification , and grid resilience . His recent work focuses on physics-informed graph learning for unit commitment problems and adversarial purification in power system classifiers. The AI-Energy Nexus Laboratory under Dr. Yu has produced impactful publications in Applied Energy , IEEE Transactions on Power Systems , and Transportation Research series, covering topics like heavy-duty EV charging infrastructure and dynamic distribution network reconfiguration . Lab members have won the American-Made Digitizing Utilities Grand Prize ($300,000) from the U.S. DOE. Leadership Roles : Chair, IEEE Power and Energy Society Distribution System Operation and Planning Subcommittee Chair, IEEE Power and Energy Society Working Group on Data-Driven Modeling for Power Distribution Networks Associate Editor, IEEE Transactions on Smart Grid and IEEE Power Engineering Letters Scientific Awards : Regents Faculty Fellowship Regents Faculty Development Award Multiple IEEE Best Paper Awards

Elliott AshView profile

Associate Professor

• Law and Economics
• Political Economy
• Econometrics
• +5 more

Elliott Ash is an Associate Professor of Law, Economics, and Data Science at ETH Zurich's Center for Law & Economics. He holds a Ph.D. in Economics and J.D. from Columbia University, a B.A. in Economics, Government, and Philosophy from the University of Texas at Austin, and an LL.M. in International Criminal Law from the University of Amsterdam. His research focuses on empirical legal studies using econometrics, NLP, and ML, examining topics like judicial behavior, legislative impact, and AI-driven governance. He has been funded by the ERC, Swiss NSF, and others. Research Interests: Elliott explores automation of legal decisions, text-as-data analysis in law, and the intersection of AI with legal systems. He develops tools like BallotBot and LePaRD to enhance legal transparency and public understanding. His work bridges law, economics, and computer science, with publications in top journals like the American Economic Journal and Review of Economics and Statistics . Teaching: Courses include Building a Robot Judge , Natural Language Processing for Law , and Big Data for Public Policy . He co-organizes the Zurich Workshop in AI+Economics and Monash-Warwick-Zurich Text-as-Data Workshops. Awards: European Research Council Starting Grant, Swiss National Science Foundation Grant, and multiple grants from U.S. and Swiss institutions. His work has been featured in NPR , VoxEU , and Georgetown Law Journal . Labs/Teams: Leads the Swiss AI Initiative's Human-AI Alignment team, collaborates with the CEPR on Political Economy research, and serves as an Economic Journal Associate Editor.

• Trustworthy Machine Learning
• Conformal Prediction
• Explainable Artificial Intelligence
• +2 more

Henrik Boström is a Professor of Computer Science specializing in Data Science Systems at the Division of Software and Computer Systems, KTH Royal Institute of Technology. His research focuses on trustworthy machine learning , with emphasis on conformal prediction (for confidence-calibrated predictions) and explainable AI . He is the developer of Python packages crepes (conformal classifiers/regressors) and xrf (explainable random forests). His primary research domains include: Developing robust methods for uncertainty quantification in predictive models Creating interpretable machine learning frameworks Optimizing ensemble techniques for high-dimensional data Applying ML to healthcare informatics and industrial diagnostics Analysis of his recent publications reveals strong emphasis on: (1) advancing conformal prediction theory for trustworthy AI, (2) enhancing interpretability of complex models like random forests and GNNs, and (3) developing efficient algorithms for uncertainty-aware learning in domains including healthcare, graph data, and high-dimensional regression. He serves as examiner for multiple degree projects and teaches courses including Programming for Data Science (ID2214) and Research Methodology and Scientific Writing (II2202) . He leads development of open-source tools for conformal prediction and model interpretation.

Alfred O. Hero, IIIView profile

Professor

• Data Science
• Statistical Machine Learning
• Distributed Optimization
• +7 more

Alfred O. Hero, III is the John H. Holland Distinguished University Professor of Electrical Engineering and Computer Science and the R. Jamison and Betty Williams Professor of Engineering at the University of Michigan, Ann Arbor. He is currently on leave from the University of Michigan as a Program Director in the CISE Directorate at the National Science Foundation. His primary appointment is in the Department of Electrical Engineering and Computer Science (EECS), with secondary appointments in the Department of Biomedical Engineering and the Department of Statistics. He is also affiliated with the UM Center for Computational Medicine and Bioinformatics (CCMB), the UM Graduate Program in Applied and Interdisciplinary Mathematics (AIM), the UM Applied Physics Program, and the Michigan Institute for Data Science (MIDAS), which he co-founded from 2015-2018. Hero's research focuses on data science, developing theory and algorithms for multimodality data collection, fusion, analysis and visualization that use statistical machine learning and distributed optimization. His work has applications in wearable technologies for personalized health and predictive medicine, spatio-temporal networks in biology, climate, and social discourse, anomaly detection, and data analysis for international security. His recent research interests include high dimensional spatio-temporal data analysis, multimodal data integration, statistical signal processing, and machine learning, with particular emphasis on predictive mathematical models for biological and physical sciences, social networks, network security and forensics, and personalized health and disease. His recent publications demonstrate a strong focus on high-dimensional statistical methods, contrastive learning, neural network optimization, change detection in temporal graphs, and applications in microbiome analysis and epidemic modeling. The research spans theoretical foundations in information theory and statistical learning while addressing practical applications across multiple domains. Scientific Awards: IEEE Signal Processing Society Best Paper Award (1998) Best Original Paper Award from Journal of Flow Cytometry (2008) Best Magazine Paper Award from IEEE Signal Processing Society (2010) SPIE Best Student Paper Award (2011) IEEE ICASSP Best Student Paper Award (2011) IEEE Signal Processing Society Technical Achievement Award (2014) IEEE Signal Processing Society Society Award (2015) IEEE Fourier Award (2020) University of Michigan Distinguished Faculty Achievement Award (2011) Hero has advised over 60 PhD students and 30 postdocs in areas including modeling, computation, and inference for large scale time varying data in the biosciences. He has received significant research funding from the Department of Energy, Army Research Office, Air Force Office of Scientific Research, and National Science Foundation. He has held leadership positions including President of the IEEE Signal Processing Society (2006-2007), Director of Division IX (Signals and Applications) on the IEEE Board of Directors (2009-2011), and Chair of the Committee on Applied and Theoretical Statistics of the US National Academies (2018-2020).

Zhou Zhi-HuaView profile

Professor

• Artificial Intelligence
• Machine Learning
• Data Mining
• +3 more

Zhou Zhi-Hua is a Professor at Nanjing University's Department of Computer Science & Technology, serving as Standing Deputy Director of the National Key Lab for Novel Software Technology and Founding Director of LAMDA (Institute of Machine Learning and Data Mining). He holds simultaneous fellowships from ACM, AAAI, AAAS, IEEE, IAPR, IET/IEE, and CCF, reflecting his exceptional contributions to computational intelligence. His educational background includes: B.Sc. in Computer Science from Nanjing University (1996) M.Sc. in Computer Science from Nanjing University (1998) Ph.D. in Computer Science from Nanjing University (2000) Zhou's research pioneers fundamental advances in machine learning theory and applications. His seminal work on ensemble methods established new frameworks for classifier combination, while innovations in multi-label learning and anomaly detection addressed critical challenges in complex data analysis. His research bridges theoretical rigor with practical implementations across diverse domains including biometrics, data mining, and computer vision, resulting in over 150 publications and 18 patents. His textbooks "Ensemble Methods" (2012) and "Machine Learning" (2016) have become standard references in the field. Analysis of his publication trajectory reveals sustained leadership in core machine learning challenges: evolving from neural network ensembles (2002) through semi-supervised learning breakthroughs (2005) to foundational work on multi-instance learning (2012) and theoretical margin analysis (2013). His recent focus demonstrates increasing sophistication in handling complex data structures while maintaining theoretical soundness. His scientific excellence is recognized through: National Natural Science Award of China (2013) PAKDD Distinguished Contribution Award (2016) IEEE ICDM Outstanding Service Award (2016) IEEE CIS Outstanding Early Career Award (2013) Microsoft Professorship Award (2006) Simultaneous fellowships from 7 major international societies Zhou provides extraordinary service to the academic community as Executive Editor-in-Chief of Frontiers of Computer Science and Associate Editor-in-Chief of Science China Information Science. He founded the ACML conference and has chaired premier events including ICDM'16 and PAKDD'14. His leadership extends to serving as General Chair for ICDM'16, Program Chair for IJCAI'15 Machine Learning Track, and Area Chair for multiple top conferences. The available text does not specify student advising details or research grants. He directs LAMDA research group at Nanjing University, which has established itself as a global powerhouse in machine learning research, and contributes significantly to the National Key Lab for Novel Software Technology's mission of developing next-generation intelligent systems.

Naoki YoshinagaView profile

Associate Professor

• Natural Language Processing
• Computational Linguistics
• Multilingual and Multimodal NLP
• +4 more

Naoki Yoshinaga is a tenured Associate Professor at the Institute of Industrial Science, The University of Tokyo, with extensive experience in natural language processing and computational linguistics. He has held academic positions since 2008 and currently leads research on pragmatic NLP models and multilingual systems. PhD in Computer Science, The University of Tokyo (2005-2008) MSc in Information Science (2000-2002) BSc in Information Science (1996-2000) His research focuses on mechanistic interpretability in NLP models, multilingual/multimodal NLP , and efficient model design using trie structures and conjunctive features. He also investigates knowledge acquisition from social data and evaluation metrics for language generation . Recent publications include work on neuron empirical gradient analysis (ACL-25), multilingual knowledge representation (EACL-24), and compact embedding methods (CoNLL-24). His research has been funded by multiple grants, including the University of Tokyo Excellent Young Researcher program and JSPS fellowships. Committee Special Award, Association for NLP (2023) JSAI SIG Research Award (2022) Best Interactive Award, DEIM Forum (2019, 2016) He developed widely-adopted NLP tools like pecco (fast classification library), RenTAL (LTAG-to-HPSG grammar converter), and J.DepP (Japanese dependency parser). His lab emphasizes strong equivalence in formalism comparisons and pragmatic model design .

Lorenzo CavallaroView profile

Professor

• Trustworthy AI for Systems Security
• Adversarial Machine Learning
• Malware Detection
• +6 more

Lorenzo Cavallaro is a Full Professor of Computer Science at University College London (UCL), specializing in Trustworthy AI for Systems Security. His research focuses on developing learning-based methods that are robust against adversaries by understanding the interplay between program analysis, representations, and machine learning models. His research interests span multiple critical areas in cybersecurity, including adversarial machine learning, malware detection, program analysis, and security evaluation. Cavallaro's work particularly emphasizes the challenges of concept drift in security systems and the development of robust defenses against evolving threats. His research has significant implications for Android security, binary analysis, and memory safety in embedded systems. Analysis of his recent publications (2024-2025) reveals a strong focus on addressing fundamental challenges in ML-based security systems. His work spans malware detection systems that maintain reliability under distribution shifts, adversarial attacks in the problem space, context-driven approaches using LLMs for security applications, and temporal invariance in malware detection. A recurring theme is the critical examination of whether ML-based security systems are truly robust and reliable in real-world scenarios. Cavallaro serves in significant editorial and advisory roles including the NDSS Steering Group (2023-2026), Associate Editor for Computer & Security and ACM TOPS, and Scientific Advisory Board for SERICS. He has been actively involved in program committees for top security conferences including IEEE S&P, USENIX Security, CCS, and NDSS from 2021-2025. He teaches Malware (COMP0060; 2022—ongoing), Research in Information Security (COMP0057; 2021—23), and Computer Security 2 (COMP0055; 2021—ongoing) at UCL, contributing to the next generation of security researchers and practitioners.

• Algorithmic Fairness
• Responsible AI
• Deep Learning
• +7 more

Golnoosh Farnadi is an Associate Professor at the Department of Computer Science and Operational Research at the University of Montreal and an Assistant Professor at the School of Computer Science at McGill University. She holds a Canada-CIFAR Chair in Artificial Intelligence and serves as a Senior Academic Member at Mila - Quebec Institute for Artificial Intelligence. Her interdisciplinary work bridges computer science, operations research, and ethical AI considerations. Her educational background includes a Ph.D. in Computer Science from KU Leuven and Ghent University (2017), followed by postdoctoral positions at the University of Montreal/MILA (2018-2020) and the University of California, Santa Cruz (2017-2018). Her research focuses on algorithmic fairness, responsible AI, deep learning, and probabilistic models, with applications spanning healthcare, recommender systems, and public policy. Farnadi's recent publications demonstrate a strong emphasis on addressing fairness in machine learning systems, with particular attention to cultural diversity in recommender systems, fairness in healthcare optimization (particularly kidney exchange programs), and mitigating hallucinations in large language models. Her work consistently combines theoretical rigor with practical applications, often employing novel mathematical frameworks to tackle complex ethical challenges in AI. Among her notable recognitions are the Google Scholar Award (2021), Facebook Research Award (2021), Google Award for Inclusion Research (2023), and being named one of the 100 Brilliant Women in AI Ethics (2023). She was also recognized as a Rising Star in AI Ethics in 2021. Farnadi supervises numerous graduate students through her EQUAL Lab (EQuity & EQuality Using AI and Learning algorithms), which focuses on developing AI systems that promote fairness and equity. Her teaching includes courses on Responsible AI, Machine Learning, and Trustworthy Machine Learning at both McGill University and HEC Montreal.

Gauthier GidelView profile

Associate Professor

• Deep Learning
• Adversarial Machine Learning
• Generative Modeling
• +5 more

Gauthier Gidel is an Associate Professor at the Department of Computer Science and Operations Research (DIRO) within the Faculty of Arts and Science at Université de Montréal, where he also holds the prestigious Canada CIFAR AI Chair position. He is a core faculty member of Mila, Quebec's AI research institute, and maintains active research collaborations with leading institutions. His academic journey includes a PhD in Computer Science under the supervision of Simon Lacoste-Julien, with internships at Sierra, ElementAI, and DeepMind during his doctoral studies. Dr. Gidel's research spans multiple critical areas in machine learning, with particular emphasis on generative modeling , adversarial machine learning , and variational inequalities for machine learning. His work explores the intersection of optimization theory and practical AI systems, focusing on challenges like LLM safety alignment, multi-agent cooperation, and robustness against adversarial attacks. He is particularly known for his contributions to understanding the theoretical foundations of generative adversarial networks through variational inequality frameworks. His recent publications reveal a strong trend toward addressing critical challenges in large language model safety and alignment, with numerous 2024-2025 papers focusing on adversarial robustness, safety evaluation methodologies, and alignment techniques for LLMs. Simultaneously, his foundational work continues in optimization theory, particularly in variational inequalities and performative prediction, demonstrating his dual focus on practical AI safety concerns and theoretical machine learning foundations. Canada CIFAR AI Chair Core member of Mila Organizer of popular NeurIPS workshops on smooth games Co-founder of the ICLR blog post track Dr. Gidel actively supervises an extensive research group with approximately 10 current graduate students and numerous alumni who have secured positions at leading institutions including Inria Lyon, Oxford, and industry research labs. His research is supported by multiple substantial grants from CRSNG, MITACS, and IVADO, including the prestigious CRSNG Discovery Grant program and MITACS Acceleration Québec projects focused on fraud detection in music streaming and conditional generation. His laboratory maintains strong connections with both academic and industry partners, fostering a collaborative environment focused on advancing AI safety and theoretical understanding.

Stephen M. ShoreView profile

Associate Clinical Professor

• Autism and Asperger Syndrome
• Successful transition to adulthood
• Employment
• +5 more

Stephen M. Shore is a Clinical Associate Professor at Adelphi University's Ruth S. Ammon College of Education and Health Sciences, specializing in autism and Asperger Syndrome with expertise in educational practices, social inclusion, and successful transition to adulthood for individuals on the autism spectrum. Dr. Shore earned his Ed.D. in Education from Boston University (2008), M.A. in Music Education from Boston University (1992), and dual B.A. degrees in Music Education and Accounting and Information Systems from the University of Massachusetts at Amherst (1986). He holds professional teaching licenses in Music and Business Management for Massachusetts public schools (grades 5-12). His research focuses on multiple critical areas including successful transition to adulthood, employment opportunities, comparative approaches for treating children with autism, socially-based inclusion methods, self-advocacy development, teaching musical instruments to individuals on the spectrum, and international perspectives on autism diagnosis and treatment. His work uniquely bridges academic research with practical applications, informed by his personal experience as someone on the autism spectrum. Dr. Shore's publications demonstrate a consistent emphasis on practical applications of autism research across diverse contexts, with recurring themes in educational strategies, inclusion methodologies, and strength-based approaches that leverage individual capabilities rather than focusing on deficits. Member, Interagency Autism Coordinating Committee (2008-present) Vice President, Autism Society of America - Massachusetts Chapter (2007-present) Board Member, Autism Society of America - National (2001-2004, 2005-present) Former Board President, Asperger's Association of New England (2001-2006) As an educator, Dr. Shore teaches specialized courses including 'Diagnosis Of And Intervention In Autism,' 'Educating Students With Autism Classified At Level 1,' and 'Classroom Management,' emphasizing evidence-based practices that accommodate neurodiversity while promoting academic and social success.

Hossein ValaviView profile

Lecturer

• In-Memory Computing
• Neural Networks
• Hardware Acceleration
• +3 more

Hossein Valavi is a Lecturer and Assistant Director of Undergraduate Studies at Princeton University, contributing to advancements in computer architecture and hardware acceleration. His research focuses on in-memory computing, neural networks, and energy-efficient systems, with notable work in reconfigurable architectures and mixed-signal processing. He has received multiple teaching awards, including recognition for innovative pandemic-era Car Lab courses and collaborative work honored by the Edison Patent Award. His academic contributions span academic positions since 2018, emphasizing both research and pedagogical excellence. Key technical areas include scalable in-memory computing systems, analog neural network accelerators, and low-power matrix factorization algorithms. His work addresses critical challenges in data movement reduction and hardware-software co-design for modern computing systems. Awards: Teaching Excellence Awards (2021, 2023), Edison Patent Award (2023) Grants & Projects: Leading developments in in-memory computing accelerators and embedded microprocessor designs Research teams under his guidance have produced impactful IP in semiconductor layouts, CNN accelerators, and programmable architectures, aiming to bridge theoretical computer science with practical hardware implementations.

Jérôme SchererView profile

Researcher

• Algebraic Topology
• Homotopy Theory
• Neuroscience
• +3 more

Jérôme Scherer is a researcher at the École Polytechnique Fédérale de Lausanne (EPFL) affiliated with the Laboratory for Topology and Neuroscience under Prof. Kathryn Hess Bellwald. He has supervised multiple PhD students including Kay Werndli, Lyne Moser, Samuel Lavenir, Olivia Monjon, and Virgile Constantin. His research focuses on algebraic topology, homotopy theory, category theory, and homological algebra, with notable contributions to localization functors, crossed modules, conjugation spaces, and homotopy nilpotent groups. His recent publications analyze fiberwise localization, admissible reflections, and cohomological purity in topological spaces. He previously coordinated the Euler course program for gifted youth in French-speaking regions and taught Linear Algebra at EPFL until 2018. He serves on the editorial board of Algebraic and Geometric Topology and has organized international conferences like the Arolla Conference on Algebraic Topology.

Yingying ChenView profile

Professor

• Smart Healthcare
• Internet of Things (IoT)
• Cyber Security
• +7 more

Yingying (Jennifer) Chen is a Distinguished Professor and Department Chair in the Department of Electrical and Computer Engineering at Rutgers University, affiliated with the Wireless Information Network Laboratory (WINLAB) and the DAISY Lab. She holds a PhD in Computer Science from Rutgers University (2007). Her research focuses on Smart Healthcare, IoT, Cyber Security, Machine Learning, and AR/VR Security, with over 300 publications and multiple patents. Key roles include Associate Director of WINLAB, Fellow of ACM, IEEE, and AAIA, and recipient of the NSF CAREER Award (2010), Henry Morton Teaching Award (2017), and ACM Distinguished Scientist distinction. Awards also include the 2024 ACM Fellow and NAI Fellow (2022). Her work emphasizes interdisciplinary applications, such as AR/VR privacy attacks, adversarial machine learning defenses, and edge computing. Notable grants include NSF projects on AI on edge devices, NextG-enabled manufacturing, and healthcare system design. She advises Ph.D. students and collaborates with industry on testbeds like the Community-based Edge Sensing Testbed (NSF CCRI). Current research explores AI-driven sensing, privacy in immersive technologies, and robust multi-model analytics. Publications span top venues like ACM MobiCom, IEEE INFOCOM, and IEEE S&P. Labs include DAISY Lab (data analysis & security) and collaborations with WINLAB for wireless innovation. She serves on editorial boards of IEEE/ACM Transactions and organizes conferences like ACM MobiCom and IEEE ICDCS.