Find Academic Supervisors

Kwang Moo Yi is an Assistant Professor in the Department of Computer Science at the University of British Columbia (UBC), where he conducts research in computer vision and machine learning. He is affiliated with the Computer Vision Lab, CAIDA (Centre for Artificial Intelligence Decision-making and Action), and ICICS (Institute for Computing, Information and Cognitive Systems) at UBC. Education: B.Sc. from Seoul National University Ph.D. from Seoul National University under Prof. Jin Young Choi Post-doctoral researcher at École Polytechnique Fédérale de Lausanne (EPFL) with Prof. Pascal Fua and Prof. Vincent Lepetit Dr. Yi's research focuses on Visual Geometry with the goal of understanding local environments, adapting to them, and acting within them. His work spans applications in autonomous vehicles, drones, robots, and Augmented/Mixed Reality systems. He employs machine learning, particularly deep learning, as the primary tool for advancing computer vision capabilities. His recent publications demonstrate a strong focus on neural rendering techniques, especially 3D Gaussian Splatting and Neural Radiance Fields (NeRF). The research trends show increasing sophistication in handling occlusions, improving rendering quality, and developing more efficient training methods for neural fields. There's also significant work connecting computer vision with practical applications in industrial settings and energy systems. Dr. Yi serves as an area chair for top computer vision and machine learning conferences including CVPR, ICCV, ECCV, NeurIPS, ICML, and AAAI. He was part of the organizing committee for CVPR 2023. He supervises graduate students including Eric (who recently completed his PhD), Gopal (now at Samsung Research), and Jeong-Gi (joining as a postdoctoral fellow). His teaching includes CPSC 425: Computer Vision and CPSC 533Y: 3D Computer Vision with Deep Learning. Dr. Yi is actively involved with the Computer Vision Lab at UBC, collaborating with researchers across CAIDA and ICICS. His work bridges theoretical computer vision with practical applications in various domains including astronomy, industrial automation, and energy systems.

• 3D Computer Vision
• Computer Vision
• Machine Learning
• +4 more

Professor Ian Davidson is a faculty member in the Department of Computer Science at the University of California Davis, College of Engineering. His research focuses on machine learning, data mining, and constraint programming, with applications in neuroscience, healthcare, and social networks. He emphasizes rigorous algorithm design and human-in-the-loop learning paradigms. Editorial Board Member: ACM TKDD, IEEE TKDE, Springer DMKD Conference Leadership: PC Chair (SDM 2012), Vice/Area Chair (IEEE ICDM, ACM KDD, SIAM DM, ECML/PKDD 2013-2015) Research Interests: Human-in-the-loop learning (active, transfer, and transductive frameworks) Constraint programming and spectral methods for clustering and classification Applications in neuroimaging analysis, intelligent tutoring systems, and social impact domains Fairness in machine learning and clustering algorithms Tensor decomposition and matrix factorization techniques Interdisciplinary collaborations in neuroscience and healthcare Recent publications highlight his work on fairness-aware clustering with constraint programming, advanced spectral methods for brain connectivity analysis, and explainable AI frameworks. His research often combines theoretical rigor with practical applications in clinical domains. Scientific Awards: Best Paper Award, SIAM Data Mining Conference 2005 Best Paper Award, ECML/PKDD 2006 Best Paper Award, ICDM 2006 Students & Collaborators: Former students: Xiang Wang (IBM Watson), Buyue Qian (Xi'an Jiaotong University), Tom Kuo (Google), Sean Gilpin (Google) Current advisees: Aubrey Guess, Zilong Bai, Erin McGinnis, Zheng Fang, Hongjing Zhang

• Machine Learning
• Data Mining
• Constraint Programming
• +6 more

Georgia Zellou is an Associate Professor in the Department of Linguistics at the University of California, Davis, where she co-directs the Phonetics Lab and conducts award-winning research at the intersection of phonetics, speech perception, and human-AI interaction. Her work investigates how phonetic detail is cognitively represented through variations in speech production, with significant contributions to understanding speech alignment with voice assistants, face-masked speech intelligibility, and cross-linguistic perception of synthetic voices. Her academic credentials include a Ph.D. in Linguistics from the University of Colorado at Boulder (2012), an M.A. in Linguistics from Stony Brook University (2007), and a B.A. in Linguistics & Anthropology from the University of Florida (2005, Cum Laude, Phi Beta Kappa). Ph.D., Linguistics, University of Colorado at Boulder (2012) M.A., Linguistics, Stony Brook University (2007) B.A., Linguistics & Anthropology, University of Florida (2005) Professor Zellou's research program centers on laboratory phonology approaches to real-world communication challenges, examining how acoustic-phonetic details influence speech perception across contexts. Her studies span speech alignment with voice-AI systems (e.g., Amazon Alexa), sociophonetic variation in bilingual speech, and the cognitive mechanisms underlying perceptual compensation for coarticulation. She employs experimental methods including eye-tracking, acoustic analysis, and perceptual testing to uncover how phonetic variation functions pragmatically in human communication and human-machine interaction. Analysis of her 15 most recent publications (2023-2025) reveals three dominant research trajectories: (1) human-AI voice interaction dynamics, including prosodic alignment and social evaluation of TTS voices; (2) intelligibility optimization in challenging contexts (face masks, clear speech for diverse listeners); and (3) cross-linguistic phonetic variation in vowelless words and consonant clusters. These works consistently bridge theoretical phonology with applied speech technology, demonstrating how fine-grained phonetic detail influences communication effectiveness in both human-human and human-machine contexts. Her scientific recognition includes: Fulbright Scholar (2022) for research in France Chancellor’s Award for Excellence in Undergraduate Mentoring (2019) Fellow of the Linguistic Society of America (2020) Amazon Faculty Research Award (2019) for Alexa-related speech studies Dean’s Fellow designation at UC Davis (2020-2023) Professor Zellou maintains an active mentoring practice recognized with the Chancellor’s Award, supervising undergraduate researchers in the Phonetics Lab while teaching core linguistics courses from introductory to advanced graduate levels. Her research program is supported by competitive grants including NSF funding, Amazon Research Awards, and UC Davis internal grants (Hellman Foundation, ISS Junior Faculty Grant), reflecting the translational value of her work for speech technology development. She has co-directed major initiatives including the 2019 LSA Linguistic Institute. The Phonetics Lab she co-leads serves as a hub for experimental phonetics research, focusing on speech production-perception relationships through projects investigating vocal accommodation to voice assistants, nasal coarticulation dynamics, and cross-linguistic prosody. Current collaborations with industry partners aim to implement human speech adaptation principles into voice assistant design to enhance naturalness and engagement.

• Phonetics
• Speech Perception
• Laboratory Phonology
• +3 more

Colin J Akerman is Professor of Neuroscience and Group Leader in the Department of Pharmacology at the University of Oxford, concurrently serving as Corange Fellow and Medical Tutor at Corpus Christi College. His research investigates fundamental mechanisms of synaptic circuit formation and plasticity, with direct implications for epilepsy, dementia, and schizophrenia through multidisciplinary approaches integrating electrophysiology, optical imaging, and computational modeling. His primary research interests encompass Synaptic Plasticity, Neural Circuit Formation, and Excitatory-Inhibitory Balance, with specific focus on neuronal progenitor influences on connectivity, chloride dynamics in inhibitory transmission, and learning mechanisms in disease contexts. The lab employs custom-built equipment and molecular tools to probe synaptic function across in vivo , in vitro , and in silico platforms, emphasizing how activity-dependent processes shape neural networks during development and disease. Recent publications (2023-2025) reveal strong thematic convergence on intracellular chloride regulation in sleep-wake cycles, cortical circuit assembly from embryonic progenitors, and innovative optical tools for neural monitoring. This work bridges molecular neuroscience with systems-level understanding of synaptic plasticity, particularly regarding ionic mechanisms in epilepsy and sleep homeostasis. No scientific awards or fellowships are explicitly documented in the source materials. Professor Akerman currently mentors four PhD students (Vourvoukelis, Selfe, Wang, Gemayel) and multiple postdoctoral researchers, having previously trained scientists now leading independent groups in Toronto, Edinburgh, Cape Town, Oxford, and London. His research is funded by the European Research Council, Innovative Medicines Initiative, and Wellcome Trust, supporting investigations into synaptic mechanisms underlying neurological disorders. The Akerman Group, established in 2008, operates as an integrative neuroscience hub within Oxford's Pharmacology Department. The 10-member team combines expertise in patch-clamp electrophysiology, optogenetics, multiphoton imaging, and computational modeling, with current projects spanning neuronal progenitor biology, inhibitory synaptic plasticity, and learning rule implementation in neural networks. The lab emphasizes technical innovation, regularly developing custom instrumentation and molecular tools for neural observation and manipulation.

• Neuroscience
• Synaptic Plasticity
• Neural Circuit Formation
• +4 more

Jay David Bolter holds the Wesley Chair of New Media and serves as Professor and Director of Computational Media at the Georgia Institute of Technology, where he is affiliated with the School of Literature, Media, and Communication within the Ivan Allen College of Liberal Arts. A foundational figure in digital media studies, he is renowned for his influential theoretical works and practical contributions to new media forms. His research spans Augmented Reality , Virtual Reality , Digital Culture , and the History of Media , with particular emphasis on remediation theory (developed with Richard Grusin) and the evolution of digital writing. As an active member of the Augmented Environments Lab, Bolter creates narrative-driven AR applications for cultural heritage sites and educational contexts, blending theoretical rigor with experimental design. His work consistently examines how new media technologies reshape human perception and cultural practices. Recent publications reveal a concentrated exploration of reality media (AR/VR) as narrative spaces, with articles addressing biofeedback integration in VR fitness, agency-driven interactive storytelling, and theoretical frameworks for understanding immersive experiences. His scholarship bridges historical media analysis with cutting-edge technical implementation, demonstrating how remediation processes continue to evolve in mixed reality environments. This trajectory reflects his lifelong investigation into the interplay between technological capabilities and human expression. Bolter maintains significant collaborative partnerships, including co-authoring seminal texts like Remediation and developing the Storyspace hypertext system with Michael Joyce. His leadership in the Augmented Environments Lab drives interdisciplinary projects that merge humanities perspectives with technological innovation, particularly in creating culturally resonant AR experiences. Teaching responsibilities include advanced courses in mixed reality design, computational media, and digital media theory, shaping the next generation of media scholars and practitioners.

• Augmented Reality
• Digital Culture
• History of Media
• +3 more

Qing Cao is an Associate Professor of Materials Science and Engineering at the University of Illinois at Urbana-Champaign, with courtesy appointments in Chemistry and Electrical Engineering. He leads the Cao Research Group within the Grainger College of Engineering and serves as Deputy Editor of Science Advances. Dr. Cao received his B.S. in Chemistry from Nanjing University in 2004 and his Ph.D. in Materials Chemistry from the University of Illinois at Urbana-Champaign in 2009. After working for 9 years as a research scientist at IBM Thomas J. Watson Research Center, he returned to UIUC in 2018 as a faculty member. His research focuses on developing functional nanomaterials for unconventional electronic systems, high-performance logic devices, and low-cost energy harvesting. The Cao Research Group specifically works on: nanoelectronic devices based on novel nanomaterials; next-generation memory devices for neuromorphic and in-memory computing; monolithic 3D integration for high performance electronics; high-performance printable electronic materials; and bioelectronics for healthcare applications. His work bridges materials science, chemistry, electrical engineering, and device physics. Analysis of Dr. Cao's recent publications reveals a strong focus on electrochemical memory devices for neuromorphic computing, with significant work on carbon nanotube-based electronics and novel nanomaterials. His 2023 Nature Electronics paper on CMOS-compatible electrochemical synaptic transistors demonstrates his leadership in developing hardware solutions for deep learning acceleration. His research trajectory shows a progression from fundamental carbon nanotube device physics to more applied systems for computing and sensing applications. IBM Pat Goldberg Memorial Best Paper Award (2017) IBM Master Inventor Award (2016) MIT Technology Review TR35 (2016) Forbes '30 Under 30' (2012) and 'Most Influential All-Star Alumni' (2016) Atlantic Council Millennium Fellow (2017) US Frontiers of Engineering by National Academy of Engineering (2016, 2019) 17 IBM Invention Achievement Awards (2011-2018) Dr. Cao has secured significant research funding including NSF grants 1950182 and 2139185. His research group actively recruits graduate students and postdoctoral researchers to work on cutting-edge materials and device projects. His work has resulted in over thirty research papers and fifty patents and patent applications. He teaches graduate courses including MSE 403 (Synthesis of Materials), MSE 460 (Electronic Materials I), and MSE 488 (Optical Materials). The Cao Research Group operates within the University of Illinois' world-class facilities including the Frederick Seitz Materials Research Laboratory and Holonyak Micro and Nanotechnology Laboratory. His research has received support from NSF, DoD, DOE, and industry partners including TSMC. The group's recent $2 million project focuses on developing technology to help mobile devices learn and adapt to their surroundings.

• Nanomaterials
• Electronic Devices
• Optoelectronic Devices
• +5 more

Georgia Chalvatzaki is a Professor in the Department of Computer Science at TU Darmstadt, leading the PEARL-Lab (Interactive Robot Perception and Learning Lab) with a team of 13 PhD candidates and postdocs. Her research focuses on human-centered robotics, integrating perception, planning, and action to develop robots that adapt to dynamic environments through structured knowledge embedding. Key research areas: Robotics, Artificial Intelligence, Machine Learning, and Human-Robot Interaction Applications: Healthcare (assistive systems), logistics automation, and sustainable agriculture Notable innovation: SE(3)-Diffusionsmodelle for 3D spatial learning in robots Her work combines model-based robotics with modern learning techniques like reinforcement learning and graph-based neural networks, enabling robots to transfer knowledge across scenarios and adjust behavior contextually. Georgia has received significant accolades, including: ERC Starting Grant (2024) Alfried Krupp Prize (2025, €1.1 million) Ellis Scholar recognition in the European Lab for Learning and Intelligent Systems She actively promotes open science, diversity, and early-career researcher development, serving as a keynote speaker at major conferences like IROS and CoRL.

• Robotics
• Artificial Intelligence
• Machine Learning
• +5 more

David J. Crandall is the Luddy Professor of Computer Science at Indiana University's Luddy School of Informatics, Computing, and Engineering. He serves as Director of the Luddy Artificial Intelligence Center and leads the IU Computer Vision Lab. With joint appointments in Informatics, Cognitive Science, Data Science, and Statistics, his work spans computer vision, machine learning, and AI. He holds a Ph.D. from Cornell University and previously worked at Eastman Kodak Research Labs. His research focuses on developing statistical and machine learning methods to analyze visual information, including object recognition, human activity analysis in video, 3D reconstruction, social media mining, and computational studies of visual attention. Key applications include egocentric vision systems, social robotics for healthcare, and cross-disciplinary collaborations with developmental psychology. Recent publications demonstrate strong emphasis on egocentric video analysis (Ego4D), human-robot interaction (CHI/HRI), and explainable AI (IJCAI). Medical imaging, nanoscale security systems, and computational social science represent emerging interdisciplinary directions. His work consistently integrates deep learning with real-world applications in health, environmental monitoring, and cultural analytics. Tracy M. Sonneborn Award (2024) Distinguished Member of the ACM (2023) Luddy Professorship (2021) NSF CAREER Grant (2013) Trustees Teaching Award (2017) He has advised over 20 Ph.D. graduates, with current students working on computer vision, robotics, and AI ethics. Major grants include $20M for the NSF AI Institute on Engaged Learning, $4.4M for trusted AI research, and funding from NIH, Google, ONR, and NASA. He directs the Computer Vision Lab and collaborates with Selma Sabanović's robotics group on social agents for older adults.

• Computer Vision
• Machine Learning
• Artificial Intelligence
• +5 more

Anil Madhavapeddy serves as Professor of Planetary Computing at the University of Cambridge's Department of Computer Science and Technology and directs the Cambridge Centre for Carbon Credits (4C). A Fellow of Pembroke College, he integrates systems research with environmental conservation through the Computer Laboratory's Environment and Energy Group. His career spans industry leadership (NetApp, Citrix, Intel), academic appointments (Cambridge, Imperial, UCLA), and entrepreneurial ventures (XenSource, Unikernel Systems, Docker). Madhavapeddy earned his PhD at Cambridge's Computer Laboratory in 2006. His research bridges computational systems and planetary-scale environmental challenges, with deep expertise in open-source development (OCaml, Xen, Docker, OpenBSD) and technology strategy advising for organizations including Zededa, Tezos Foundation, and Tarides. His work centers on environmental computing and climate informatics, leveraging distributed systems and functional programming to develop sensing infrastructure for conservation. Recent projects focus on carbon credit systems, AI-driven biodiversity monitoring, and sustainable computing architectures that minimize ecological footprints while maximizing analytical capability. Analysis of his 2025 publications reveals a concentrated effort on AI-integrated conservation tools, privacy-preserving carbon accounting, and energy-efficient computing. Key themes include spatial networking for ecological data, LLM-enhanced evidence retrieval in conservation science, and novel metrics for extinction risk assessment—demonstrating computational innovation applied to urgent planetary boundaries. No scientific awards were documented in the source material. Madhavapeddy advises multiple technology firms on strategic development while leading the Cambridge Centre for Carbon Credits, though specific grant funding details remain unreported. He actively contributes to the Environment and Energy Group at Cambridge's Computer Laboratory and directs the interdisciplinary Cambridge Centre for Carbon Credits (4C). His open-source leadership spans critical infrastructure projects including OCaml, Xen, and Docker, fostering collaborative development communities that underpin modern cloud and container technologies.

• Environmental Computing
• Climate Change Informatics
• Distributed Systems
• +5 more

Roberto Albano is an external lecturer and teaching assistant at the Interuniversity Department of Regional and Urban Studies and Planning (DIST) within Politecnico di Torino's College of Architecture and Design . He has been actively involved in teaching urban planning modules across multiple degree programs since 2019, including courses like Urban Design Workshop B and Heritage Redevelopment and Enhancement Project . Teaching Roles : Course Lecturer for Heritage-focused Urban Planning (2020–2024), Collaborator for Urbanism modules in Heritage programs (2022–2024). Research Focus : Multidisciplinary approaches to urban design, heritage conservation, and spatial planning. His work emphasizes collaborative teaching frameworks and integrating design innovation into territorial strategies. Publications : Contributed to edited volumes on urban design pedagogy and regional development trends, notably co-editing Pieces of the City (2021) and analyzing design industry evolution in Piedmont (2018).

• Urban Planning
• Heritage Conservation
• Interdisciplinary Education
• +3 more

Nick Koudas is a Professor in the Department of Computer Science at the University of Toronto, specializing in large-scale data management, data systems, and applied machine learning. His research integrates machine learning techniques into scalable data platforms to enhance the analysis of massive datasets. He holds a PhD from the University of Toronto, an MSc from the University of Maryland, and a Bachelor's degree from the University of Patras. Education: PhD, University of Toronto MSc, University of Maryland at College Park Bachelor's degree, University of Patras, Greece Research Interests: Relational Deep Dive (ReDD): Natural language query execution over unstructured documents Streaming Video Queries (SVQ): Interactive query processing for video streams Reliable Text-to-SQL: Generating accurate SQL queries with human-in-the-loop assistance Machine Learning Integration in Data Systems Publications: Focus on video analytics, query processing, and reliable natural language interfaces. Notable works include optimizing video queries, declarative frameworks for temporal constraints, and abstention-based SQL generation. Awards: Inventor of the Year (1st Prize), University of Toronto (2011) Best Paper Awards at international conferences Entrepreneurship & Advising: Co-founder of Sysomos (Meltwater Group), Aislelabs (Constellation Software), and Workorb Advisor to mapintent and ktau Labs & Teams: Leads research groups developing systems like ReDD and SVQ, emphasizing collaboration between academia and industry.

• Large-Scale Data Management
• Data Systems
• Big Data Analysis
• +5 more

Alex Mariakakis is an Assistant Professor in the Department of Computer Science at the University of Toronto, leading the Computational Health and Interaction (CHAI) lab. His research focuses on leveraging ubiquitous and wearable technologies for healthcare applications, including smartphone-based health sensing for conditions like traumatic brain injury, jaundice, and inebriation. He holds affiliations with KITE@UHN and AXL venture studio, emphasizing translational research. Education: PhD in Computer Science (University of Washington, advised by Shwetak Patel and Jacob O. Wobbrock), B.S. in Electrical and Computer Engineering and Computer Science (Duke University). Prior roles include postdoctoral work at Sage Bionetworks and academic advising roles at UW. Key research interests include mobile health (mHealth), human-computer interaction, and machine learning applied to sensor data. His work has received Best Paper Awards at ACM CHI and COMPASS, and media attention from BBC and National Geographic. Recent activities include talks on embracing ubiquitous tech for healthcare (KITE Research Rounds, June 2025) and contributions to courses like 'Advanced Topics in Mobile Health.'

• Ubiquitous Computing
• Mobile Health (mHealth)
• Human-Computer Interaction (HCI)
• +4 more

Mizuko (Mimi) Ito is a cultural anthropologist and learning scientist at the University of California, Irvine, serving as Director of the Connected Learning Lab and holder of the John D. and Catherine T. MacArthur Foundation Chair in Digital Media and Learning. She previously held research appointments at Keio University and the University of Southern California. Ito earned dual PhDs in Education and Anthropology from Stanford University and a BA in East Asian Studies from Harvard University. Education: PhD in Education, Stanford University PhD in Anthropology, Stanford University Bachelor's Degree in East Asian Studies, Harvard University Research Interests: Ito's work focuses on leveraging youth interests and digital media to foster equitable, socially connected learning. Her research spans mobile media culture in Japan, youth social media engagement in the US, and global adoption of children's media. She developed the connected learning framework, emphasizing youth-centered, equity-oriented approaches to education in the digital age. Grants & Partnerships: Ito has secured funding from major organizations including the MacArthur Foundation, Bill and Melinda Gates Foundation, National Science Foundation, and Microsoft Research. She co-founded the Connected Learning Alliance to advance research and impact in technology and learning. Awards: Recipient of the Jan Hawkins Award for Early Career Contributions (AERA) Labs & Initiatives: Directs the Connected Learning Lab at UC Irvine, which explores opportunities and risks of digital media in education. The Lab collaborates with global networks to design inclusive learning ecosystems.

• Digital Media and Learning
• Cultural Anthropology
• Learning Sciences
• +3 more

Prof. Dennis Komm is an Associate Professor at ETH Zurich's Department of Computer Science, leading the group for Algorithms and Didactics. He chairs the Center for Computer Science Education (ABZ) and serves on committees such as the Swiss Maturity Board (Schweizerische Maturitätskommission) and the STEM Commission of the Swiss Academies. Previously, he held roles at RWTH Aachen University (Master's, 2008), ETH Zurich (PhD, 2012), University of Zurich (external lecturer, 2014–2020), and PH Graubünden (including department head and professor of 'Fachdidaktik Informatik'). Education: He completed a Master's in Computer Science at RWTH Aachen (2008), a PhD at ETH Zurich (2012), and studies in Information Technology at Queensland University of Technology (2006). His academic journey includes visiting roles at King's College, Stanford, and Comenius University. He has taught extensively across institutions, emphasizing Python and LOGO-based approaches for beginners. Research focuses on algorithm design, approximation algorithms, reoptimization, and advice complexity in theoretical CS. His work in education explores computational thinking, programming pedagogy (especially for K–12), and interdisciplinary approaches (e.g., robotics in math). Recent trends in his articles highlight advancements in online algorithms, optimization under dynamic conditions, and initiatives to integrate CS into Swiss school curricula sustainably. He actively promotes CS education through platforms like WebTigerPython and collaborates on projects such as CyberQuest and MINTerlink. His outreach includes organizing conferences (e.g., STIU 2025) and workshops on programming and cybersecurity for teachers and students. Despite no listed scientific awards, his contributions to education and theoretical CS are recognized through editorial roles in journals like Informatics in Education and contributions to the TigerJython Group. Grant-related advising includes co-supervising doctoral theses on robotics, USOs, and programming didactics. He advocates for equitable educational opportunities via the Passerelle exam and the Swiss Beaver Competition. His team's work spans teacher training, didactic certifications, and bridging university-school collaborations through initiatives like MINTerlink. Labs and teams: Head of ABZ (ETH's CS education center), collaborator with the Computational Robotics Lab, and part of the TigerJython Group. He also co-organizes the Colloquium on Mathematics, Computer Science, and Education with ETH's Mathematics Department.

• Algorithm Design and Analysis
• Computer Science Education
• Theoretical Computer Science
• +3 more

Chaowei Xiao is an Assistant Professor at the University of Wisconsin-Madison (starting 2023), affiliated with the School of Computer, Data & Information Sciences. His research focuses on securing AI systems, particularly exploring robustness in trustworthy machine learning, autonomous systems, and large language models (LLMs). He holds a Ph.D. from the University of Michigan, Ann Arbor, and a B.S. from Tsinghua University. Before joining UW-Madison, he worked as a research scientist at NVIDIA (2020–2022) and at Arizona State University (2022–2023). His work bridges model and system perspectives to ensure practical robustness and provable guarantees in AI applications like autonomous driving, healthcare, and IoT. Key research areas include adversarial robustness, AI security, and ethical AI. Recent contributions include frameworks for detecting LLM hallucinations, mitigating jailbreak attacks, and securing multi-modal systems. His work on diffusion models for adversarial purification and physical-world attacks on autonomous driving systems has been widely recognized. Notable awards include the 2024 USENIX Security Distinguished Paper Award, ACM Gordon Bell Finalist (2024), and Schmidt Sciences AI2050 Fellowship. He has advised students like Xiaogeng Liu (NVIDIA Fellow) and secured grants from Amazon, Apple, and UW-Madison. His lab actively publishes at top venues like NeurIPS, ICML, and CVPR.

• Trustworthy Machine Learning
• Security
• Computer Vision
• +3 more