Matthew Louis Mauriello is an Assistant Professor in the Department of Computer and Information Sciences at the University of Delaware , where he directs the Sensify Lab . He holds a PhD in Computer Science from the University of Maryland (2018) and completed postdoctoral work at Stanford University (School of Medicine, 2020; School of Public Policy & Environmental Engineering Department, 2019). Research interests span Human-Computer Interaction (HCI), Ubiquitous Computing, and User-Centered Design with applications in: Sustainability Human-Building Interaction Wearable Technology Personal Informatics Educational Game Design Mental Health Interventions Recent publications highlight trends in stress monitoring (skin-like biosensors, workplace wellbeing), energy auditing (thermography systems), and educational technology (block-based programming tools for teachers). His work appears in ACM CHI, ACM Human-Computer Interaction, and Building and Environment. Scientific awards include: Best Paper Honorable Mention, CHI 2016 Best Paper Honorable Mention, CHI 2015 Best of WebSci'18 Teaching at University of Delaware encompasses courses like Educational Game Design Operating Systems Advanced Web Technologies Computing for Social Good with a focus on project-based learning and systems thinking.
Andrea Arpaci-Dusseau is the Susan Beth Horwitz WARF Professor of Computer Sciences and Catherine A. Erickson Professor in the School of Computer, Data & Information Sciences at the University of Wisconsin-Madison. She has been a professor at UW-Madison since January 2000 and currently serves as Graduate Advising Chair for the Computer Sciences Department. Her research focuses on computer systems with primary emphasis on file and storage systems, but also making significant contributions in distributed systems, virtualization, and scheduling. According to csrankings.org, she has published the fourth-most papers in premier systems conferences (SOSP and OSDI) and the most at the top file and storage conference (FAST). Professor Arpaci-Dusseau's recent publications demonstrate continued leadership in storage systems research, with increasing focus on cloud architectures, persistent memory technologies, and system reliability. Her work bridges theoretical foundations with practical implementations, consistently addressing real-world challenges in modern computing environments. ACM SIGOPS Mark Weiser Award 2018 (highest honor in systems field) UW-Madison Van Hise Outreach Teaching Award 2017 Multiple Best Paper awards at FAST, SOSP, OSDI, and EuroSys conferences Carolyn Rosner Award for Excellence in Teaching (2010, 2017) Co-chaired major conferences including USENIX ATC '04, FAST '07, OSDI'18, and SOSP'24 Professor Arpaci-Dusseau has co-advised 28 Ph.D. students and is deeply committed to educational outreach through the CaTaPuLT project, which connects UW-Madison students with K-12 schools to teach computational thinking using Scratch. This initiative has reached hundreds of students across Madison and earned her significant recognition for teaching excellence. She leads the Arpaci-Dusseau Systems Lab (ADSL) and is involved with the Wisconsin Institute on Software-defined Datacenters in Madison (WISDoM), where her research group continues to advance state-of-the-art solutions in computer systems.
Dr. Chengmo Yang is a Professor in the Department of Electrical and Computer Engineering at the University of Delaware, with a joint appointment. She received her PhD and MSc in Computer Science from the University of California, San Diego, and a BSc in Microelectronics from Peking University, China. PhD, University of California, San Diego MSc, University of California, San Diego BSc, Peking University, China Her research focuses on enhancing security, reliability, non-volatility, and energy efficiency in embedded systems, cyber-physical systems (CPS), and Internet-of-Things (IoT). She leads the Computer Architecture, Reliability, and Security (CARES) group and has authored over 70 peer-reviewed publications. Recent publications emphasize neural network accelerators, non-volatile memory (NVM) optimization, and security frameworks for embedded systems. Her work explores fault tolerance, wear leveling, and side-channel attack mitigation in NVM-based FPGAs, STT-RAM, and SSDs. National Science Foundation Career Award (2013) University of Delaware Mid-Career Faculty Excellence in Scholarship Award (2020) Best paper award at ICESS (2019) Three best paper nominations at DAC, DATE, and GLSVLSI (2019) Dr. Yang serves as Associate Editor for IEEE TCAD and ACM TODAES. She is the Diversity & Inclusion Representative for IEEE CEDA and has organized numerous conferences including Technical Program Chair for CODES-ISSS 2022. Her lab has hosted current and former students like Fanruo Meng (PhD candidate), Fateme Hosseini (Qualcomm), and Patrick Cronin (Intel), focusing on graduate-level research in hardware security and reliability.
Dawn Song is a Professor in the Department of Electrical Engineering and Computer Science at the University of California, Berkeley, affiliated with multiple research centers including the Berkeley Artificial Intelligence Research Lab (BAIR) and the Berkeley Center for Responsible, Decentralized Intelligence (RDI). She holds leadership roles in AI safety, cybersecurity, and blockchain research. Her work bridges machine learning, security, and distributed systems, with notable contributions to formal verification, privacy-preserving technologies, and AI governance. Education: Ph.D. (2002) and M.S. (1999) in Computer Science from UC Berkeley and Carnegie Mellon University, respectively. She previously served as an Assistant Professor at Carnegie Mellon University before joining UC Berkeley in 2007. Research Interests: Dawn's work focuses on AI safety, cybersecurity, and the ethical implications of frontier AI. She explores topics such as large language model vulnerabilities, zero-knowledge proofs, blockchain security, and policy frameworks for AI governance. Her research combines theoretical rigor with practical applications, addressing challenges in secure systems, adversarial machine learning, and privacy-preserving computation. Publications: Her recent work includes groundbreaking studies on LLM memorization, smart contract decompilation, and AI agent cybersecurity evaluation. She also leads initiatives like the Singapore Consensus and California Report on AI safety priorities, emphasizing global collaboration in risk mitigation. Notable Awards: MacArthur Fellowship (2010), ACM Fellow (2019), IEEE Fellow (2019) Advising & Grants: She advises projects on AI policy and cybersecurity, securing grants from NSF, DARPA, and industry collaborations. Her lab develops tools like CyberGym for evaluating AI agents and zkPyTorch for secure machine learning. Labs & Teams: Her research groups at UC Berkeley focus on cutting-edge projects in AI safety, blockchain, and cybersecurity, collaborating with industry leaders and policymakers to advance both technical and ethical standards.
Wei Xu is an Associate Professor at Georgia Institute of Technology's College of Computing and School of Interactive Computing, with affiliations to the Machine Learning Center. Their research bridges machine learning, natural language processing, and social media with focus areas in large language models, cultural bias mitigation, multilingual capabilities, and human-AI collaboration in text evaluation. NSF CAREER and Google Academic Research Award recipient Director of NLP X Lab PhD from New York University, BSMS from Tsinghua University Research interests span: Multilingual Multicultural LLMs addressing representational gaps and cultural adaptation in language models (NAACL 2025, ACL 2024); Robustness and Reasoning through dynamic AGI evaluations (ACL 2024, EMNLP 2024); Interdisciplinary NLP applications in security, healthcare, and law (EMNLP 2024, ACL 2024). Recent publications focus on multilingual alignment (NAACL 2025), privacy risk estimation (arXiv 2025), cultural bias analysis (ACL 2024), and medical text simplification (EMNLP 2024). Key themes include bias mitigation, multimodal processing, and practical LLM evaluation. Scientific Awards : NSF CAREER, Google/Sony/Criteo research awards, ACL'24 Best Social Impact Award, COLING'18 Best Paper Advising 15 PhD/MS/BSMS students including Yao Dou (human-centered LLM evaluation), Tarek Naous (multilingual LLMs), and alumni like Chao Jiang (Apple AI/ML) and Yang Chen (NVIDIA research scientist). Teaches graduate courses on NLP and LLMs.
Stefano Ermon is an Associate Professor in the Department of Computer Science at Stanford University, affiliated with the Artificial Intelligence Laboratory and a Senior Fellow at the Woods Institute for the Environment. His research focuses on advancing machine learning and generative AI techniques to address societal and environmental challenges, including computational sustainability, geospatial analysis, and climate science. He holds a Ph.D. from Cornell University (2015). Education: Ph.D. in Computer Science, Cornell University (2015). Research Interests: Ermon’s work bridges foundational machine learning (e.g., diffusion models, generative AI, and optimization) with applications in sustainability, geospatial analysis (via satellite imagery), and earth observation systems. Notable contributions include predicting poverty using satellite data and developing scalable methods for molecule generation. Articles Trends: His recent work emphasizes diffusion models for generative tasks (e.g., text-to-image, molecule design), geospatial AI (e.g., environmental monitoring), and ethical AI (e.g., bias mitigation in LLMs). He also explores applications in robotics and scientific computing. Awards: He has received prestigious awards, including the ICML 2024 Best Paper Award, Sloan Research Fellowship, Microsoft Research Faculty Fellowship, and the IJCAI Computers and Thought Award. Advising and Grants: Ermon teaches courses like Probabilistic Graphical Models (CS228) and has secured grants from NSF, ONR, AFOSR, and private foundations. His lab develops tools for climate science and sustainable development. Labs/Teams: Leads the Stanford AI Lab group focused on computational sustainability and generative AI, collaborating with institutions like the Woods Institute for environmental applications.
Stephen Licht is an Associate Professor of Ocean Engineering and Graduate Director at the University of Rhode Island's College of Engineering, where he directs the Robotics Laboratory for Complex Underwater Environments (R-CUE). His research focuses on developing maritime robots capable of operating in dynamic and unpredictable environments through biologically inspired propulsion, distributed pressure sensing, model-based optimal control, and compliant underwater manipulation technologies. Ph.D. in Oceanographic and Mechanical Engineering from MIT/WHOI Joint Program (2008) B.S. in Mechanical Engineering from Yale University (1998) Former Senior Research Scientist at iRobot and Senior Robotics Engineer at Vecna Robotics Current Research Affiliate with MIT Department of Mechanical Engineering Former Visiting Faculty at Libera Università di Bolzano (2019-2020) Dr. Licht's research spans marine robotics with emphasis on biologically inspired propulsion systems that provide high authority and bandwidth thrust, nonlinear attitude control for maneuvering in dynamic conditions, compliant underwater manipulation technologies, and unmanned aerial monitoring of coastal structures. His work bridges mechanical engineering principles with oceanographic applications to create more capable underwater robotic systems that can operate in complex marine environments. His recent publications demonstrate a strong trend toward soft robotics applications for deep-sea exploration, with particular focus on jamming grippers and neutrally buoyant manipulation systems. The research also shows increasing integration of additive manufacturing techniques for field-deployable solutions and computational methods for autonomous systems operating in challenging marine environments. His work spans fundamental control theory, mechanical design, and practical field applications. Dr. Licht has secured significant research funding as both Principal Investigator and Co-Principal Investigator from major organizations including the Office of Naval Research, NOAA, NSF, and various university collaborations. His grants focus on advancing unmanned underwater vehicle technology, soft robotics for deep-sea applications, and coastal monitoring systems. Active mentor to numerous graduate and undergraduate students in Ocean Engineering Successful track record of student placements at organizations including Jaia Robotics, Scripps Institution of Oceanography, FORSSEA Robotics, and government research labs Collaborates with researchers at MIT, WHOI, University of Connecticut, University of Maine, and international institutions Licht leads the R-CUE lab which develops innovative solutions for underwater robotics challenges, with particular expertise in biomimetic propulsion, soft robotics for deep-sea applications, and autonomous systems for environmental monitoring. The lab maintains strong industry connections with OceanGate Inc. and FabNewport, and engages with local educational institutions through outreach programs with Roger Williams Middle School.
Boris Hanin is an Associate Professor at Princeton University's Department of Operations Research and Financial Engineering (ORFE) and Associated Faculty at the Program in Applied and Computational Mathematics (PACM). Prior to Princeton, he held academic positions at Texas A&M University (Assistant Professor of Mathematics), MIT (NSF Postdoctoral Fellow), and Northwestern University (PhD in Mathematics under Steve Zelditch). He works part-time at Foundry, an AI/computing startup, leading the Foundry Institute. PhD in Mathematics, Northwestern University NSF Postdoctoral Fellowship, MIT Mathematics Associate Professor, Princeton ORFE Part-Time Leader, Foundry Institute His research spans machine learning, probability theory, and mathematical physics, focusing on neural network theory (approximation power, optimization guarantees), random matrix theory, and spectral asymptotics. He has made foundational contributions to understanding gradient behavior, initialization, and infinite-width limits in deep learning. Boris has supervised numerous PhD students and postdocs, with former members securing prestigious positions at Harvard, MIT, and Huawei. He serves as Associate Editor for journals like Pure and Applied Analysis and Mathematics of Operations Research , and has taught short courses at Oxford, Luxembourg, and Tor Vergata on statistical physics of neural networks and deep learning theory. 2024 Sloan Fellowship in Mathematics NSF CAREER grant DMS-2143754 NSF grant DMS-2133806 His research group collaborates on topics including hyperparameter transfer, architecture-aware scaling, and spectral analysis of random waves and neural networks. He actively contributes to theoretical machine learning through foundational publications in venues like Probability Theory and Related Fields , Journal of Machine Learning Research , and Communications in Mathematical Physics .
University of California, Los AngelesUnited States
Kai-Wei Chang is an Associate Professor at the University of California, Los Angeles (UCLA) in the Department of Computer Science, part of the Henry Samueli School of Engineering. He is also an Amazon Scholar at Alexa AI, focusing on advancing trustworthy AI and multimodal foundation models. His research bridges NLP, machine learning, and ethical AI, with a focus on fairness, robustness, and bias mitigation in language and vision-language systems. Education: Ph.D. in Computer Science (UIUC, 2015), M.S. and B.S. in Computer Science and Electrical Engineering from National Taiwan University. Research Interests: Trustworthy NLP (fairness, robustness), Multimodal Foundation Models (e.g., VisualBERT, GLIP), Reasoning in LLMs, and mitigating societal biases in AI systems. Notable contributions include pioneering work on aligning NLP models with human values and developing SOTA multimodal models like DesCo and GLIP. Awards: Sloan Research Fellowship (2021), Okawa Grant (2018), EMNLP Best Paper (2017), KDD Best Paper (2010). His work is funded by NSF, IARPA, ONR, and industry partners like Amazon, Google, and Facebook. Service: VP-Elect of SIGDAT, Ethics Committee Chair (NAACL 2022), Organizer of Trustworthy NLP Workshops, and Senior Area Chair for top conferences (ACL, NeurIPS, AAAI). Labs/Teams: Leads the UCLA Natural Language Processing Group, fostering interdisciplinary research on ethical AI and multimodal systems.
Abhishek Jain is an Associate Professor in the Department of Computer Science at Johns Hopkins University and a Senior Scientist at NTT Research. He is affiliated with the Data Science and AI Institute, the Information Security Institute, and the Algorithms and Complexity group. University: Johns Hopkins University Department: Computer Science Academic Rank: Associate Professor Institutional Roles: Co-director of the Advanced Research in Cryptography group, member of the Theory Group, and co-leader of the Cryptography Group Education: Ph.D. in Computer Science from the University of California Los Angeles (2012), advised by Amit Sahai and Rafail Ostrovsky. Recipient of the Symantec Outstanding Graduate Student Award during his Ph.D. Research Interests Cryptography Secure computation Proof systems Program obfuscation Privacy Blockchain Theoretical computer science Research Trends: His recent publications emphasize cryptographic protocols for homomorphic encryption, zero-knowledge proofs, and secure multi-party computation, alongside applications in blockchain and privacy-preserving systems. Key themes include scalability, verifiable evaluation, and adapting cryptographic techniques to dynamic and distributed environments. Scientific Awards 2020 NSF CAREER Award Best Paper Awards at Eurocrypt and the International Conference on the Theory and Applications of Cryptographic Techniques Advising & Grants: Mentors Ph.D. students and interns/postdocs at NTT Research. Research funded by NSF, DARPA, JP Morgan, Ethereum Foundation, Stellar, Cisco, Samsung, and JHU Catalyst awards. Labs & Teams: Co-leads the Cryptography Group at Johns Hopkins, participates in the DC Area Crypto Day, and organizes the weekly Theory Seminar. Collaborates with institutions including MIT CSAIL, BUSEC, and Microsoft Research New England.
Kristen Grauman is a Full Professor in the Department of Computer Science at the University of Texas at Austin, where she leads the UT Computer Vision Group. Her research focuses on computer vision and machine learning, with applications in visual recognition, video analysis, and multi-modal perception. She received her B.A. from Boston College and her Ph.D. from MIT. Her research interests span visual recognition, image and video search, video analysis, first-person vision, embodied and multi-modal perception, and interactive machine learning. She has made significant contributions to the field, particularly in developing algorithms for understanding visual content and human activities from video, including foundational work on the Pyramid Match Kernel and relative attributes. Her recent publications reveal a strong emphasis on egocentric (first-person) vision, audio-visual learning, and view-invariant representations. There is a clear trajectory toward multi-modal integration (vision, audio, language) and real-world applications in instructional videos, human activity understanding, and embodied AI systems. She has received numerous awards including: AAAI Fellow (2019) J. K. Aggarwal Prize, International Association for Pattern Recognition (2018) Helmholtz Prize (2017) UT Austin Academy of Distinguished Teachers (2017) Best Paper Award, Asian Conference on Computer Vision (2016) Presidential Early Career Award for Scientists and Engineers (2014) Computers and Thought Award, International Joint Conferences on Artificial Intelligence (2013) Pattern Analysis and Machine Intelligence Young Researcher Award (2013) Alfred P. Sloan Research Fellow (2012) Marr Prize (2011) Prof. Grauman serves as Associate Editor-in-Chief for the IEEE Transactions on Pattern Analysis and Machine Intelligence. She has secured substantial research funding including the Presidential Early Career Award, NSF grants, and industry partnerships. Her advising has produced numerous influential publications and students who are now leaders in computer vision. She leads the UT Computer Vision Group, which collaborates closely with the Electrical and Computer Engineering Department. The group is pioneering large-scale egocentric video research through projects like Ego4D and Ego-Exo4D, focusing on real-world applications in human activity understanding, audio-visual perception, and interactive systems.
Massachusetts Institute of TechnologyUnited States
Polina Golland is a Professor in the Department of Electrical Engineering and Computer Science (EECS) at MIT and a Principal Investigator in the Computer Science and Artificial Intelligence Laboratory (CSAIL). Her research focuses on developing novel techniques for biomedical image analysis and understanding, particularly in medical vision, AI/ML, and health care applications. She leads the Medical Vision Group and collaborates with the Vision Group at CSAIL. Her work emphasizes statistical modeling of medical images, shape modeling, and predictive analytics for biological processes. Current projects include fetal MRI analysis, cardiac MRI segmentation, and quantitative assessment of pulmonary edema in chest X-rays. She has secured grants from NIH, MIT-IBM Watson AI Lab, and other institutions to support her research. Dr. Golland teaches courses on inference, probability, and probabilistic systems. She advises graduate students in MIT's EECS program and has mentored numerous postdocs and researchers. Her lab focuses on translating advanced imaging techniques into clinical workflows, with applications in neuroimaging, fetal health monitoring, and cardiovascular disease analysis. Notable collaborations include work with Harvard Medical School affiliates, Brigham and Women's Hospital, and the MIT Jameel Clinic. Her research aims to bridge computational methods with clinical needs, improving diagnostic tools and treatment planning through machine learning and medical imaging innovation.
Sewoong Oh is a Professor at the Paul G. Allen School of Computer Science & Engineering at the University of Washington, where he has been faculty since 2019. His research focuses on the foundations of machine learning with particular emphasis on differential privacy, secure and robust machine learning, and federated learning. Prior to joining UW, he was at the Department of Industrial and Enterprise Systems Engineering at the University of Illinois at Urbana-Champaign from 2012-2019. He is affiliated with multiple NSF AI Institutes including ACTION (Agent-based Cyber Threat Intelligence and Operation), AI-EDGE (Future Edge Networks and Distributed Intelligence), and IFML (Foundations of Machine Learning). Oh received his PhD in Electrical Engineering from Stanford University in 2011 under Andrea Montanari, followed by postdoctoral work at MIT's Laboratory for Information and Decision Systems under Devavrat Shah. His educational background spans top institutions in theoretical computer science and electrical engineering. His research spans the critical intersection of machine learning security, privacy, and robustness. Oh's work addresses fundamental challenges in making AI systems reliable and trustworthy, with particular focus on defending against backdoor attacks, developing privacy-preserving algorithms, and creating efficient tokenization methods for language models. His recent SuperBPE work demonstrates how moving beyond traditional subword tokenization can significantly improve language model efficiency and performance. His research consistently bridges theoretical foundations with practical implementations, as evidenced by numerous open-source repositories containing production-ready code. Oh's publications reveal a consistent trajectory toward addressing security and privacy concerns in increasingly complex machine learning systems, with recent work focusing on language model tokenization, data-centric AI, and federated learning frameworks. His research shows strong interdisciplinary connections between theoretical computer science, statistics, and practical machine learning systems. ACM SIGMETRICS best paper award (2015) NSF CAREER award (2016) ACM SIGMETRICS rising star award (2017) GOOGLE Faculty Research Awards (2017, 2020) 2024 ICML Best Paper Award (for work by advisee Jon Hayase) Professor Oh maintains an active research group with numerous PhD students, postdocs, and undergraduate researchers. His students have secured prestigious positions at leading tech companies including Amazon, Google, and Snap, as well as academic appointments at institutions like University of Wisconsin-Madison and Shanghai Jiao Tong University. He has received substantial research funding through his participation in multiple NSF AI Institutes and industry research awards from Google. His lab maintains several active GitHub repositories implementing cutting-edge research in backdoor defense, robust statistics, and privacy-preserving machine learning.
Furong Huang is an Associate Professor at the University of Maryland's Department of Computer Science, with affiliations at the Institute for Advanced Computer Studies, Center for Machine Learning, Maryland Robotics Center, and Applied Mathematics, Statistics, and Scientific Computation Program. Her research bridges trustworthy machine learning, sequential decision-making, and foundation models for robotics, emphasizing reliability, interpretability, and ethical standards. Research Interests: Trustworthy AI Generative AI Reinforcement Learning AI Security Algorithmic Fairness Foundation Models for Robotics Recent Publications span leading conferences (NeurIPS, ICML, ICLR, CVPR) and journals, focusing on: Robustness in Vision-Language Systems Trustworthy Generative AI Foundation Models for Sequential Decision-Making AI Security and Watermarking Scientific Awards MIT TR35 Innovator Under 35 (Asia Pacific 2022) Best Paper Award, AdvML Frontier Workshop, NeurIPS 2024 NSF NAIRR Pilot Awardee Microsoft Accelerate Foundation Models Research Award (2023) JP Morgan Faculty Research Awards (2019–2022) Advising and Grants : Her lab has graduated students to roles at OpenAI, Google, Meta, and Netflix. Research funded by DARPA, NSF, ONR, AFOSR, and industry partners like Microsoft, Adobe, and Capital One. Labs & Teams : Leads research groups focused on Trustworthy AI and Robotics at the University of Maryland, collaborating with the Maryland Robotics Center and Applied Mathematics Program.
University of Illinois Urbana-ChampaignUnited States
Huan Zhang serves as an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Illinois Urbana-Champaign (UIUC), with affiliate appointments in the Department of Computer Science and the Coordinated Science Laboratory. His research focuses on building trustworthy AI systems with formal verification techniques to provide provable guarantees for safety-critical applications, particularly in machine learning and neural networks. Dr. Zhang received his Ph.D. in Computer Science from UCLA in 2020, advised by Professor Cho-Jui Hsieh. His academic journey includes an M.S. in Computer Engineering from UC Davis (2014) and a Bachelor of Engineering from Zhejiang University (2012). Prior to joining UIUC, he completed a postdoctoral fellowship at Carnegie Mellon University (2021-2023) with Professor Zico Kolter. Huan Zhang's research program centers on formal verification of machine learning systems, with particular emphasis on neural network verification, AI safety, robustness, and reliability. He pioneered the linear bound propagation-based verification framework that enables formal verification for networks with millions of neurons. His work spans five major research categories: formal verification of machine learning, training trustworthy ML models, machine learning safety and adversarial attacks, reinforcement learning safety, and optimization for scalable machine learning. His CROWN framework (NeurIPS 2018) established a foundational approach for neural network verification through efficient linear bound propagation. His recent publications demonstrate a strategic expansion from foundational verification techniques toward increasingly complex systems including large language models, vision-language models, and robotic control systems. The research trajectory shows a clear progression from theoretical frameworks to practical implementations with real-world applications, particularly in safety-critical domains. His work increasingly bridges formal methods with practical AI deployment requirements. Winner of International Verification of Neural Networks Competition (VNN-COMP) as team leader (2021-2024) Schmidt Futures AI2050 Early Career Fellowship ($300,000 research grant) Adversarial Machine Learning (AdvML) Rising Star Award (2021) IBM PhD Fellowship (2018) Dr. Zhang leads the development of α,β-CROWN, a neural network verifier that has won VNN-COMP 2021-2023, and auto_LiRPA, a PyTorch-based library for perturbation analysis on general computational graphs. He has mentored numerous graduate students from CMU, UCLA, UIUC, and Columbia University. His research is supported by significant funding including the Schmidt Futures fellowship and industry collaborations. He teaches courses including ECE 120, ECE 484, ECE 584, and ECE 598 HZ on topics ranging from computing fundamentals to safe autonomy and machine learning. Dr. Zhang maintains active research collaborations across multiple institutions and is affiliated with UIUC's Coordinated Science Laboratory. His work has significant implications for safety-critical AI applications in autonomous systems, healthcare, and other mission-critical domains where reliability guarantees are essential. He regularly gives guest lectures at institutions including Yale, Stony Brook, and the University of Nebraska Lincoln on formal verification techniques.
