Find Academic Supervisors

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.

• Artificial Intelligence
• Cybersecurity
• Machine Learning
• +7 more

Adrian Weller is a prominent researcher and academic at the University of Cambridge, serving as a Director of Research in Machine Learning within the Department of Engineering. He holds multiple significant leadership roles including Programme Director for Trust and Society at the Leverhulme Centre for the Future of Intelligence (CFI), and previously served as Programme Director for AI at The Alan Turing Institute, the UK national institute for data science and AI. His work bridges theoretical machine learning research with practical applications and societal implications of artificial intelligence. Weller's research interests span a broad spectrum of AI and machine learning topics with a particular focus on ensuring beneficial societal outcomes. His work encompasses explainability, fairness, robustness, scalability, privacy, safety, and ethics in AI systems. He has made significant contributions to trustworthy machine learning, including developing frameworks for AI governance, certification, and human-AI collaboration. His research group actively investigates neuro-symbolic approaches, privacy-preserving techniques, and methods for improving the reliability and interpretability of AI systems. His recent publications demonstrate a strong trend toward addressing the practical challenges of deploying AI systems in real-world contexts, particularly focusing on certification frameworks, governance mechanisms, and human-centered approaches. His work spans theoretical advances in machine learning architectures while maintaining a strong connection to societal impact, with publications appearing in top venues across AI, machine learning, and interdisciplinary applications. Scientific Awards: MBE for services to digital innovation (2022 Queen's Birthday Honours) Turing AI Fellowship for Trustworthy Machine Learning Weller actively supervises a large group of PhD students and postdocs, with current students including Juyeon Heo, Yanzhi Chen, Katie Collins, Isaac Reid, Yichao Liang, Herbie Bradley, and Shoaib Siddiqui. His former students have gone on to positions at leading institutions including Google DeepMind, ETH Zurich, NYU, and MPI-IS Tübingen. He has served on numerous advisory boards including the Centre for Data Ethics and Innovation, UNESCO's expert group on AI ethics, and the World Economic Forum's Global Future Council on AI. His research has been supported through his Turing AI Fellowship and various collaborative projects focused on safe and ethical AI development. Weller leads a vibrant research group focused on trustworthy machine learning, which actively organizes workshops and conferences including ICML 2024 (where he served as Program Chair), multiple workshops on responsible AI, and events through the ELLIS network. His group collaborates extensively across disciplines, working with researchers in computer science, social sciences, law, and policy to address the multifaceted challenges of developing beneficial AI systems.

• Artificial Intelligence
• Machine Learning
• Explainability
• +9 more

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.

• Trustworthy Machine Learning
• Formal Verification of Machine Learning
• AI Safety
• +4 more

Michael Carbin is the Jamieson Career Development Assistant Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT) and leads the MIT Programming Systems Group. His research focuses on programming systems that address system uncertainty to enhance performance, energy efficiency, and resilience, particularly in environments involving neural networks , approximate computing , and unreliable hardware . His work spans probabilistic programming , quantum computing , and machine learning systems . Articles highlight contributions in pruning neural networks , quantum data structures , and compiler optimization , reflecting trends in deep learning , formal verification , and language-driven systems . Scientific Awards : MIT Frank E. Perkins Award (2020) Sloan Research Fellowship (2020) Facebook Research Award (2019) NSF CAREER Award (2018) Best Paper Awards at OOPSLA (2013, 2014) He has advised numerous graduate students and postdocs including Eric Atkinson, Cambridge Yang, and Charles Yuan, and served on program committees for conferences like POPL, OOPSLA, and ICLR. His group collaborates with institutions such as MIT CSAIL and explores applications in quantum algorithms and probabilistic inference .

• Programming Systems
• Approximate Computing
• Probabilistic Programming
• +4 more

Greg Durrett is an Associate Professor in the Department of Computer Science at University of Texas at Austin, leading the TAUR Lab (Text Analysis, Understanding, and Reasoning ). His research focuses on advancing Large Language Models (LLMs) for knowledge-intensive tasks in medical information processing scientific discovery legal reasoning . He received his B.S. in Computer Science and Mathematics from MIT (2010) and Ph.D. in Computer Science from UC Berkeley (2016). His work develops techniques to train LLMs with new capabilities augment models for reliability assess model outputs improve reasoning frameworks . His 15 most recent publications (2021-2025) span knowledge propagation in LLMs chain-of-thought reasoning code generation benchmarks multi-modal reasoning fact verification discourse analysis . Scientific honors include NSF CAREER Award (2024) NSF grants (2018, 2024) Bloomberg Data Science Grant (2017) Facebook Fellowship (2014) Best Paper Finalist (EMNLP 2013) . Teaching: CS388: Natural Language Processing (graduate) CS371N: NLP (undergraduate) High school NLP module .

• Natural Language Processing
• Machine Learning
• Artificial Intelligence
• +7 more

Sicun Gao is an Associate Professor in the Computer Science and Engineering department at the University of California, San Diego. His research focuses on practical algorithms for NP-hard search and optimization problems in computational systems, emphasizing combinatorial perspectives in numerical and statistical contexts to achieve reliable autonomy. Research Interests: Automated reasoning, Hamilton-Jacobi reachability, safe reinforcement learning, control barrier functions, and optimization in cyber-physical systems. Teaching: Courses on AI search, optimization, and graduate research seminars. The 15 most recent publications highlight advancements in safe AI control, motion planning, and policy optimization, often integrating neural networks with formal verification. Awards include the IEEE Power & Energy Society Technical Committee Prize Paper Award and the IROS RoboCup Best Paper Award. He advises PhD students working on AI-driven control and robotics, with alumni placed at institutions like Seoul National University, Amazon, and Apple. Grants include NSF Career, Air Force Young Investigator, and DARPA Assured Autonomy funding. His lab develops tools like dReal for automated reasoning in nonlinear theories over the reals.

• Algorithms and Optimization
• Automated Reasoning
• Cyber-Physical Systems
• +3 more

Osbert Bastani is an Associate Professor at the Department of Computer and Information Science, University of Pennsylvania, leading the trustml@Penn research group. He is affiliated with the ASSET , PRECISE , and PRiML centers, and the PLClub research group. His research focuses on Trustworthy Neurosymbolic Systems , Synthesizing Neurosymbolic Programs , and Machine Learning for Programmer Productivity , with applications in verification, fairness, and human-AI collaboration. He received the NSF CAREER Award in 2023. His recent publications (2024-2025) emphasize AI Safety , LLM Robustness , and Algorithmic Fairness , including work on adversarial robustness, conformal prediction, and program synthesis. Students he has advised include Sagnik Anupam, Stephen Mell, Jason Ma, Shuo Li, and others. Awards: NSF CAREER Award (2023)

• Machine Learning
• Neurosymbolic AI
• Program Synthesis
• +10 more

Rachit Agarwal is an Associate Professor in the Department of Computer Science at Cornell University, with research focusing on systems, networking, and theoretical problems arising in practical systems. He leads a research group working on resource disaggregation, host architecture, secure cloud storage, and datacenter design. PhD in Computer Science, Cornell University Undergraduate, IIT Kanpur His research spans three major directions: Resource Disaggregation (with $3M NSF and Google awards), Host Architecture (exploring terabit interconnects), and PANCAKE (secure oblivious cloud storage with $1M NSF award). He also contributed to foundational work in Near-optimal Datacenter Design and Data Plane Monitoring . Awards include the Sloan Fellowship, NSF CAREER, IRTF Applied Networking Prize, and multiple best paper awards. His recent publications focus on host network architecture, congestion control, oblivious data access mechanisms, and secure cloud storage systems. He has advised multiple Ph.D. and postdoctoral researchers who now hold faculty positions at leading institutions. Sloan Research Fellowship NSF CAREER award Kavli Fellowship IRTF Applied Networking Research Prize SIGCOMM Best Student Paper Award Usenix Security Distinguished Paper Award Tau Beta Pi Professor of the Year 2025 Rachit has advised numerous students including current Cornell advisees like Midhul Vuppalapati, Shreyas Kharbanda, and Omar Eqbal. Former advisees include Saksham Agarwal (UIUC), Qizhe Cai (UVA), and Mina Tahmasbi Arashloo (University of Waterloo). His research is supported by large NSF grants and industry awards, with deployments in real-world systems and open-source contributions.

• Systems
• Networking
• Theory of Computing
• +6 more

Richard M. Murray is the Thomas E. and Doris Everhart Professor of Control and Dynamical Systems and Bioengineering at the California Institute of Technology (Caltech). He holds a B.S. from Caltech (1985), M.S. from UC Berkeley (1988), and Ph.D. from UC Berkeley (1990). He has served in academic roles from Assistant Professor (1991–1997) to his current endowed professorship. He chaired the Engineering and Applied Science division (2000–2005) and Biology and Biological Engineering (2020–2024). His research focuses on feedback control in biological and autonomous systems, synthetic cells, and networked control systems. Collaborators include experts in robotics, synthetic biology, and systems biology. Key awards include the IEEE Control Systems Award and election to the National Academy of Engineering. His educational contributions span courses on control systems, robotics, and bioengineering. Current research projects include the Developer Cell initiative (Sloan Foundation), layered testing for autonomous systems (AFOSR), and microbiome-based environmental solutions (CHARMME, ARO). He advises numerous graduate students and postdocs, with notable alumni in academia and industry. Labs include facilities in Keck and Steele laboratories at Caltech. His work bridges control theory, synthetic biology, and autonomous systems to address societal challenges like environmental monitoring and safe autonomy.

• Control Theory
• Autonomous Vehicles
• Biological Circuit Design
• +3 more

Insup Lee is the Cecilia Fitler Moore Professor in the Department of Computer and Information Science and Director of the PRECISE Center at the University of Pennsylvania's School of Engineering and Applied Science. He holds a secondary appointment in the Department of Electrical and Systems Engineering and the Perelman School of Medicine’s Department of Biostatistics, Epidemiology, and Informatics. IEEE TCCPS Distinguished Leadership Award (2023) Fellow of the AAAS (2022) Test of Time Award, Runtime Verification (2019) Fellow of the ACM (2017) Best Paper Awards at IEEE ICPS, ACM/IEEE ICCPS, and MEMOCODE His research focuses on cyber-physical systems , real-time and embedded systems , safe autonomy , and internet of medical things , with applications in healthcare and connected systems. He advises PhD students including Eric Lu, Kaustubh Sridhar, Sooyong Jang, and Jean Park (co-advised with Kevin Johnson). Recent publications address safety monitoring for learning-enabled systems, model-free control synthesis using reinforcement learning, and multilingual toxicity guardrails for large language models. His team collaborates with institutions like Hillrom and Penn Nursing to optimize medical device usage in clinical settings.

• Cyber-physical Systems
• Real-time and Embedded Systems
• Safe Autonomy
• +3 more

Byron Wallace is the Sy and Laurie Sternberg Interdisciplinary Associate Professor at Northeastern University's Khoury College of Computer Sciences, where he also serves as Associate Dean for Research and Director of the BS in Data Science Program. His research focuses on Natural Language Processing and Machine Learning applications in healthcare. Education Details of formal education are not explicitly provided in the available text, though he holds a PhD from Tufts University (mentioned in thesis award context). Research Interests His work centers on developing NLP and ML models for health applications, with particular emphasis on: Biomedical evidence synthesis automation Electronic Health Record processing Model interpretability and trustworthiness Human-in-the-loop systems Learning with limited supervision Research Trends Recent publications demonstrate strong focus on large language model applications in healthcare, including factuality evaluation for medical summarization, evidence extraction from clinical trials, and interpretable risk prediction models. Notable contributions include work on GPT-3 applications in medical evidence synthesis and neural methods for EHR analysis. Scientific Awards ACL Outstanding Paper Award (2022) ICLR Spotlight (top 5% acceptance) (2024) Best Student-led Paper Award at AMIA 2021 NSF CAREER Award (2018-2023) Advising and Grants Currently advises 4 PhD students and has mentored numerous others. Major funding includes: NSF CAREER Award ($500K+) NIH R01 grant for EHR summarization NSF Medium grant for healthcare summarization Support from Army Research Office, Amazon, and Seton Hospital Labs and Teams Leads the Evidence Inference project team working on automated biomedical evidence synthesis. Collaborates with Brigham and Women's Hospital, Mass General Hospital, and Reboot Rx for clinical translation of research.

• Natural Language Processing
• Machine Learning
• Artificial Intelligence
• +5 more

Kenneth P. Birman is the N. Rama Rao Professor of Computer Science at Cornell University, where he has had a long and impactful career in distributed systems, cloud computing, and AI/ML infrastructure. He is known for foundational contributions to reliable and scalable distributed systems, and for leading high-impact projects such as Cascade, Vortex, and Derecho. He is also the author of a widely used textbook on reliable distributed systems and has founded multiple companies based on his research. Education: Ph.D. in Computer Science, University of California, Berkeley M.S. in Computer Science, University of California, Berkeley B.A. in Computer Science, Columbia University Research Interests: Professor Birman's research focuses on building reliable, secure, and scalable distributed systems . His current emphasis is on AI and ML infrastructure , particularly in reducing latency and improving performance through hardware acceleration, RDMA-based communication, and edge computing. He explores how to eliminate data movement bottlenecks in AI pipelines and how to support real-time, mission-critical applications in domains like healthcare, smart grids, and industrial IoT. His work spans systems programming, cloud computing, fault tolerance, and formal verification . He has designed systems that have been deployed in high-stakes environments such as the New York Stock Exchange, the Swiss Exchange, and the French Air Traffic Control system. Scientific Awards: ACM Fellow (1999) IEEE Fellow (2014) IEEE Tsutomu Kanai Award for innovations in distributed computing Teaching and Mentorship: Professor Birman teaches two courses in the fall semester: CS4414: Systems Programming and CS5416: Cloud and ML Systems Programming . He has advised numerous Ph.D. and M.S. students, including Alicia Yang, Tiancheng Yuan, Yifan Wang, Weijia Song, Edward Tremel, Sagar Jha, Jonathan Behrens, and Mae Milano. He has announced that Fall 2025 will be his last semester teaching, and he is no longer recruiting new students, though he will continue supervising current ones. Labs and Projects: He leads the Derecho Project and the Cascade/Vortex Project , both focused on high-performance distributed systems. These projects are collaborative efforts with students and industry partners, and the software is released under open-source licenses. He also maintains strong ties with Cornell's systems group and collaborates with faculty across CS, ECE, IS, and the Cornell Tech NYC campus.

• Distributed Systems
• Cloud Computing
• Machine Learning Systems
• +5 more

Ram Vasudevan is an Associate Professor and Associate Chair of Graduate Studies in the Department of Robotics at the University of Michigan. His research focuses on developing tools for safe and robust deployment of robotic systems, emphasizing optimization, nonlinear control, and real-world applications. Key areas include legged robot locomotion, shared control systems, and safety-critical autonomous systems. Research Interests: Optimization and control of nonlinear systems, locomotion of legged robots, shared control active safety systems, and automation of diagnostic/rehabilitative tasks. His ROAHM Lab prioritizes mathematical guarantees for robotic performance, with applications in medical robotics, autonomous vehicles, and soft robotics. Recent work emphasizes trajectory optimization, sensor fusion, and safety-aware control strategies. He has contributed to benchmarks for autonomous vehicle perception and novel methods in thermal image restoration using neural radiance fields. Awards: None explicitly listed in provided text. Labs/Teams: Directs the ROAHM Lab, collaborating on projects like robotic tail mechanics, real-time motion planning, and sensor data analysis. Active in academic conferences including RSS and ICRA.

• Optimization and control of nonlinear systems
• Legged robot locomotion
• Autonomous systems safety
• +4 more

Alessio Lomuscio is a Professor of Safe Artificial Intelligence at Imperial College London, holding the prestigious Royal Academy of Engineering Chair in Emerging Technologies and recognized as an ACM Distinguished Member. He leads the Safe AI Lab, which focuses on developing methods and tools for the verification of AI systems to ensure their safe and secure deployment in applications of societal importance. His research spans verification and robust learning for neural networks and decision trees, robust machine learning in aviation and finance, monitoring of machine learning systems, assurance for autonomous systems and AI, and verification and validation of neuro-symbolic systems. Lomuscio has made significant contributions to formal verification methods for AI systems, particularly in the context of safety-critical applications. His recent publications demonstrate a strong focus on neural network verification techniques, with applications across multiple domains including finance, aviation, and autonomous systems. His work bridges theoretical advances in formal methods with practical applications in real-world AI systems, addressing critical challenges in AI safety and trustworthiness. Scientific Awards: Royal Academy of Engineering Chair in Emerging Technologies ACM Distinguished Member Lomuscio has served in numerous leadership roles, including as Co-Director (2023-present) and Deputy Director (2019-2023) of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence. He has also held positions as Director of Strategy and Planning (2017-2020), Member of Management Committee (2013-2020), and Deputy Head of Department (2016-2017). His editorial service includes roles as Associate Editor for Artificial Intelligence Journal and Editorial Board Member for Journal of Artificial Intelligence Research and Journal of Autonomous Agents and Multi-agent Systems. His research group actively mentors students and researchers, with current openings for PhD and postdoctoral positions focused on AI verification and safety. Lomuscio's work has established him as a leading figure in the field of safe and verifiable AI systems, with significant contributions to both theoretical foundations and practical applications.

• Artificial Intelligence
• Machine Learning Verification
• Neural Network Verification
• +5 more

Kamalika Chaudhuri is a Professor in the Department of Computer Science and Engineering at the University of California, San Diego (UCSD), and also serves as a Director and Research Scientist with the FAIR team at Meta AI. Her research focuses on the foundations of trustworthy machine learning, including robust machine learning, learning with privacy, and out-of-distribution generalization. Dr. Chaudhuri has earned her PhD from UC Berkeley in 2007 with a dissertation on "Learning Mixtures of Distributions." Her academic journey has led her to become a leading researcher in machine learning theory with a particular emphasis on privacy and robustness. Her research interests span machine learning foundations with a strong focus on trustworthy AI . She investigates problems at the intersection of differential privacy , adversarial robustness , and out-of-distribution generalization . Her work addresses critical challenges in developing machine learning systems that maintain privacy while preserving utility, resist adversarial attacks, and generalize effectively beyond training data distributions. She has pioneered approaches in privacy-preserving machine learning, robust learning theory, and methods for detecting and mitigating data memorization in models. An analysis of her recent publications (2024-2025) reveals a strong focus on the intersection of privacy, security, and machine learning. Her work spans differential privacy mechanisms, membership inference attacks, memorization detection, and fairness certification. She has been particularly active in developing methods for privacy-preserving foundation models, with several papers on differentially private computer vision and language models. Her research demonstrates a consistent thread of addressing fundamental challenges in trustworthy AI while developing practical solutions that balance privacy, accuracy, and utility. Best Award at the ICLR 2024 Workshop on Privacy Regulation and Protection in Machine Learning Distinguished Paper Award at IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2024 Dr. Chaudhuri has advised numerous PhD students who have gone on to prominent positions at Google, DeepMind, Microsoft Research, and other leading AI institutions. Her group maintains an active research blog with guest posts from UCSD researchers. She has served in significant leadership roles including General Chair for ICML 2022 and Program Co-Chair for both ICML 2019 and AISTATS 2019, where she pioneered initiatives to improve reproducibility in machine learning research. Her research group at UCSD focuses on trustworthy machine learning, with current projects spanning privacy-preserving AI, robustness against adversarial attacks, and methods for ensuring reliable out-of-distribution generalization. The group collaborates closely with the FAIR team at Meta AI, where Dr. Chaudhuri serves as a Research Scientist.

• Machine Learning
• Trustworthy Machine Learning
• Differential Privacy
• +4 more