جست‌وجوی استاد و پژوهشگر

Yiwei Lyuمشاهده پروفایل

استادیار

• Safe Control
• Verification
• Behavior Planning
• +۶ مورد دیگر

Yiwei Lyu serves as Assistant Professor in the Department of Computer Science and Engineering at Texas A&M University, joining the faculty in August 2025 after completing her Ph.D. at Carnegie Mellon University. Her research program bridges control theory, machine learning, and social science to develop safe, socially-compliant autonomous systems. Her educational background includes: Ph.D. in Electrical and Computer Engineering, Carnegie Mellon University (2025) B.S. in Electronic Information Engineering, The Chinese University of Hong Kong, Shenzhen (2019) Professor Lyu's work centers on risk-aware safe control for multi-agent systems, with emphasis on verifiable safety guarantees in human-robot interaction. She pioneers methods integrating control barrier functions with social preference modeling to enable robots that navigate complex environments while respecting human norms. Her research spans autonomous driving, multi-robot coordination, and human behavior prediction, consistently addressing the critical challenge of safety assurance in uncertain real-world scenarios. Analysis of her 15 most recent publications reveals a cohesive trajectory: evolving from foundational safe control (2021-2022) to sophisticated risk-aware frameworks (2023-2024) that incorporate social compliance and learning. Her work consistently targets high-impact applications in autonomous vehicles while maintaining theoretical rigor, with 7 papers receiving best paper awards or nominations since 2021. Her exceptional contributions have been recognized through: MIT EECS Rising Star (2024) - top global early-career honor IEEE/ACM Human-Robot Interaction Pioneer designation (2024) Qualcomm Innovation Fellowship (2023) Multiple best paper awards at ICRA, IROS, and AAMAS venues Professor Lyu actively builds her research group, having welcomed her first PhD student in August 2025. Her competitive fellowship funding and rapid publication record indicate strong grant support potential. She serves on editorial boards (ICRA 2026 Associate Editor) and professional committees (Junior Co-chair, Multi-Robot Systems Technical Committee), demonstrating growing leadership in the robotics community. As a new faculty member, Professor Lyu combines fresh perspective with proven research excellence, offering students unique opportunities to shape the future of safe autonomy at the intersection of engineering and social sciences.

• Psychedelic research
• psilocybin-assisted research
• neurophenomenology
• +۶ مورد دیگر

Sophia Armand is an Assistant Professor in the Department of Psychology at the University of Copenhagen, Faculty of Social Sciences. Her academic work focuses on the intersection of neuroscience, psychology, and psychedelic research, with particular emphasis on understanding the role of serotonin in psychological processes. Dr. Armand's research primarily examines the role of brain serotonin in psychological processes such as cognition, mood, and consciousness. She is particularly interested in how serotonergic psychedelics like psilocybin affect the human mind and how these substances can be used safely and ethically in psychotherapy to treat conditions like depression and OCD. Her interdisciplinary approach combines questionnaires, interviews, and neuroimaging techniques including fMRI and PET. Key research areas include psychedelic research, psilocybin-assisted therapy, neurophenomenology, and clinical applications for mental health disorders. Her recent publications (2023-2025) demonstrate a strong focus on psychedelic mechanisms and antidepressant effects. Major themes include psilocybin's effects on cerebral blood flow and emotional processing, escitalopram's impact on synaptic density and reinforcement learning, and the relationship between depression treatment and sexual function. Her work shows significant media attention with some publications covered by hundreds of news outlets and substantial academic engagement. Dr. Armand frequently collaborates with researchers at the University of Copenhagen, particularly with G.M. Knudsen, D.S. Stenbæk, and P.M. Fisher, indicating involvement in established research groups focused on neuropsychopharmacology and psychedelic studies. Her work sits at the cutting edge of psychedelic science, which has seen renewed interest after decades of research restrictions.

Stuart Jonathan Russellمشاهده پروفایل

استاد

• Artificial Intelligence
• Machine Learning
• Probabilistic Reasoning
• +۷ مورد دیگر

Stuart Jonathan Russell is a Distinguished Professor of Computer Science, Cognitive Science, and Computational Precision Health at the University of California, Berkeley. He holds the Smith-Zadeh Chair in Engineering and is also a Professor of Computational Precision Health at the University of California, San Francisco. Russell is the founder and leader of the Center for Human-Compatible Artificial Intelligence (CHAI) at UC Berkeley and serves as an Honorary Fellow of Wadham College, Oxford. His academic journey began with a B.A. in Physics from the University of Oxford, followed by a Ph.D. in Computer Science from Stanford University. Throughout his distinguished career, Russell has received numerous prestigious honors including the IJCAI Computers and Thought Award (1995), IJCAI Award for Research Excellence (2022), Fellow of the Royal Society (2025), and Member of the National Academy of Engineering (2025). Russell's research spans multiple domains within artificial intelligence, with a recent focus on ensuring AI systems remain beneficial to humanity. His work includes significant contributions to machine learning, probabilistic reasoning, knowledge representation, planning, real-time decision making, and inverse reinforcement learning. In recent years, his research has increasingly focused on AI safety, value alignment, and developing frameworks for human-compatible AI systems that maintain human control as AI capabilities advance. His publication record shows a clear trend toward addressing the long-term challenges of AI development, particularly the control problem and value alignment. The research spans theoretical foundations of AI, practical applications in robotics and decision making, and critical examinations of the societal implications of increasingly capable AI systems. Russell's work has evolved from foundational AI research to increasingly focus on the alignment problem and mechanisms for ensuring AI systems remain beneficial. Russell has received numerous scientific awards recognizing his contributions to the field: IJCAI Computers and Thought Award (1995) AAAI Fellow (1997) ACM Fellow (2003) AAAS Fellow (2011) Blaise Pascal Chair (2012) Reith Lectures (2021) Officer of the Order of the British Empire (OBE) (2021) Fellow of the Royal Society (2025) Member of the National Academy of Engineering (2025) Russell has advised numerous doctoral students including Marie desJardins, Eric Xing, and Shlomo Zilberstein, and has mentored many postdoctoral researchers who have become leaders in the field. His research has been supported by various grants from organizations including the National Science Foundation, Defense Advanced Research Projects Agency, and other funding bodies focused on advancing AI research with careful consideration of safety and societal impact. He has been particularly active in securing funding for research on human-compatible AI and value alignment. He founded and leads the Center for Human-Compatible Artificial Intelligence (CHAI), which brings together researchers from multiple disciplines to address the challenge of creating AI systems that reliably do what humans want them to do. The center collaborates with other research groups including the Berkeley Artificial Intelligence Research (BAIR) lab, the Kavli Center for Ethics, Science, and the Public (KCESP), and the Institute for Cognitive and Brain Sciences (ICBS), creating a rich interdisciplinary environment for addressing the challenges of AI safety and human compatibility.

Đorđe Žikelićمشاهده پروفایل

استادیار

• Formal Methods
• Program Analysis and Verification
• Trustworthy AI
• +۵ مورد دیگر

Đorđe Žikelić is an Assistant Professor of Computer Science at the School of Computing and Information Systems at Singapore Management University (SMU) in Singapore. He completed his PhD in 2023 at the Institute of Science and Technology Austria (ISTA) under Krishnendu Chatterjee and Petr Novotný, receiving both Outstanding PhD Thesis and Outstanding Scientific Achievement awards. Prior to his doctorate, he earned bachelor's and master's degrees in mathematics from the University of Cambridge. His educational background includes: PhD in Computer Science, Institute of Science and Technology Austria (ISTA), 2023 Bachelor's and Master's in Mathematics, University of Cambridge Dr. Žikelić's research focuses on advancing formal methods to ensure software and AI systems are correct, safe, and trustworthy. His work bridges theoretical aspects of formal reasoning about probabilistic systems with practical automated verification methods. His primary research interests span three interconnected areas: Program Analysis and Verification: He develops techniques for analyzing probabilistic programs, numerical programs, and efficient quantifier elimination methods, addressing fundamental challenges in verifying complex software systems. Trustworthy AI and Safe Autonomy: He creates formal verification frameworks for learning-enabled control systems and neural networks, ensuring AI operates safely in uncertain environments through methods like runtime monitoring and certificate repair. Probabilistic System Verification: He explores broader applications including bidding games on graphs and blockchain protocol analysis, extending formal methods to novel domains beyond traditional finite-state verification. His publication trajectory shows a consistent progression from theoretical foundations to practical applications, with recent work increasingly focused on integrating formal verification with machine learning. His 2024-2025 publications demonstrate growing expertise in verifying learning-based systems and developing practical tools like PolyQEnt for quantified entailment solving. His scientific achievements have been recognized with: Outstanding PhD Thesis Award at ISTA Outstanding Scientific Achievement Award at ISTA Distinguished Paper Award at FM 2024 Dr. Žikelić serves on program committees for major conferences including TACAS, PLDI, AAAI, and CAV. He actively mentors through the Programming Languages Mentoring Workshop (PLMW) at PLDI 2025. His research group at SMU focuses on developing novel algorithms for verifying correctness of programs and AI systems, with current projects spanning formal methods, artificial intelligence, and programming languages.