Vitaly Shmatikov is a professor of computer science at Cornell Tech and the Cornell Ann S. Bowers College of Computing and Information Science . Prior to his current position, he worked at the University of Texas at Austin and SRI International. His research focuses on digital privacy , computer security , and security and privacy issues in machine learning . Education: Ph.D. in Computer Science and M.S. in Engineering Economic Systems from Stanford University Teaching: Offers courses like CS 5435 Security & Privacy Concepts in the Wild Shmatikov's research has received multiple accolades, including the Caspar Bowden PET Award three times and Test-of-Time Awards from leading IEEE and ACM symposiums. His work addresses adversarial system design and practical applications of privacy and security. Scientific Awards: Caspar Bowden PET Award (3x) IEEE Test-of-Time Award ACM Test-of-Time Award ACM/IEEE Symposium on Logic in Computer Science Test-of-Time Award USENIX Security Outstanding Paper Award EMNLP Distinguished Paper Award He actively mentors students and collaborates on cutting-edge security research, with applications in cryptography, malware analysis, and behavioral economics in cybersecurity.
Dr. James McDonald serves as a Lecturer and Research Fellow at the University of New South Wales (UNSW) within the School of Civil and Environmental Engineering's Water Research Centre (WRC). His work at the Vallentine Annexe (H22), Room 102, Kensington Campus focuses on advancing water treatment technologies and understanding contaminant behavior in water systems. His position bridges academic instruction with cutting-edge research in environmental engineering. McDonald's research spans multiple critical areas in water science and engineering, with particular emphasis on trace organic contaminants, membrane technologies, and advanced water treatment processes. His work investigates the fate and removal of pharmaceuticals, personal care products, and industrial chemicals in various water treatment systems. He has made significant contributions to understanding disinfection by-product formation, chiral inversion of pharmaceuticals, and the development of novel membrane technologies for improved water purification. His research combines experimental approaches with computational modeling to address complex water quality challenges. Analysis of McDonald's recent publications reveals a strong focus on emerging contaminants, particularly PFAS compounds and chiral pharmaceuticals, and their behavior in water treatment systems. His work demonstrates expertise in both conventional and advanced water treatment technologies, with increasing emphasis on sustainable approaches including green infrastructure and novel membrane processes. The interdisciplinary nature of his research connects environmental engineering, chemistry, microbiology, and materials science to address contemporary water quality challenges. McDonald actively collaborates with researchers across multiple institutions and has contributed to numerous significant studies on water quality and treatment. His work supports the development of more effective water recycling systems and safer drinking water supplies. While specific grant information isn't detailed in the available text, his extensive publication record suggests sustained research funding in water treatment technologies and contaminant fate studies. As part of UNSW's Water Research Centre, McDonald contributes to one of Australia's leading water research facilities. The WRC provides a collaborative environment for addressing complex water challenges through interdisciplinary research that integrates engineering, chemistry, and environmental science perspectives.
Dr. Kaya de Barbaro is an Associate Professor in the Department of Psychology at the University of Texas at Austin (College of Liberal Arts). She holds a Ph.D. from the University of California San Diego. Her research focuses on bridging computer science and developmental/clinical psychology, particularly maternal mental health and infant social-emotional development. She directs the Daily Activity Lab, which uses mobile/wearable sensors and machine learning to analyze real-world interactions, aiming to develop just-in-time interventions for new mothers. Key research areas include maternal-infant dynamics, physiological synchronization, and the impact of environmental chaos on development. She has pioneered methods for analyzing high-density data, such as Granger causality and machine learning algorithms to detect behaviors like crying and holding. Recent work emphasizes leveraging ecological momentary assessment surveys and 24-hour LENA audio recordings to understand proximal mechanisms of development. Dr. de Barbaro teaches Psychology 333D (Introduction to Developmental Psychology) and has developed curricula for both in-person and online formats. She is actively involved in training students through the Eureka program at UT Austin. Her lab collaborates on tools like chatbots for postpartum mental health and has published extensively on sensor-based methodologies in developmental science.
Maja J Matarić is the Chan Soon-Shiong Chaired and Distinguished Professor of Computer Science at the University of Southern California's Viterbi School of Engineering, with courtesy appointments in Neuroscience and Pediatrics. She serves as founding director of the USC Robotics and Autonomous Systems Center, co-director of the USC Robotics Research Lab, and Principal Scientist at Google DeepMind. Previously, she held leadership roles as USC's interim Vice President of Research (2020-2021) and Vice Dean for Research (2006-2019). Her educational background includes: PhD in Computer Science and Artificial Intelligence from MIT (1994) MS in Computer Science from MIT (1990) BS in Computer Science from University of Kansas (1987) Matarić pioneers Socially Assistive Robotics (SAR) , a field her lab named, focusing on human-robot interaction that provides assistance through social rather than physical support. Her research targets critical health and wellness challenges including post-stroke rehabilitation, autism spectrum disorder therapy, cognitive exercises for Alzheimer's patients, ADHD academic support, and mental health interventions. She develops systems modeling user engagement, personality, and motivation, with extensive real-world deployments in schools, rehabilitation centers, and homes. Analysis of her recent publications reveals dominant themes in cognitive health robotics (2025 CHI paper on LLM-powered elder care), pediatric assistive technology (2025 IDC speech therapy review), and adaptive preference modeling (2025 HRI contrastive learning work). Her research consistently bridges machine learning with human-centered design for vulnerable populations. Major scientific recognition includes: ACM Athena Lecturer Award (2024) ACM Eugene L. Lawler Humanitarian Award (2024) ACM Fellow (2020) Presidential Mentoring Award (2011) Multiple society fellowships (AAAS, IEEE, AAAI) As a dedicated mentor, Matarić has championed underrepresented groups through CRA-W, placing numerous women in faculty positions. She leads USC Viterbi's K-12 STEM Outreach Program serving low-income Los Angeles schools and authored The Robotics Prime for student education. Her research has secured significant funding enabling real-world technology transfer, with documented impact in rehabilitation centers and homes through deployable SAR systems. Her Robotics Research Lab at USC drives innovation in embodied AI, with current projects spanning LLM-integrated elder care robots, ADHD academic companions, and autism therapy systems. The lab emphasizes co-design with end-users and rigorous real-world validation across diverse populations.
Bernard Comrie is a Research Professor Emeritus in Linguistics at the University of California, Santa Barbara (UCSB), affiliated with the College of Letters and Science. He previously served as Director of the Department of Linguistics at the Max Planck Institute for Evolutionary Anthropology in Leipzig (1998–2015) and held a Distinguished Professorship at UCSB (2002–2021). His career includes teaching positions at the University of Cambridge, University of Southern California, and leadership roles in major research institutions. Comrie’s research focuses on Language universals and typology Historical linguistics Languages of the Caucasus, New Guinea, and Great Andamanese He emphasizes fieldwork-driven cross-linguistic analysis of topics like tense/aspect, transitivity, numeral systems, and prehistoric migration studies through collaborations with archaeologists and geneticists. His recent publications explore morphosyntactic variation (e.g., verb indexing in Asian languages, reflexivity in Tsez), language contact (Kanashi prehistory), and numeral system typology. Articles often bridge theoretical linguistics with empirical data from understudied languages. Notable contributions include the World Atlas of Language Structures and foundational work on Nakh-Daghestanian and Andamanese languages. He advocates for interdisciplinary approaches to reconstructing prehistoric human movements via linguistic evidence.
Olga Sorkine-Hornung is a Professor of Computer Science at ETH Zurich and head of the Institute of Visual Computing. She leads the Interactive Geometry Lab, focusing on theoretical and practical advancements in digital content creation, geometry processing, and shape modeling. Current position: ETH Zurich, Department of Computer Science Previous roles: Courant Institute (NYU), Technical University of Berlin Education: BSc and PhD from Tel Aviv University, postdoc at TU Berlin Her research spans shape representation, digital fabrication, computer animation, and fundamental geometry processing. Key contributions include Laplacian surface editing, as-rigid-as-possible deformation, and generalized winding numbers. She works on applications in VR, AR, and autonomous systems. Awards include Test of Time Awards (2024), ACM Fellow (2020), ERC Consolidator Grant (2020), and EUROGRAPHICS Young Researcher Award (2008). She has supervised numerous students and co-developed software libraries like libigl and Instant Meshes . Co-chair roles for SIGGRAPH, Eurographics, and Pacific Graphics Editorial board member for ACM Transactions on Graphics and other journals Keynote speaker at VMV, CVPR, and SIAM conferences Her work bridges mathematical rigor with practical implementation, advancing computer graphics and geometry processing through intuitive algorithms that maintain surface detail while enabling efficient computation.
Steven Jackson is a Professor of Information Science and Science and Technology Studies at Cornell University's Bowers College of Computing and Information Science, with additional graduate field appointments in Communication and Public Affairs. Since July 2023, he has served as Vice-Provost for Academic Innovation at Cornell, and previously held leadership positions as Chair of Information Science and Dean of William Keeton House. His work bridges academic research with significant institutional leadership in higher education innovation. Dr. Jackson's research focuses on critical intersections of technology, society, and the environment, with three primary strands: technology ethics, law and policy; maintenance, repair and sustainability; and technology, inequality and global development. His work draws from American pragmatism, political economy, and science and technology studies, integrating methods from sociology, anthropology, philosophy, and media studies. He is particularly interested in how computing practices meet social and material worlds, with implications for infrastructure, collaboration, sustainability, and cultural practice. His recent publications reveal a strong emphasis on repair as both theoretical concept and practical methodology, exploring 'ordinary hope' as a framework for technological engagement and examining unmaking as a necessary counterpart to design. The research spans diverse geographical contexts from the global North to South, addressing caste dynamics in computing, digital authoritarianism, and infrastructure challenges in developing contexts. Dr. Jackson has received significant recognition including an NSF CAREER award and more than twenty paper awards at leading computing and information science venues. His research has been supported by major organizations including the U.S. National Science Foundation, Social Science Research Council, Ford Foundation, Sloan Foundation, World Bank, Intel Research, Atkinson Center for Sustainability, and the Canadian Social Science and Humanities Research Council. As an advisor, Dr. Jackson has mentored numerous graduate students who have gone on to prominent positions at institutions worldwide. He currently advises Jen Liu, Amy Cheatle, Daniel Mwesigwa, Johan Michalove, and Ritik Batra, while his former students include Palashi Vaghela (Assistant Professor at Simon Fraser University), Samir Passi (Responsible AI Researcher at Microsoft), Maggie Jack (Assistant Professor at NYU), and Ranjit Singh (Senior Researcher at Data and Society). Dr. Jackson convenes the Computing On Earth Lab, an experimental collaboration bringing together social scientists, humanists, artists, and engineers to rethink the material and planetary foundations of computing. The lab reflects his commitment to interdisciplinary approaches that address computing's environmental impacts and sustainability challenges.
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.
Jackie Chit Kit Cheung is an Associate Professor in the School of Computer Science at McGill University, where he co-directs the Reasoning and Learning Lab. He holds the Canada CIFAR AI Chair and serves as an Associate Scientific Co-Director at the Mila Quebec AI Institute. He is also a consulting researcher at Microsoft Research Montreal. Academic Background: Ph.D. in Computer Science, University of Toronto (2010–2014) M.Sc. in Computer Science, University of Toronto (2008–2010) B.Sc. (Honours) in Computer Science, minors in Linguistics and German, University of British Columbia (2004–2008) Research Interests: Jackie Cheung's research lies at the intersection of natural language processing, machine learning, and cognitive science. He focuses on natural language generation , automatic summarization , commonsense and pragmatic reasoning , and the evaluation of NLP systems . His work aims to build language models that reflect real-world structure and reasoning, with applications in health, education, and language revitalization. He is particularly interested in how implicit meaning is processed in context, a core concern in linguistic pragmatics. Publication Trends: His recent publications (2024–2025) show a strong emphasis on evaluation methodologies (e.g., COSMIC, ECBD), hallucination and factuality in language models, coreference and reasoning , and long-context modeling . He frequently collaborates across institutions and integrates insights from linguistics and psychology into NLP system design and analysis. Scientific Awards: Best Paper Award, ACL 2018 Outstanding Paper Award, NAACL 2018 Student Research Workshop SAC Award, ACL 2024 (for COSMIC) Best Poster Award, CMDO AI-Health Symposium 2024 Advising and Grants: He advises a large and diverse group of graduate students, including PhD and Master’s candidates, often in co-supervision with other faculty. His group has received support from major AI and health research initiatives, including CIFAR and Mila. He has trained alumni who have gone on to faculty and industry research positions. He has served in leadership roles in top NLP conferences, including as Senior Area Chair, Workshop Chair, and Program Chair of Canadian AI 2018. Labs and Teams: He co-directs the Reasoning and Learning Lab at McGill and is deeply involved with Mila – Quebec AI Institute . He founded the NLP Reading Group at McGill, which brings together researchers from computer science, linguistics, and information studies to discuss theoretical and applied NLP topics.
Alexei A. Efros is a Professor in the Department of Electrical Engineering and Computer Sciences (EECS) at UC Berkeley, where he holds the Howard Friesen Professorship and is affiliated with the Berkeley Artificial Intelligence Research (BAIR) Lab. He previously served on the faculty at the Robotics Institute of Carnegie Mellon University (CMU) and completed a postdoctoral fellowship at the University of Oxford. His research spans data-driven computer vision, self-supervised learning, computational photography, and applications to computer graphics and robotics. His research interests include: Data-Driven Computer Vision Self-Supervised and Unsupervised Learning Generative Models and Image Synthesis Visual Representation Learning Applications in Robotics and Human-Computer Interaction Intersections with Human Vision and the Humanities The recent publications highlight a strong trend toward self-supervised learning, visual reasoning, and generative modeling, particularly diffusion models and 3D scene understanding. His work increasingly bridges computer vision with language, robotics, and cognitive science, emphasizing interpretability and real-world applicability. There is a clear focus on leveraging unlabeled data and developing methods for robust, generalizable AI systems. His scientific awards and recognitions include: Berkeley Fellowship Google Fellowship Soros Fellowship NSF Fellowship SIGGRAPH Outstanding Doctoral Dissertation Award Facebook Fellowship Adobe Fellowship CMU School of Computer Science Distinguished Dissertation Award ACM Doctoral Dissertation Honorable Mention Alexei Efros has advised numerous PhD students and postdocs, many of whom have gone on to faculty positions at top institutions including CMU, Stanford, MIT, Columbia, NYU, and Georgia Tech. His lab has received research funding from major tech companies and federal agencies, though specific grants are not detailed in the text. He teaches core computer vision and machine learning courses at both undergraduate and graduate levels at UC Berkeley. His research group is highly active, with ongoing projects in 3D perception, generative modeling, and vision-language systems. He leads a vibrant research lab at UC Berkeley, part of the BAIR consortium, collaborating with leading researchers such as Jitendra Malik, Trevor Darrell, Pieter Abbeel, and Angjoo Kanazawa. His lab fosters strong interdisciplinary connections with institutions worldwide, including Oxford, INRIA, and École Normale Supérieure.
Christopher G. Atkeson is a Professor at the Robotics Institute at Carnegie Mellon University (CMU), where he has been since 2000 after previously holding positions at MIT and Georgia Institute of Technology. His research focuses on fulfilling the science fiction vision of machines achieving human levels of competence in perception, cognition, and action, with particular emphasis on understanding how to get machines to generate and perceive human behavior. Atkeson's work spans two complementary approaches: humanoid robotics and human aware environments. His research interests include nonparametric learning, memory-based learning, reinforcement learning, learning from demonstration, and modeling human behavior. He is particularly known for his work on robot learning of challenging dynamic tasks such as juggling, trajectory-based optimization, and soft robotics (including his contributions to the Baymax character in Disney's Big Hero 6). His recent publications demonstrate a strong focus on tactile sensing (FingerVision), human-in-the-loop optimization for exoskeletons, deep learning for locomotion control, and trajectory-based optimization methods. His work consistently bridges theoretical foundations in machine learning with practical implementations on physical robots. Among his scientific recognitions are an NSF Presidential Young Investigator Award, a Sloan Research Fellowship, and a Teaching Award from the MIT Graduate Student Council. Atkeson has advised numerous students who have gone on to successful careers in academia and industry, including notable researchers like Andrew Moore and Stefan Schaal. His teaching includes courses on dynamic optimization, humanoids, kinematics, dynamics, and control.
Prof. Dr. Claudine Moulin is a Full Professor of Historical Linguistics at the Department of German Studies, University of Trier. She co-directs the Trier Center for Digital Humanities and serves as Vertrauensdozentin der Deutschen Forschungsgemeinschaft. With academic roots in Brussels and Bamberg, she completed her PhD in 1990 and Habilitation in 1999 at the University of Bamberg. Her research spans medieval and early modern languages, manuscript studies, digital humanities, and Luxembourgish linguistics. As a leading scholar in historical linguistics, Moulin's work explores urban language history, phraseology, and cultural knowledge transmission through manuscripts. She has directed major digital humanities projects like LexicoLux and Cartul@rium, while pioneering digital codicology methods for medieval texts. Her research combines traditional philology with computational approaches. Her academic accolades include the Akademiepreis Rheinland-Pfalz (2010), Landesverdienstorden (2014), and the Verdienstkreuz am Bande (2025). She has held visiting professorships at Sorbonne, EHESS Paris, and EPHE, and received fellowships from the Humboldt Foundation and European Science Foundation. Notable Academic Roles: Co-founder and Chair of DHd (Digital Humanities in German-speaking countries) Founding member of Trier Center for Language and Communication Member of German Historical Institute Paris scientific board Advisory positions at Austrian Center for Digital Humanities and Herzog August Bibliothek Her editorial leadership includes chief editorship of Sprachwissenschaft journal and co-editorship of Germanistische Bibliothek monograph series. She has mentored over 40 graduate students in topics ranging from medieval marginalia to urban language studies.
Rui Zhang is an Associate Professor in the Department of Computer and Information Sciences at the University of Delaware. He holds a PhD in Electrical Engineering from Arizona State University (2013) and has held academic positions at the University of Hawaii and industry roles at UTStarcom. His research focuses on cybersecurity, wireless networks, and privacy-preserving technologies, with notable work on secure edge computing and mobile authentication systems. Education: PhD, Electrical Engineering, Arizona State University, 2013 M.E., Communication and Information Systems, Huazhong University of Science & Technology, 2005 B.E., Communication Engineering, Huazhong University of Science & Technology, 2001 Research Interests: Rui’s work spans secure wireless systems, mobile crowdsourcing, accessibility technologies for visually impaired users, edge computing, and social network privacy. He has led NSF-funded projects on trustworthy hierarchical edge computing and secure mobile cloud sensing. Grants & Awards: Recipient of the NSF CAREER Award (2017) and multiple NSF grants totaling over $1M. Current focus includes NSF-funded research on edge computing security and privacy-preserving data aggregation. Teaching: Has taught courses in algorithms, network security, and computer networks at both University of Delaware and University of Hawaii. Labs & Teams: Leads research projects in secure edge computing and collaborates with Arizona State University on federally funded initiatives. Active in organizing academic conferences like ISC 2016 and serving on editorial boards of IEEE journals.
Anthony Rowe is the Siewiorek and Walker Family Professor of Electrical and Computer Engineering at Carnegie Mellon University (CMU) and a Chief Scientist at Bosch Research. His primary affiliation is with the CyLab and the Wireless, Sensing and Embedded Systems (WiSE Lab) at CMU. He specializes in networked embedded systems, sensor networks, and extended reality (XR) technologies. His research emphasizes energy-efficient sensing, real-time localization, and XR integration with physical systems. Research Focus: His work spans XR systems (e.g., AR/VR edge networking in ARENA), mmWave radar for sensing (e.g., tire wear monitoring via Osprey), distributed edge computing (Silverline), and low-power wide-area networking (OpenChirp). Recent efforts include AI-integrated XR platforms (XaiR) and radar tomography (DART). Grants & Projects: Leads the CONIX Research Center ($27.5M NSF/DARPA grant), Bosch-funded edge computing projects, and DOE initiatives on microgrids. Notable projects include ARENA (XR edge architecture), GridBallast (smart grid control), and rural microgrid deployments in Haiti. Awards: Best Student Paper (ISMAR 2024), Best Paper (IPSN 2020), and the Steven J. Fenves Research Award (2015). Recognized for innovations in localization (MobiCom 2021), radar (ICRA 2023), and energy systems (BuildSys 2010). Teaching: Teaches courses on embedded systems (18-349/18-449), real-time systems, and mixed reality (18-453). Courses emphasize hands-on design and real-world applications. Labs & Teams: Directs the WiSE Lab, collaborating with Bosch Research and industry partners. The lab develops open-source frameworks like ARENA and OpenChirp, and contributes to standards for edge computing and sensing.
Anca Dragan is an Associate Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley, where she runs the InterACT Lab focused on algorithms for human-AI and human-robot interaction. Currently on leave from Berkeley, she leads AI Safety and Alignment at Google DeepMind, overseeing safety for Gemini models and preparing for future advancements. Dragan has been a co-PI of the Center for Human-Compatible AI and served on the steering committee for the Berkeley AI Research (BAIR) Lab. B.Sc. in Computer Science from Jacobs University Bremen, Germany Ph.D. from Carnegie Mellon University Dr. Dragan's research focuses on enabling AI agents to work effectively with, around, and in support of people. Her work bridges robotics, machine learning, and game theory to create systems that better understand human preferences and coordinate with users. Key areas include AI alignment (ensuring AI does what people actually want), learning reward functions from diverse human feedback forms, and developing algorithms for human-AI collaboration across domains like autonomous vehicles, brain-machine interfaces, and recommender systems. Her research emphasizes maintaining uncertainty about human preferences and accounting for the plurality of human values. Dr. Dragan's recent publications reveal a strong focus on addressing fundamental challenges in AI safety and alignment. Her work spans theoretical foundations of reward learning, practical implementations for human-AI coordination, and critical examinations of limitations in current approaches. There's a clear trajectory toward more robust, safe, and value-aligned AI systems that can handle complex human preferences while avoiding both present-day harms and potential catastrophic risks. IEEE RAS Early Academic Career Award in Robotics and Automation (2021) McEntyre Award for Excellence in Teaching (2020) PECASE (Presidential Early Career Award for Science and Engineering) (2019) Sloan Fellowship (2018) NSF CAREER Award (2017) Okawa Foundation Award (2017) MIT Tech Review 35 Innovators Under 35 (2017) Multiple best paper awards at top robotics and AI conferences Dr. Dragan has mentored numerous successful students who have gone on to faculty positions at MIT, Stanford, CMU, and Princeton, as well as industry roles at DeepMind, Waymo, and Meta. Her advising philosophy emphasizes both technical rigor and consideration of broader societal impacts. She has secured significant research funding including NSF CAREER, ONR Young Investigator, and Okawa Foundation awards, supporting work on human-AI interaction and alignment. Dragan has also consulted for Waymo for six years, helping develop roadmaps for deploying increasingly learning-based safety-critical systems. Dr. Dragan leads the InterACT Lab at UC Berkeley, which has produced influential work on Cooperative Inverse Reinforcement Learning, Inverse Reward Design, and other foundational concepts in human-AI interaction. The lab's research has significantly shaped the field of AI alignment, with applications spanning autonomous vehicles that coordinate with human drivers, brain-machine interfaces that adapt to user needs, and language models that better understand human preferences. Current work focuses on scaling safety approaches as AI capabilities advance, ensuring alignment keeps pace with technological progress.
