Deva Kannan Ramanan is a Professor at the Robotics Institute of Carnegie Mellon University , focusing on computer vision , machine learning , and human-centered robotics . His work bridges neurorobotics and visual perception , with applications in autonomous driving and 4D reconstruction . Research Topics Computer Vision 3-D Vision and Recognition Visual Servoing Neurorobotics Human-Centered Robotics Graphics & Creative Tools His recent publications in CVPR , ICRA , and ICCV emphasize 4D human reconstruction , neural rendering , and vision-language models for autonomous systems. He serves as General Chair of CVPR 2027 and Program Chair of CVPR 2018 , with IARPA funding for aerial-ground rendering (2023-2027). Current students include PhD candidates Sally Chen, Kangle Deng, and Zhiqiu Lin, while past advisees like Arun Vasudevan and Olga Russakovsky now hold positions at Amazon and Meta respectively.
Michael Kaess is an Associate Professor at the Robotics Institute, Carnegie Mellon University (CMU), within the School of Computer Science. He leads the Robot Perception Lab (RPL) and contributes to the Field Robotics Center (FRC) and Computer Vision Group (CV). His research focuses on efficient perception algorithms for mobile robots, particularly in 3D mapping, SLAM, and sensor fusion using vision, LiDAR, inertial, and sonar data. Kaess holds a PhD in Computer Science from Georgia Tech and was a postdoc at MIT's Marine Robotics Lab. Education: Georgia Institute of Technology, PhD in Computer Science (2008) MIT, Postdoctoral Associate (2008–2010) Research Interests: Kaess develops algorithms for robust and efficient inference in robotics, emphasizing factor graphs and linear algebra. His work spans underwater robotics, aerial systems, tactile SLAM, and multi-sensor integration. Key areas include SLAM with planes/lines, imaging sonar reconstruction, and neural field methods for LiDAR-visual fusion. Publications: Over 145 papers, including work on EDPLVO (visual odometry), HoloOcean (underwater simulation), and neural radiance fields with LiDAR. Recent trends focus on robust incremental smoothing, acoustic-optical fusion, and real-time volumetric mapping. Awards: Recognized with the RSS Test of Time Award (2020), Outstanding Associate Editor (2022), and paper awards at ICRA/ICRA. Active in conference organization (IROS/ICRA program committees). Advising & Grants: Supervises 10+ current PhD/MSc students, with past advisees contributing to CoRL/ICRA work. Manages grants in perception, autonomy, and marine robotics. Teaches courses like Robot Localization and Mapping (16-833). Labs/Teams: Directs RPL, collaborates with FRC on field robotics. Develops open-source tools like GTSAM (GNU Toolkit for Smoothing and Mapping).
Katerina Fragkiadaki is the JPMorgan Chase Associate Professor of Computer Science in the Machine Learning Department at Carnegie Mellon University. She works at the intersection of Artificial Intelligence, Computer Vision, Machine Learning, Language Understanding, and Robotics. PhD from GRASP Lab, University of Pennsylvania Postdoctoral researcher at UC Berkeley (with Jitendra Malik) and Google Research Recipient of NSF CAREER, DARPA Young Investigator, Amazon, Google, Sony, UPMC, and AFOSR awards Organizer of CoRL 2023 Workshop on Generalist Robots ICLR 2024 Program Chair, multiple area chair roles Her research group focuses on developing machines that autonomously improve world models through human-environment interactions, with specific emphasis on: Representation learning and video understanding 2D/3D unified vision-language models Generative simulation and reinforcement learning Real2Sim/Sim2Real robot learning Continual learning and spatial common sense 3D scene reconstruction and dynamics Recent publications highlight advancements in: 3D mesh generation with compositional transformers Unified 2D/3D perception frameworks Physics-aware generative models Diffusion-based robotic manipulation policies Embodied agents with memory prompting Awards include: 2024: DARPA Young Investigator Award 2023: Amazon Faculty Award 2022: Sony Faculty Research Award 2021: UPMC Faculty Research Award 2020: NSF CAREER Award 2019: Google Faculty Award Key collaborations span institutions including UC Berkeley, Google Research, Stanford, MIT, and University of Tsukuba. Her work bridges theoretical innovation with practical applications in: Autonomous robot manipulation 4D world modeling Language-grounded perception Visual dynamics prediction Embodied program synthesis Physics-based simulation engines
Osman Yağan is a Research Professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University (CMU), with affiliate faculty status in the School of Computer Science. He is also a core member of CyLab Security and Privacy Institute. Prior to joining CMU in 2013, he was a Postdoctoral Research Fellow at CyLab. He holds a Ph.D. in Electrical and Computer Engineering from the University of Maryland (2011) and a B.S. from Middle East Technical University (2007). His research focuses on modeling, analysis, and optimization of computing systems, leveraging applied probability, network science, data science, and machine learning. Key areas include multi-armed bandits, resilient machine learning, contagion processes in networks, and cybersecurity. Research Interests include Machine Learning, Data Science, Network Science, Cybersecurity, and Robustness in Cyber-Physical Systems. He has advised numerous students, including current PhD candidates Yurun Tian, Orkun İrsoy, and Ishank Juneja, as well as notable alumni such as Mansi Sood (now at MIT) and Jun Zhao (Assistant Professor at Nanyang Technological University). Key Awards include the CIT Dean's Early Career Fellowship, IBM Academic Award, and Best Paper Awards at ICC 2021, IPSN 2022, and ASONAM 2023. His work spans theoretical contributions (e.g., contagion models in multi-layer networks) and applied research (e.g., mitigating cascading failures in power systems). He leads or co-leads grants from ONR, NSF, and ARO, focusing on resilient machine learning, network robustness, and pandemic modeling.
Anthony Rollett is a Professor in the Department of Materials Science and Engineering at Carnegie Mellon University , where he has been a faculty member since 1995. He serves as the Principal Investigator and Co-Director of the NASA-supported Institute for Model-Based Qualification & Certification of Additive Manufacturing (IMQCAM) and co-director of the Next Manufacturing Center . Prior to CMU, he held leadership roles at Los Alamos National Laboratory (1991-1995). Education: Ph.D., Materials Engineering, Drexel University (1987) MA, Metallurgy and Materials Science, Cambridge University (1977) Research Interests: Rollett’s work focuses on microstructural evolution and microstructure-property relationships in 3D using experiments and simulations. His expertise spans additive manufacturing , metal 3D printing , materials for energy systems , grain growth , recrystallization , and stereology , with techniques like high-energy diffraction microscopy (HEDM) and dynamic x-ray radiography (DXR) . Scientific Contributions: He has over 320 peer-reviewed publications and an h-index >80 . His recent articles highlight machine learning for laser processing , fatigue analysis of additively manufactured alloys, and design optimization for heat exchangers in supercritical CO2 and solar thermal applications . Scientific Awards: Fellow of ASM International (1996) Fellow of the Institute of Physics (UK) (2004) Fellow of The Minerals, Metals & Materials Society (TMS) (2011) Cyril Stanley Smith Award (TMS, 2014) Member of Honor, French Metallurgical Society (2015) US Steel Professor (2017) Francqui International Professor (2020-2021) International FAME Award (2023) Leadership & Impact: Rollett co-led the development of a NASA Space Technology Research Institute for additive manufacturing and established a new master’s program in additive manufacturing (2018). His research group is funded by industry , federal agencies , and Pennsylvania state grants . He also serves on the Basic Energy Science Advisory Committee and Defense Programs Advisory Committee for the Department of Energy.
Yaser Sheikh is an Associate Professor at the Robotics Institute of Carnegie Mellon University (on leave) and Director of the Facebook Reality Lab, Pittsburgh . He holds appointments in the Mechanical Engineering Department and focuses on ' metric telepresence ' for AR/VR interactions. His research spans machine perception , computer vision , computer graphics , and machine learning , with applications in social behavior modeling and dynamic 3D reconstruction. University: Carnegie Mellon University Roles: Associate Professor (Robotics Institute), Director (Facebook Reality Lab) Contact: yaser@cs.cmu.edu, yasers@fb.com Research Interests include: Computer Vision: Pose estimation, 3D reconstruction, camera calibration Computer Graphics: Face/Hand animation, photorealistic rendering Machine Learning: Neural rendering, unsupervised learning for landmark detection AR/VR: Telepresence, immersive social interactions Notable Trends in Publications reveal a focus on real-time pose estimation (e.g., OpenPose), dynamic 3D reconstruction , and codec avatars for VR/AR. Recent works emphasize universal priors and neural rendering for photorealistic avatars. Scientific Awards include: Popular Science’s Best of What’s New Award Honda Initiation Award (2010) Best Paper Awards: WACV (2012), SCA (2010), ICCV THEMIS (2009) Hillman Fellowship for Excellence in Computer Science Research (2004) Advising and Grants: He has advised numerous PhD students (e.g., Hanbyul Joo, Tomas Simon) and received funding from the National Science Foundation , DARPA, and industry partners like Intel , Disney , and Honda . Labs & Teams: Leads the Facebook Reality Lab in Pittsburgh, collaborating with institutions like Carnegie Mellon University and Disney Research.
Burak Ozdoganlar is a Ver Planck Endowed Chair Professor of Mechanical Engineering at Carnegie Mellon University (CMU) and Associate Director of the Engineering Research Accelerator. He holds courtesy faculty positions in Biomedical Engineering and Materials Science and Engineering. Ozdoganlar earned his Ph.D. in Mechanical Engineering from the University of Michigan (1999), M.S. degrees from Ohio State University (1993, 1995), and a B.S. in Aeronautical Engineering from Istanbul Technical University (1991). Ph.D., Mechanical Engineering, University of Michigan (1999) MS, Mechanical Engineering, Ohio State University (1995) MS, Aeronautical and Astronautical Engineering, Ohio State University (1993) BS, Aeronautical Engineering, Istanbul Technical University (1991) Ozdoganlar’s research focuses on multi-scale manufacturing processes (macro/micro/nano), precision engineering , structural dynamics , and modal testing , with applications in biomedical device fabrication , microneedle arrays , soft electronics , and 3D ice printing for vascular networks. His work bridges computational modeling with experimental validation. Recent scientific awards include the 2023 AIMBE College of Fellows induction, ASME Fellow (2019), and NSF CAREER Award (2006). He served as interim CTO of the Advanced Robotics for Manufacturing (ARM) Institute and chaired the ASME-MED Manufacturing Equipment Technical Committee. Ozdoganlar leads projects in scalable manufacturing for implantable medical devices , bioelectric medicine , and wearable robotics . His lab develops 3D ice-printed vascular templates for tissue engineering and liquid metal circuits for soft electronics, funded by institutions like the Manufacturing Futures Institute and ARPA-H.
Jack Beuth is a Professor of Mechanical Engineering at Carnegie Mellon University (CMU), affiliated with the College of Engineering. He has been on the faculty since 1992 and leads the NextManufacturing Center, focusing on additive manufacturing (AM) research. His work emphasizes process mapping for AM, material science, and machine learning integration in manufacturing processes. Key affiliations include the Engineering Research Accelerator and the Manufacturing Futures Institute. Education: Ph.D. in Engineering Sciences, Harvard University (1992) M.S. in Engineering Sciences, Harvard University (1989) M.S. in Engineering Science and Mechanics, Virginia Tech (1987) B.S. in Engineering Science and Mechanics, Virginia Tech (1984) Research Interests: Additive Manufacturing (process modeling, material characterization, and defect analysis) Melt pool dynamics and thermal modeling Machine learning for process optimization and quality control Advanced materials for AM (e.g., Ti-6Al-4V, Inconel 718) His research has led to innovations like 'process map' approaches for AM, enabling better control over variables such as melt pool geometry and microstructure. Awards and Recognition: Ralph R. Teetor Educational Award (1998) George Tallman and Florence Barrett Ladd Development Professorship (2000) ASME Curriculum Innovation Award (2005) Benjamin Richard Teare Teaching Award (2009) Grants and Collaborations: $3.5M cooperative agreement with the U.S. Army Combat Capabilities Development Command’s Army Research Laboratory (ARL) for AI-driven AM process optimization. Collaborations with Westinghouse Electric Company on 3D-printed nuclear components, such as spacer grids for pressurized water reactors. Labs and Teams: NextManufacturing Center: A research hub for AM innovation, emphasizing industrial partnerships and applied research. Beuth’s Additive Lab: Specializes in melt pool analysis, process mapping, and material behavior under AM conditions.
Martin Larsson is a Professor in the Department of Mathematical Sciences at Carnegie Mellon University (CMU), affiliated with the Mellon College of Science. He holds a Ph.D. from Cornell University and completed a postdoctoral appointment at the Swiss Finance Institute at EPFL, Lausanne, Switzerland. His research focuses on Mathematical Finance, stochastic analysis, probability, and statistics, with emphasis on affine and polynomial processes, stochastic portfolio theory, and sequential statistics. Key research domains include modeling interest rate term structures, large-scale equity market dynamics, and statistical testing in online settings. He serves as the Departmental representative for the Master of Science in Computational Finance (MSCF) program at CMU. Larsson has received the Bruti-Liberati Visiting Fellowship from the University of Technology Sydney. His work bridges theoretical probability with applications in finance, including contributions to stochastic volatility modeling, optimal contracts in trading, and robust portfolio optimization under uncertainty. Publications span topics such as martingale exit times, Wasserstein distance convergence, and ergodic control in stochastic systems, reflecting his interdisciplinary approach to mathematical finance and probability theory. His research often combines analytical techniques with stochastic control and geometric flows.
Hanbyul Joo is an Assistant Professor in the Department of Computer Science and Engineering at Seoul National University (SNU). Prior to joining SNU, he was a Research Scientist at Facebook AI Research (FAIR) in Menlo Park. He completed his Ph.D. in the Robotics Institute at Carnegie Mellon University, working with Yaser Sheikh, and received his M.S. in Electrical Engineering and B.S. in Computer Science from KAIST, Korea. Dr. Joo's educational journey began at KAIST, where he earned both his Bachelor's and Master's degrees. He then pursued his Ph.D. at Carnegie Mellon University's Robotics Institute, completing his dissertation titled "Sensing, Measuring, and Modeling Social Signals in Nonverbal Communication." His doctoral work focused on developing the Panoptic Studio, a unique sensing system with over 500 synchronized cameras for capturing social interactions. Dr. Joo's research primarily focuses on endowing machines and robots with the ability to perceive and understand human behaviors in 3D . His goal is to build "social Artificial Intelligence" that can interact with humans using social signals (body languages). He pursues this direction using data-driven methods where data is collected by measuring the wide spectrum of social signals transmitted during interpersonal social interaction. His research spans computer vision, machine learning, computer graphics, and robotics , with particular emphasis on 3D human pose estimation, human-object interaction, and social signal processing. His recent publications demonstrate a clear trend toward leveraging diffusion models for 3D reconstruction and generation tasks, with a focus on human-centric applications. His work bridges the gap between 2D image understanding and 3D scene reconstruction, often utilizing pre-trained models to overcome data limitations. The research consistently addresses fundamental challenges in understanding human behavior, interaction with objects, and social dynamics in 3D space. Dr. Joo is a recipient of several prestigious awards including the Samsung Scholarship and the CVPR Best Student Paper Award in 2018 . His paper "Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies" received this honor at CVPR 2018. His research has been widely recognized in top computer vision and AI conferences, with multiple oral presentations at venues like CVPR, ICCV, and ECCV. Dr. Joo actively mentors a large group of students, with approximately 15 current students working toward MS/PhD degrees under his supervision. His lab, the SNU VCLab, focuses on cutting-edge research in computer vision and graphics. He has secured significant research funding through his work, though specific grant details aren't provided on his website. Dr. Joo frequently serves as an area chair for major conferences including CVPR, ICCV, and NeurIPS, demonstrating his standing in the academic community. Dr. Joo leads the SNU VCLab, which has developed several notable datasets and tools including SNU ParaHome, FrankMocap, and the CMU Panoptic Studio Dataset. His lab maintains strong industry connections, with students interning at leading companies like Meta. The lab's research focuses on building the infrastructure and algorithms needed for social AI, with an emphasis on practical applications that can be deployed in real-world settings.
Fernando De la Torre is a Courtesy Professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University, with an affiliation to the Robotics Institute where he has been a research faculty member since 2005. He holds a Ph.D. in Electronic Engineering from Ramon Llull University (2002). His research focuses on machine learning and computer vision, with applications in human health, augmented/virtual reality, generative models, and data-centric methodologies. He directs the Human Sensing Laboratory, which explores technologies for human behavior analysis and health monitoring. Notable contributions include founding FacioMetrics LLC (acquired by Meta), advancing facial recognition and 3D human digitization, and developing frameworks for robust visual models. His work bridges theory and practice, with over 225 peer-reviewed publications and editorial roles, including Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence. Recent research trends emphasize generative AI applications in satellite imagery analysis, VR/AR rendering optimizations (e.g., Gaussian splatting), and clinical motion recognition for healthcare. His projects often intersect with industry, addressing challenges in wearable health monitoring and immersive technologies. His lab collaborations span academia and industry, focusing on scalable solutions for 3D human modeling, adversarial robustness, and multimodal data fusion. Key achievements include pioneering work on 3D face animation from speech and garment reconstruction from single images.
Robert E. (Rob) Kass is the Maurice Falk University Professor of Statistics and Computational Neuroscience at Carnegie Mellon University, holding joint appointments in the Department of Statistics & Data Science, Machine Learning Department, and Neuroscience Institute. His research spans Bayesian statistics, neural data analysis, and computational neuroscience. Kass earned a B.A. in Mathematics from Antioch College, a Ph.D. in Statistics from the University of Chicago, and has been at CMU since 1981. He has served as Department Head of Statistics (1995–2004) and Interim Co-Director of the CNBC (2015–2018). His work focuses on statistical methods for neuroscience, particularly analyzing spike train data and identifying cross-brain interactions. Notable contributions include co-authoring Analysis of Neural Data and foundational articles on Bayesian inference. Kass has received prestigious awards such as the National Academy of Sciences membership and COPSS Distinguished Achievement Award. Research interests include computational neuroscience, statistical modeling of neural systems, and interdisciplinary education. He has advised numerous students and co-organized major workshops like the Statistical Analysis of Neuronal Data series. Kass’s work emphasizes the interplay between statistical rigor and scientific insight, bridging theoretical and applied domains. Education: B.A. in Mathematics, Antioch College Ph.D. in Statistics, University of Chicago Postdoctoral Fellow, Princeton University Scientific contributions include advancements in spike train analysis, Bayesian model assessment, and statistical methods for brain connectivity. His work on neural synchrony and population coding has influenced both theoretical and applied neuroscience.
Aswin Sankaranarayanan is a Professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University (CMU) , where he leads the Image Science Lab . His research focuses on computational photography , 3D shape estimation , and novel imaging system design . He earned his Ph.D. in Electrical and Computer Engineering (2009) from the University of Maryland and completed a postdoctoral fellowship at Rice University (2012) . Research Themes: Developing imaging systems that exploit low-dimensional signal models to overcome traditional sensing limitations Co-design of optics and processing algorithms for efficient sensing Application of non-linear signal models to high-dimensional data Advancing compressed sensing and big data processing techniques Scientific Recognition: SIGGRAPH 2023 Best Paper Award (Split-Lohmann Multifocal Displays) CVPR 2019 Best Paper Award (Fermat Paths for NLOS Reconstruction) NSF CAREER Award (2017) Dean’s Early Career Fellowship (2018-2021) Herschel Rich Invention Award (2016) Technical Contributions: His recent publications reveal expertise in non-line-of-sight shape reconstruction , VR/AR display systems , and biomedical imaging . Collaborations span institutions like University College London and University of Toronto.
Joshua D. Bard is an Associate Professor and Associate Head for Design Research at Carnegie Mellon University's School of Architecture. His work bridges traditional craft and cutting-edge robotics, focusing on human-machine collaboration in construction domains. He leads Archolab, an award-winning research group exploring digital fabrication methods like 'Morphfaux' (robotic plaster techniques) and 'Spring Back' (parametric steam bending). Education: M.Arch (Distinction) from University of Michigan; B.A. in Literature & Philosophy from Wheaton College. Professional affiliations include the Manufacturing Futures Institute and rob|arch. Research emphasizes reviving historical crafts through digital tools, such as augmented reality interfaces for architectural education and thermal-tuned concrete panels via robotic processes. His teaching includes generative modeling and architectural robotics labs. Awards: Architect Magazine R+D Award, Canadian Wood Council Merit Award Key Projects: Plaster ReCast AR app, Thermally Informed Robotic Concrete Panels Collaborators: Dana Cupkova, Garth Zeglin, Steven Mankouche Current courses include 62-225 Generative Modeling and 48-555 Introduction to Architectural Robotics. His work is featured in venues like the Carnegie Museum of Art and academic journals like International Journal of Architectural Computing .
Dr. Yongjie Jessica Zhang is a Professor at Carnegie Mellon University, holding appointments in both the Department of Mechanical Engineering and the Department of Biomedical Engineering . She received her B.S. and M.S. in Engineering Mechanics from Tsinghua University, followed by an M.S. in Aerospace Engineering and a Ph.D. in Computational Engineering and Sciences from the University of Texas at Austin. After a postdoctoral fellowship at ICES, she joined CMU in 2007, advancing from assistant to full professor by 2016. Research Interests : Image-based geometric modeling, mesh generation, finite element analysis (FEA), isogeometric analysis, and applications in computational biomedicine, materials science, and computer-assisted surgery. Leadership Roles : Chair of Solid Modeling Association (2019-2020), USACM Executive Committee Member-at-Large (2017-2021), and ELATE Fellow (2017-2018). Her work addresses the critical challenge of automating high-fidelity geometric modeling and mesh generation for complex domains (e.g., human anatomy), which traditionally consumes ~80% of FEA time. Her group develops AI-driven methods for multiscale modeling (molecular to organ), with applications in neuroscience , biomechanics , and 4D printing . Notable awards include the Presidential Early Career Award (PECASE) , NSF CAREER Award , and ASME Van C. Mow Medal (2025) . Dr. Zhang’s publications span over 170 peer-reviewed articles, focusing on truncated hierarchical B-splines , polycube meshing , and neurite transport modeling . She has advised more than 40 students, including PhD candidates and postdoctoral fellows. Her editorial roles include Associate Editor of Computer Aided Geometric Design and editorial board memberships in Computer-Aided Design and Engineering with Computers .
