جستجوی استاد راهنمای دانشگاهی

Jun-Yan Zhuمشاهده پروفایل

استادیار

• Computer Vision
• Generative Models
• Image Synthesis
• +۶ مورد دیگر

Jun-Yan Zhu is an Assistant Professor at Carnegie Mellon University's School of Computer Science, affiliated with the Robotics Institute and Computer Science Department. His research focuses on generative models, computer vision, and graphics. He holds a B.E. from Tsinghua University and a Ph.D. from UC Berkeley, with postdoctoral work at MIT CSAIL. Zhu leads the Generative Intelligence Lab, exploring human-creator collaboration with generative models. Affiliations: Robotics Institute, CMU Graphics Lab, CMU Computer Vision Group Education: B.E. (Tsinghua), Ph.D. (UC Berkeley) Research Interests: Generative AI, image/video synthesis, neural rendering, tactile sensing integration Notable contributions include CycleGAN, pix2pix, and GAN compression techniques. His work has been commercialized in Adobe's Firefly and NVIDIA's Canvas tools. Awards: ACM SIGGRAPH Dissertation Award, David J. Sakrison Prize, CVPR Best Paper Finalist Lab Members: 10+ PhD students and researchers Current projects include LEGO design synthesis, tactile-driven 3D generation, and generative model personalization.

Aswin Sankaranarayananمشاهده پروفایل

استاد

• Computational Photography
• 3D Shape Estimation
• Imaging Systems
• +۴ مورد دیگر

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.

Yongjie Jessica Zhangمشاهده پروفایل

استاد

• Finite Element Method
• Isogeometric Analysis
• Image-Based Geometric Modeling
• +۵ مورد دیگر

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 .

Joseph Ramseyمشاهده پروفایل

پژوهشگر

• Causal Inference
• Machine Learning
• Computational Epistemology
• +۴ مورد دیگر

Joseph Ramsey is a Researcher in the Department of Philosophy at Carnegie Mellon University , affiliated with the Dietrich College of Humanities and Social Sciences . He serves as Director of Research Computing and has been instrumental in developing computational infrastructure and algorithms for causal inference. Core projects: Tetrad (causal search algorithms), AProS (proof generator for logic), Causality Lab , and Laboratory for Symbolic and Educational Computing . His research spans causal modeling, algorithm design, and applications in neuroscience, bioinformatics, and education. He has contributed to software tools like Causal-learn and Py-Tetrad , enabling scalable causal discovery in high-dimensional datasets. He has received funding from NASA, NSF, and the University of Pittsburgh for projects ranging from Martian rover software to glaucoma detection models. His work integrates philosophy, computer science, and applied statistics.

Daniel Cardoso Llachمشاهده پروفایل

دانشیار

• Architectural Automation
• Human-Machine Interaction
• Digital Technology History
• +۳ مورد دیگر

Daniel Cardoso Llach is an Associate Professor at Carnegie Mellon University's School of Architecture , where he chairs the Master of Science in Computational Design program and co-directs the CoDe Lab . His scholarship merges history, science and technology studies (STS), and computational design , focusing on the cultural and socio-technical dimensions of design automation. Education: PhD and MS in Architecture: Design and Computation from MIT , BArch from Universidad de los Andes Research Grants: Supported by the Graham Foundation for historical CAD exhibitions and by the Alexander Von Humboldt Foundation for postwar computational design research in Germany His work interrogates the politics of software, the materiality of computational systems , and the ethical implications of AI/robotics in architectural practice. Recent projects include reconstructing early CAD systems and analyzing data-driven urban technologies. Scientific awards include: Alexander Von Humboldt Fellowship (2024–2025) ACM CSCW Methods Mention for emulation-based software research (2021)

Amritanshu Pandeyمشاهده پروفایل

استادیار

• Grid Simulation and Optimization
• Grid Cybersecurity
• Modeling of Future Energy Systems
• +۳ مورد دیگر

Amritanshu Pandey is an Assistant Professor in Electrical Engineering at the University of Vermont, with a part-time adjunct appointment in Electrical and Computer Engineering at Carnegie Mellon University. His research focuses on enhancing the efficiency, reliability, and security of electric grids through methods in circuit theory, optimization, and machine learning. He pioneered the SUGAR simulation engine for power systems and collaborates globally on grid challenges. Research Interests: Pandey's work spans renewable integration, grid cybersecurity, digital twins, and decarbonization. Key projects include developing algorithms for large-scale grid optimization, anomaly detection, electric vehicle infrastructure modeling, and cyber-resilient energy systems. His research addresses real-world challenges in rapidly evolving grids across Asia and Africa. Awards: Best Paper Award, IEEE PES General Meeting (2017, 2021) Best-of-the-Best Paper Award, IEEE PES General Meeting (2021) Best Student Paper Runner-up, ECML-PKDD (2018) Students & Labs: He advises 7 PhD students and has graduated 11 advisees (PhD/MS/BS). His lab focuses on power systems innovation, including the SUGAR simulation framework and projects on grid cybersecurity and sustainable electrification.

Keenan Craneمشاهده پروفایل

دانشیار

• Computer Science
• Mathematics
• Scientific Computing
• +۷ مورد دیگر

Keenan Crane is the Michael B. Donohue Associate Professor of Computer Science and Robotics at Carnegie Mellon University , with membership in the Center for Nonlinear Analysis and mentorship in the Geometry Collective . His research bridges differential geometry and computer science to develop fundamental algorithms for geometric data processing. Education : BS from University of Illinois at Urbana-Champaign, PhD from Caltech Fellowships : Google PhD Fellow, NSF Mathematical Sciences Postdoctoral Fellow Research focuses on Discrete Differential Geometry , addressing PDE solutions, mesh processing, and geometric modeling through methods like: Walk on Spheres for PDEs Intrinsic Triangulations for robust geometry Repulsive Energy formulations for collision avoidance Recent publications span 2025–2021 , emphasizing grid-free algorithms , anisotropic mesh generation , and differentiable systems . Scientific accolades include Packard Fellowship and NSF CAREER Award . Students include Nicole Feng , Olga Gutan , and Zoë Marschner . During his 2024 sabbatical at Roblox , he does not accept new researchers. Key software contributions include Penrose (math diagram generation) and I♥Mesh (domain-specific language for mesh algorithms).

Minchen Liمشاهده پروفایل

استادیار

• Computer Graphics
• Machine Learning
• Robotics
• +۴ مورد دیگر

Minchen Li Assistant Professor at Carnegie Mellon University's School of Computer Science (Computer Science Department). Formerly an Assistant Adjunct Professor at UCLA's Mathematics Department. Holds a Ph.D. from the University of Pennsylvania's SIG Center for Computer Graphics, followed by a postdoctoral position there. Research focuses on physics-based simulation, integrating numerical analysis, high-performance computing, and machine learning. Notable contributions include the IPC method for frictional contact simulation and large-scale material point methods. Education Ph.D., Computer and Information Science, University of Pennsylvania (2020) M.Sc., Computer Science, University of British Columbia (2018) B.Eng., Computer Science and Technology, Zhejiang University (2015) Research Interests Advances in physical simulation for visual computing, robotics, and manufacturing. Specializes in robust and efficient methods for solid/fluid dynamics, contact modeling, and GPU acceleration. Combines numerical analysis with machine learning to address challenges in simulation accuracy and versatility. Awards 2021 ACM SIGGRAPH Outstanding Doctoral Dissertation Award 2024 SCA Early Career Researcher Award Advising & Labs Leads the Simulation Intelligence Group (SIG) at CMU Graphics Lab. Advises PhD students Guying Lin, Juntian Zheng, Michael Liu, and Zhaofeng Luo. Collaborates with industry and academic partners on projects like VR-based modeling systems and scalable simulation frameworks.

Will Townesمشاهده پروفایل

استادیار

• Biostatistics
• Epidemiology
• Infectious Disease Forecasting
• +۷ مورد دیگر

Will Townes is an Assistant Professor in the Department of Statistics and Data Science at Carnegie Mellon University's Dietrich College of Humanities and Social Sciences. He joined CMU in 2022 after completing a postdoctoral fellowship in computer science at Princeton University with Barbara Engelhardt. His academic journey includes a Ph.D. in biostatistics from Harvard University under Rafael Irizarry's supervision, an M.S. in math and statistics from Georgetown, and earlier work in tropical ecology fieldwork in the Philippines. Dr. Townes specializes in applied statistics with primary focus areas in biomedical and public health domains. His research centers on wastewater-based epidemiology, wearable devices, and auxiliary signals for infectious disease tracking and forecasting as part of the Delphi research group. He has developed normalization, feature selection, and dimension reduction methods for single cell RNA-Seq and spatial transcriptomics data analysis. His broader research interests span biostatistics, epidemiology, genomics, time series forecasting, and theoretical aspects of Tweedie distributions. His recent publications reveal a strong emphasis on wastewater surveillance methodologies, single-cell data analysis techniques, and infectious disease forecasting models. The research demonstrates a consistent focus on computational scalability and efficiency through approximate inference techniques. Dr. Townes approaches statistical problems with a pragmatic perspective, comfortable with probabilistic (Bayesian) models while drawing inspiration from diverse statistical perspectives. Member of DELPHI Lab Group at CMU Active contributor to genomics and biostatistics research Focus on computational efficiency in statistical methods Dr. Townes mentors several students including Gabrielle Thivierge (PhD candidate working on infectious disease forecasting methods), Julia Elrod, and Anna Rosengart. He teaches data science courses at CMU, including a field course in Costa Rica where students work with community partners on real-world data projects involving water quality indicators, spring flow rates, and ecological monitoring.

Valerie Venturaمشاهده پروفایل

استاد

• Computational Neuroscience
• Time Series Forecasting
• Graphical Models
• +۶ مورد دیگر

Valerie Ventura is a Professor in the Department of Statistics and Data Science at Carnegie Mellon University's Dietrich College of Humanities and Social Sciences. She serves as Co-Director of the Ph.D. Program and maintains dual affiliations as affiliated faculty in the Machine Learning Department and the Center for the Neural Basis of Cognition (CNBC). As a graduate advisor for the Program in Neural Computation (PNC), she bridges statistical methodology with neuroscience applications. Her research focuses on computational neuroscience, particularly time series forecasting, networks, algorithms, and nonparametric methods. Key research areas include computational neuroscience, biostatistics & epidemiology, graphical models & networks, and DELPHI lab projects. Her work integrates advanced statistical techniques to solve complex problems in neural data analysis, motor control, and neural decoding. Analysis of her publication record reveals consistent contributions to neural decoding methodologies, spike train analysis, and cortical covariance modeling. Her recent work emphasizes practical applications in brain-machine interfaces and neural prosthetics, with a strong focus on improving decoding accuracy through novel statistical approaches to spike sorting and waveform analysis. The integration of machine learning with traditional statistical methods characterizes her interdisciplinary approach. Scientific Awards: 2006 Canadian Journal of Statistics Best Paper Award As an educator, Ventura serves as Co-Director of the Ph.D. Program in Statistics and Data Science while advising students through the CNBC's Program in Neural Computation. Her collaborations span multiple departments and research centers, particularly through the DELPHI Lab Group which focuses on computational neuroscience applications. Current research directions suggest continued innovation in neural decoding algorithms and applications to motor control systems.

Feras Saadمشاهده پروفایل

استادیار

• Probabilistic Programming
• Artificial Intelligence
• Programming Languages
• +۴ مورد دیگر

Feras Saad is an Assistant Professor in the Computer Science Department at Carnegie Mellon University, affiliated with the Principles of Programming and Artificial Intelligence groups. He received his Ph.D. in Computer Science from the Massachusetts Institute of Technology (MIT) in 2022, where his dissertations on probabilistic programming systems earned him the George M. Sprowls PhD Thesis Award and Charles & Jennifer Johnson MEng Thesis Award. His research focuses on developing scalable computing systems for probabilistic modeling and inference, integrating ideas from programming languages and probabilistic AI. Key research themes include probabilistic programming languages, automated probabilistic model discovery, statistical estimation and testing, random sampling algorithms, and applications in science and engineering. His lab explores new techniques to improve reasoning systems through automation, accuracy, and scale. Dr. Saad has published extensively in top venues including PLDI, POPL, ICML, and Nature Communications. His work spans foundational computational questions to practical software systems for probabilistic inference. Research trends show consistent focus on bridging theoretical computer science with practical applications in probabilistic modeling, with recent advances in random sampling algorithms and probabilistic programming systems. Awards and honors include: George M. Sprowls PhD Thesis Award in Artificial Intelligence and Decision Making (2023) Charles & Jennifer Johnson MEng Thesis Award in Computer Science (2017) Editor's Highlight for Nature Communications paper (2024) He currently advises graduate students Gaurav Arya and Thomas Draper in the Probabilistic Computing Systems Lab. His research is supported by software libraries including GenSQL, BayesNF, and SPPL that enable practical applications across scientific domains.

• Machine Learning
• Generative Modeling
• Scientific Computing
• +۳ مورد دیگر

Tanya Marwah is a Research Fellow at the Simons Foundation , collaborating with Polymathic AI . She earned her PhD from Carnegie Mellon University's Machine Learning Department, co-advised by Prof. Andrej Risteski and Prof. Zachary Lipton, and holds a master's degree from CMU's Robotics Institute. Her research bridges Machine Learning and Scientific Computing , focusing on generative modeling , inverse problems , and building scientific agents . Her work explores theoretical and empirical foundations for applying ML to differential equations, with key contributions in neural operators , memory mechanisms , and edge embeddings in GNNs . Recent publications highlight trends in PDE solvers via LLMs , cross-modal adaptation , and implicit regularization in SGD . She has received the prestigious Siebel Scholar award and actively contributes to top ML venues (NeurIPS, ICML, ICLR, TMLR). Her collaborations span institutions including Carnegie Mellon University, Polymathic AI, and CMU's Robotics Institute.

Lisa Leeمشاهده پروفایل

پژوهشگر

• Artificial Intelligence
• Reinforcement Learning
• Continual Learning
• +۵ مورد دیگر

Lisa Lee is a Research Scientist at Google DeepMind, focusing on creating AI agents that emulate biological learning and adaptability. She previously taught at Princeton University and received TA awards for Deep Reinforcement Learning and Probabilistic Graphical Models. Education: PhD in Machine Learning from Carnegie Mellon University (advised by Ruslan Salakhutdinov and Eric Xing); A.B. in Mathematics from Princeton University (advised by Sanjeev Arora). Her research centers on AI embodiment, intrinsic motivation, and hierarchical planning. She explores how evolutionary-inspired inductive biases and memory mechanisms can enable agents to generalize across physical and conceptual domains, as demonstrated in her work on robotic agility benchmarks and multimodal transformers. Notable scientific contributions include the Barkour quadruped robot benchmark, Gemini multimodal models, and theoretical work on causal language models. She co-organized key AI workshops at NeurIPS and ICML, and her awards include Princeton's TA of the Year for technical courses. Leadership: ICML Workflow Chair (2019), NeurIPS workshop co-organizer (2019, 2021), peer reviewer for top AI conferences.

Srinivasa G. Narasimhanمشاهده پروفایل

استاد

• Computer Vision
• Computer Graphics
• Computational Imaging
• +۵ مورد دیگر

Srinivasa G. Narasimhan is the U.A. and Helen Whitaker Professor of Robotics at Carnegie Mellon University's Robotics Institute within the School of Computer Science. He directs the Illumination and Imaging Laboratory (ILIM) and leads the Computational Imaging group, focusing on the physics of computer vision and graphics. His research develops novel imaging technologies for applications in robotics, transportation, medical imaging, and environmental sensing. Research interests span computational imaging, light transport modeling, and active perception systems. Key areas include: Physics-based vision for atmospheric and material interactions Novel camera designs and programmable lighting systems Robust perception for autonomous vehicles and medical diagnostics Non-line-of-sight imaging and computational scatterography Publications demonstrate strong emphasis on 3D reconstruction, computational optics, and vision systems for intelligent transportation. Recent works leverage self-supervised learning for dynamic scene understanding and develop novel sensors for medical and automotive applications. Awards and honors include: Best Paper awards at CVPR (2019, 2022), IV (2021), and ICCP (2020) Marr Prize Honorable Mention (ICCV 2013) Multiple demo awards at CVPR/ICCP Current advising includes 5 PhD students and 1 master's student. Major grants include NSF EXPEDITIONS (Computational Photo-Scatterography), DARPA REVEAL, and industry support from Ford, GM, Adobe, and Zillow. Manages multiple labs developing technologies like adaptive headlights, thermal imaging systems, and MHz-rate light steering devices.

Dominik Moritzمشاهده پروفایل

استادیار

• Human-Centered Machine Learning
• Data Science
• Interactive Systems
• +۶ مورد دیگر

Dominik Moritz is an Assistant Professor at the Human-Computer Interaction Institute (HCII) of Carnegie Mellon University and Machine Learning researcher at Apple. He leads the Data Interaction Group and develops systems for interactive data visualization. Ph.D. in Computer Science from University of Washington (2019) B.S. in Computer Science from Hasso Plattner Institute (2013) His research focuses on: Human-Centered Machine Learning Data Visualization Toolkits Interactive Systems Design Accessibility in Visual Analytics Scalable Web-Based Visualization Recent publications address visualization design knowledge formalization (Draco), cross-filtering frameworks (Mosaic), and accessibility evaluation (Chartability). He has received Best Paper Honors at VIS and EuroVis conferences. Professional Collaborations: Co-founder of Vega-Lite visualization grammar Collaborations with Jeff Heer, Bill Howe, Jock MacKinlay Projects with Microsoft Research and Google Research