BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Robotics Institute Carnegie Mellon University - ECPv6.15.12.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.ri.cmu.edu
X-WR-CALDESC:Events for Robotics Institute Carnegie Mellon University
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260911T143000
DTEND;TZID=America/New_York:20260911T153000
DTSTAMP:20260911T203540
CREATED:20260828T164708Z
LAST-MODIFIED:20260911T212228Z
UID:153335-1789137000-1789140600@www.ri.cmu.edu
SUMMARY:Augmenting Bee Colonies with Robotics and AI Technologies for Ecosystem Support
DESCRIPTION:Abstract: Earth’s ecosystems are facing a rapid decline in biodiversity\, with honeybees —keystone pollinators critical to ecosystem stability— being among the most affected. The EU-funded RoboRoyale project addresses this crisis by integrating advanced robotics and AI to augment the beehive\, enabling observation at unprecedented resolutions and scales. Featured on the cover of Science Robotics and receiving the 6th Edge of Government Award at the World Government Summit in 2024 our system tracks the Queen’s behaviors\, colony efficiency\, comb states\, and long-term foraging activities\, while advancing micro-robotic intervention capabilities to support hive health. In this talk\, I will discuss the challenges of developing this system\, share key findings regarding complex social interactions\, and explore the future potential of bio-hybrid research. \nBio: Erol Şahin is a Professor of Computer Engineering at Middle East Technical University (METU) and the founding Director of the Center for Robotics and AI (ROMER). Established with over 5 million Euros in funding\, ROMER spans 25\,000 square feet of state-of-the-art facilities\, including prototyping workshops\, specialized research arenas\, and advanced robotic platforms. Dr. Şahin earned his PhD in Cognitive and Neural Systems from Boston University\, following a BSc in Electrical and Electronics Engineering from Bilkent University and an MSc in Computer Engineering from METU. Before assuming his current position\, he worked as postdoctoral researcher at the Université Libre de Bruxelles.   Between 2013 and 2015\, Dr. Sahin spent two years at the Robotics Institute of Carnegie Mellon University during his sabbatical. His research interests include swarm robotics\, robotic learning\, and human-robot interaction—work that has secured more than 2.5 million Euros from the European Union\, TUBITAK\, and industrial partners. Notably\, his contributions to robotic learning were awarded a 53-DOF iCub humanoid platform through the RobotCub project in 2007. Dr. Şahin has edited several journal special issues and books\, currently serves as an Associate Editor for Adaptive Behavior\, and is a member of the Editorial Board for the Swarm Intelligence journal.
URL:https://www.ri.cmu.edu/event/augmenting-bee-colonies-with-robotics-and-ai-technologies-for-ecosystem-support/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/08/erol-sahin.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260904T143000
DTEND;TZID=America/New_York:20260904T153000
DTSTAMP:20260911T203540
CREATED:20260828T164202Z
LAST-MODIFIED:20260910T180458Z
UID:153332-1788532200-1788535800@www.ri.cmu.edu
SUMMARY:CANCELED - Trust\, Sensing\, and Learning for Provable Multi-Robot Performance
DESCRIPTION:Seminar Canceled \nThis seminar has been canceled and may be rescheduled for a future date. Please check back for updates. ×Abstract: Multi-robot systems are physically embodied networks — they sense\, move\, and communicate through the physical world. The bar for safe decision-making rises as these systems enter safety-critical\, real-world settings where they must perform well under uncertainty. Our work shows that physicality is a resource against the two kinds of uncertainty they face: intentional (or adversarial)\, where data is manipulated by malicious agents\, and natural\, where aspects of the environment are simply unknown. Most of this talk concerns intentional uncertainty. Here\, one way to exploit physicality is by using communication as a sensor. Because the signals robots exchange are difficult to forge\, they carry evidence that can be cross-validated to yield a quantifiable likelihood that an agent’s data is trustworthy. This is the foundation of cy-trust\, in which stochastic observations of trust model an agent’s trustworthiness probabilistically from physical rather than cryptographic evidence. Each neighbor’s contribution is then weighted by its trust value. Under this framework\, we show that consensus\, distributed optimization\, and other core coordination tasks admit almost-sure convergence with bounded deviation from their nominal performance\, even when malicious agents exceed half of a node’s connectivity\, past the classical Byzantine bound. We support this finding with both theory and hardware experiments under adversarial attack. Against natural uncertainty\, we show that real-time sensing can be folded into rollout-based reinforcement learning\, where the same machinery reweights futures rather than neighbors. We apply this idea to routing a fleet of robots to stochastically appearing demand and\, with Project CETI\, to the first autonomous robotic rendezvous with sperm whales at sea. Finally\, we preview some of our future work combining trust with long-horizon sequential decision-making\, targeting planning that stays provably resilient when the data informing the plan may itself be corrupted. \nBio: Stephanie Gil is the John L. Loeb Associate Professor of Engineering and Applied Sciences at Harvard University and an Associate Faculty member of the Kempner Institute. Her research focuses on trust and coordination in multi-robot systems\, at the intersection of robotics\, communication\, and learning. Her contributions have been recognized through the DARPA Young Faculty Award (2024)\, the Office of Naval Research Young Investigator Award (2021)\, and the National Science Foundation CAREER Award (2019). She was named a 2020 Sloan Research Fellow for her work at the intersection of robotics and communication. She earned her Ph.D. at CSAIL at MIT\, specializing in multi-robot coordination and control\, and her B.S. at Cornell University.
URL:https://www.ri.cmu.edu/event/trust-sensing-and-learning-for-provable-multi-robot-performance/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/08/Stephanie-Gil_SQUARW.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260831T153000
DTEND;TZID=America/New_York:20260831T163000
DTSTAMP:20260911T203540
CREATED:20260825T175254Z
LAST-MODIFIED:20260825T175617Z
UID:153282-1788190200-1788193800@www.ri.cmu.edu
SUMMARY:My Bitter Lesson with Computer Graphics
DESCRIPTION:Abstract:  In his essay “The Bitter Lesson\,” Richard Sutton argued that general methods leveraging computation ultimately outperform hand-crafted ones. In this talk\, I share my own version of this lesson\, learned the hard way over a decade in computer graphics. Where does the bitter lesson apply to graphics\, and where does it not? I argue that the answer depends on whether a problem genuinely requires 3D\, physics\, and control\, or if it simply produces 2D pixels. I will also share a few advices for graduate students starting their research today\, showing which directions will compound in value over a decade\, and which will be quietly subsumed by the next scale-up. \nBio:  Giljoo Nam is a research scientist at Meta focused on Physical AI\, building systems that understand the structure and behavior of the 3D physical world. His research bridges computer vision and graphics\, with focus areas including generative AI\, 3D reconstruction\, motion tracking\, inverse rendering\, computational imaging\, and human modeling. He earned his Ph.D. in Computer Science from KAIST in 2019.. \nHomepage:   https://giljoonam.github.io/ \n  \nSponsor: \nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/my-bitter-lesson-with-computer-graphics/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/08/8-31-26.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260810T153000
DTEND;TZID=America/New_York:20260810T163000
DTSTAMP:20260911T203540
CREATED:20260805T190409Z
LAST-MODIFIED:20260805T190409Z
UID:153064-1786375800-1786379400@www.ri.cmu.edu
SUMMARY:Using Sound to Steer Light and Light to Measure Sound
DESCRIPTION:Abstract:   Light and sound are traditionally treated as distinct physical phenomena\, yet their interaction provides a powerful mechanism for manipulating and sensing information across imaging\, communication\, and measurement. This talk explores computational acousto-optic systems that co-design acoustics\, optics\, and signal processing to enable programmable control of light and high-speed optical sensing without mechanical motion. \nFirst\, an acousto-optic structured-light system is presented in which ultrasound generates rapidly varying refractive-index patterns that steer laser beams at megahertz rates. Combined with event-based vision\, this approach projects up to two million structured-light planes per second and enables 3D scanning at up to 1\,000 frames per second. \nNext\, the same acousto-optic principle is applied to underwater optical backscatter communication by dynamically steering retroreflected light toward or away from a receiver using ultrasound. This enables low-power underwater devices to achieve megabit-per-second data transmission without mechanically actuated optics. \nFinally\, the talk investigates the complementary direction of using light to measure sound. By combining a continuous-wave laser\, a high-speed photodetector\, and commodity software-defined radios\, phase-based depth measurements are performed at megahertz rates\, recovering microscopic surface vibrations and acoustic signals from remote objects. \nTogether\, these systems demonstrate that acoustic waves can serve as programmable optical elements while optical measurements provide sensitive probes of acoustic phenomena. By tightly integrating acoustics\, optics\, computational imaging\, and signal processing\, this work establishes a unified framework for building fast\, programmable sensing and communication systems that operate beyond the capabilities of conventional mechanically actuated approaches. \nBio:  Dhawal Sirikonda is a PhD candidate at Dartmouth College working with Prof. Adithya Pediredla in the Rendering and Imaging Science Lab (RISc). He builds next-generation ultra-fast LiDAR sensors and novel imaging systems for high-speed perception and communication applications. His research focuses on designing computational imaging systems by leveraging diverse sensor modalities\, including event cameras\, RGB-D sensors\, and emerging hybrid sensing architectures. His current work explores novel acousto-optic imaging systems for fast scanning and communication applications. He is particularly interested in combining machine learning and physics-based computational methods to develop robust real-world sensing systems. Prior to his PhD\, he completed his Master’s degree working with Prof. P. J. Narayanan at the intersection of 3D Vision and Real-Time Graphics. \nHomepage:   https://dhawal.xyz \nSponsor:\nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/using-sound-to-steer-light-and-light-to-measure-sound/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/08/8-10-26.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260720T153000
DTEND;TZID=America/New_York:20260720T163000
DTSTAMP:20260911T203540
CREATED:20260714T141829Z
LAST-MODIFIED:20260720T165726Z
UID:151792-1784561400-1784565000@www.ri.cmu.edu
SUMMARY:Cutting the Skip: Training Residual-Free Transformers
DESCRIPTION:Abstract:   Transformers are ubiquitous. They influence nearly every aspect of modern AI. However\, the mechanics of their training remain poorly understood. This poses a problem for the field due to the immense amounts of data\, computational power\, and energy being invested in the training of these networks. I highlight a recent intriguing empirical result from our group. Specifically\, although self-attention catastrophically fails to train without a skip connection under standard conditions\, deep transformers can in fact be trained successfully without them. In this talk\, I explore what makes this possible and what it reveals about the fundamental training dynamics of modern transformers. I also speculate on why truly deep networks may be important for improving generalization and efficiency. \n \nBio:  Simon Lucey Ph.D. is the Director of the Australian Institute for Machine Learning (AIML) and a professor in the School of Computer Science\, at Adelaide University. He is also Director of the CommBank Foundational AI Research Centre. Prior to this he was an associate research professor at Carnegie Mellon University’s Robotics Institute (RI) in Pittsburgh USA; where he spent over 10 years as an academic. He was also Principal Research Scientist at the autonomous vehicle company Argo AI from 2017-2022. He has received various career awards\, notably the AmCham AI Scientist of the year in 2024. He was also a member of the Australian Government’s AI Expert Group\, and their National Robotics Strategy committee. Simon’s research interests span AI\, machine learning\, computer vision and robotics. \nSponsor:\nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/cutting-the-skip-training-residual-free-transformers/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/07/7-20-26-4.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260513T153000
DTEND;TZID=America/New_York:20260513T163000
DTSTAMP:20260911T203540
CREATED:20260429T191158Z
LAST-MODIFIED:20260429T191629Z
UID:151146-1778686200-1778689800@www.ri.cmu.edu
SUMMARY:Quanta Perception as Probabilistic Events
DESCRIPTION:Abstract:  Autonomous systems ultimately rely on extracting information from light\, yet remain brittle in extreme environments\, from nighttime navigation to high-speed robotics. This limitation stems from a classical imaging abstraction: conventional sensors integrate photon flux over fixed exposure windows\, imposing trade-offs between sensitivity\, dynamic range\, and temporal resolution that degrade perception when photons are scarce or dynamics are rapid. Emerging quanta (single-photon) image sensors overcome these limits by detecting individual photons\, but they generate photon streams that exceed the compute and latency budgets of real-time systems by orders of magnitude. \n\nHere we introduce probabilistic events\, a computational primitive for real-time quanta perception at the limit of individual photons. By computing the posterior distribution over the time since the last abrupt intensity change\, we represent photon streams as recursively computed belief states. Rather than the binary\, fixed-threshold triggers of event cameras\, this recursive Bayesian formulation yields three simultaneous\, low-latency signals: motion-adaptive scene flux\, high-fidelity activity maps\, and an entropy measure quantifying perceptual uncertainty. This representation enables perception in extreme conditions\, including detecting and estimating the pose of a running person at ~0.05 lux illumination—without retraining standard vision models. Our approach sustains input throughputs exceeding 50\,000 quanta frames per second on commodity GPU hardware—four to five orders of magnitude faster than state-of-the-art quanta reconstruction baselines—yielding kilohertz-scale outputs even for megapixel arrays. By replacing frame reconstruction with direct probabilistic inference over photon streams\, this work enables real-time perception at the photon limit and bridges photon-counting quanta sensing with practical robotic vision.\n \nBio:   Varun Sundar is a graduate student at the University of Wisconsin–Madison\, pursuing a Ph.D. in computer science. At UW–Madison\, he is advised by Prof. Mohit Gupta\, where he focuses on single-photon imaging techniques. His work has been published at venues such as CVPR\, ICCV\, and SIGGRAPH\, and has included live demos at ICCP 2023\, CVPR 2024 and SIGGRAPH 2024 (which won the best-in-show award in the Emerging Technologies track). In 2026\, he was awarded the Ivanisevic Award at UW–Madison\, which recognizes outstanding computer science dissertators. He previously received a bachelor’s degree in electrical engineering from the Indian Institute of Technology\, Madras in 2020. \nHomepage:   https://varun19299.github.io/ \nSponsor:\nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/quanta-perception-as-probabilistic-events/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/04/5-13-26.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260427T153000
DTEND;TZID=America/New_York:20260427T163000
DTSTAMP:20260911T203540
CREATED:20260421T163228Z
LAST-MODIFIED:20260421T163228Z
UID:151102-1777303800-1777307400@www.ri.cmu.edu
SUMMARY:Learning Through Fitting: Advancing Non-Pixel Representations for Visual Inference
DESCRIPTION:Abstract:  Gridded pixel and voxel representations form the backbone of visual computing\, but they struggle to scale efficiently to large\, high-dimensional data\, such as volumetric medical scans and complex scientific simulations. Consequently\, continuous\, nongridded models such as implicit neural representations (INRs) and Gaussian splatting have gained significant research traction over the past five years. However\, their use has largely been confined to signal reconstruction rather than acting as foundational data types for downstream analysis. In this talk\, I will present our recent work on elevating continuous models beyond mere signal representation. First\, I will discuss how injecting learned priors into INRs via strategic parameter initialization enables powerful new capabilities\, including rapid\, amortized fitting to novel signals and even semantic segmentation. Second\, I will briefly outline our recent efforts in performing visual recognition tasks directly on 2D Gaussian image representations. Finally\, I will highlight interesting future directions in this “learning through fitting” paradigm of visual computing. \nBio:  Guha Balakrishnan is an Assistant Professor in the Electrical and Computer Engineering Department at Rice University. His research group tackles a diverse range of problems across computer vision and imaging\, with a primary focus on developing efficient neural representations for complex visual signals and advancing responsible AI through uncertainty estimation and interpretability techniques. He frequently grounds these methods in real-world applications by collaborating with domain experts in scientific disciplines such as medicine and the geosciences. His scientific contributions have been recognized with several honors\, including the NSF CAREER Award and the MICCAI Best Paper Award. Before joining Rice\, he completed his Ph.D. at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL)\, and earned his undergraduate degrees in Computer Science and Computer Engineering from the University of Michigan\, Ann Arbor. \nHomepage:  www.guhabalakrishnan.com \nSponsor:\nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/learning-through-fitting-advancing-non-pixel-representations-for-visual-inference/
LOCATION:Newell-Simon Hall 4305
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/04/4-27-26-Balakrishnan.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260420T130000
DTEND;TZID=America/New_York:20260420T140000
DTSTAMP:20260911T203540
CREATED:20260414T163047Z
LAST-MODIFIED:20260414T163047Z
UID:151005-1776690000-1776693600@www.ri.cmu.edu
SUMMARY:The AI That Sees Cancer Coming
DESCRIPTION:Abstract: Cancer rarely announces itself. It hints. It hides. Radiologists often describe their work as looking for needles in a haystack. By the time we are certain\, it is often too late. Artificial intelligence (AI) offers a fundamentally new approach to this problem. By learning complex statistical patterns from large collections of medical images and clinical outcomes\, AI can detect subtle signals that can appear long before disease becomes visible to the human eye. This creates an unprecedented opportunity to assist radiologists and find cancer earlier\, potentially saving thousands of lives. As a case study\, I will focus on the early detection of pancreatic cancer\, where the cost of delay is steep and the window for effective treatment is narrow. We have developed an AI system that analyzes CT scans to detect and localize early cancer. This system achieved 94% sensitivity at 99% specificity\, which outperforms 34% sensitivity at 95% specificity for expert radiologists. Importantly\, the system was able to detect cancer about 13.6 months earlier than radiologists. I will then introduce a battery of new AI methodology developed by our team that enabled this system\, including vision-language models\, synthetic data generation\, novel AI architectures\, and active learning. These ideas extend beyond the pancreas: our AI system has already outperformed radiologists in detecting eight different cancer types. This success was also enabled by the collaboration with a team of 50 radiologists and datasets from 445 hospitals across 19 countries. I will close with a broader vision: AI systems that learn longitudinal representations of human biology by integrating imaging\, clinical data\, and causal modeling. Such systems can detect and forecast multiple cancers long before symptoms emerge. Because in cancer care\, time is life. \nSpeaker Bio: Zongwei Zhou is an assistant research professor in the Johns Hopkins University’s Department of Computer Science with a joint appointment in Oncology through the School of Medicine’s Sidney Kimmel Comprehensive Cancer Center. As a member of the Data Science and AI Institute and the Center for Imaging Science\, his research focuses on medical computer vision\, language\, and graphics for early cancer detection and diagnosis. He is best known for developing UNet++\, a widely adopted segmentation architecture cited about 18\,000 times since its publication in 2019. He currently serves as PI on an NIH–NIBIB R01 grant ($2.8M\, top 1.0 percentile). His work has earned multiple honors\, including the AMIA Doctoral Dissertation Award 2022\, Elsevier–MedIA Best Paper Award\, and MICCAI Young Scientist Award. Dr. Zhou also received the President’s Award for Innovation\, the highest honor for graduate students at Arizona State University\, and has been recognized among the Top 2% of Scientists Worldwide every year since 2022. \n  \nSponsor: The Carnegie Mellon Graphics Seminar is generously supported by Roblox.
URL:https://www.ri.cmu.edu/event/the-ai-that-sees-cancer-coming/
LOCATION:Graphic Lounge @ Smith Hall 2nd Floor (236)
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/04/4-20-26-ZongweiZhou.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260417T143000
DTEND;TZID=America/New_York:20260417T153000
DTSTAMP:20260911T203540
CREATED:20260203T201707Z
LAST-MODIFIED:20260420T130550Z
UID:150312-1776436200-1776439800@www.ri.cmu.edu
SUMMARY:The Role of Rationality in Modern Robotics
DESCRIPTION:Abstract: The classical approach to AI designed systems that were rational at run-time: they had explicit representations of beliefs\, goals\, and plans and ran inference algorithms\, online\, to select actions. The rational approach was criticized (by the behaviorists) and modified (by the probabilists) but persisted in some form. More recently\, relatively unstructured data-driven end-to-end approaches have demonstrated great success in a wide variety of domains\, and began to seem like a plausible route to general-purpose intelligent robots. However\, most recently\, we have begun to see the limits of pure behavior learning and many practitioners are re-integrating forms of search and explicit reasoning into their approaches. \nI will revisit the rational-agent approach to the design of intelligent robots\, from the perspectives of engineering effort\, computational efficiency\, cognitive modeling and understandability. I will present some current research focused on understanding the roles of learning in runtime-rational agents with the ultimate aim of constructing general-purpose human-level intelligent robots as well as understanding human intelligence. \nBio: Leslie is a Professor at MIT. She has an undergraduate degree in Philosophy and a PhD in Computer Science from Stanford\, and was previously on the faculty at Brown University. She was the founding editor-in-chief of the Journal of Machine Learning Research. Her research agenda is to make intelligent robots using methods including learning\, planning\, and reasoning about uncertainty. She was doing agentic AI way before it was cool.
URL:https://www.ri.cmu.edu/event/the-role-of-rationality-in-modern-robotics/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/02/Kaelbling_Leslie-preferred-as-of-2023-230x230-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260413T153000
DTEND;TZID=America/New_York:20260413T163000
DTSTAMP:20260911T203540
CREATED:20260331T235136Z
LAST-MODIFIED:20260331T235318Z
UID:150830-1776094200-1776097800@www.ri.cmu.edu
SUMMARY:Generative Re-Photography with Video Models
DESCRIPTION:Abstract: I will introduce “generative re-photography” methods that use new generative video models to get more out of your photos—even the blurry ones. First\, I will present a method for converting motion-blurred images to video. This method can even predict the “past” and “future” (right before and after the capture) of a motion-blurred image. I will then show how this method can bring “historical scenes to life” such as photos of soldiers landing on north side of France during the Normandy invasion of 1944 or a boxing match between Mohammed Ali and Jurgen Blin in 1971. Then\, I will present a robust post-capture refocusing method that converts a single defocus-blurred image into a focal stack spanning multiple focus distances. Our work overturns the conventional wisdom of photography\, suggesting these “corrupted images” can actually reveal more about the world than the “perfect” images which have been the holy grail of image processing. Additionally\, our findings suggest that video models implicitly understand how camera capture settings affect image appearance\, and I will discuss how this exciting capability could inspire new directions for computational photography. \nBio: Sai Tedla is a PhD student at York University\, Toronto\, supervised by Michael Brown. He currently works on the intersection of computational photography and generative models. He is a visiting student at the University of Toronto supervised by David Lindell and Kyros Kutulakos\, and will soon join the university as a Schmidt AI Postdoctoral Fellow. Additionally\, Sai is a current intern at Sony AI Japan and has previously interned at Samsung AI Center Toronto and Adobe NextCam. \nHomepage:  https://sites.google.com/view/tedlasai \n  \nSponsor \nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/generative-re-photography-with-video-models/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/03/4-13-26-rotated.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260413T130000
DTEND;TZID=America/New_York:20260413T140000
DTSTAMP:20260911T203540
CREATED:20260407T215147Z
LAST-MODIFIED:20260407T215147Z
UID:150906-1776085200-1776088800@www.ri.cmu.edu
SUMMARY:Title: Geometric Perspectives in AI
DESCRIPTION:Abstract: Geometry can make AI approaches more accurate\, efficient and controllable. In this talk\, we cover three contributions that demonstrate this. The first is DeltaConv\, a building block for CNNs on curved surfaces. DeltaConv works directly on the surface\, rather than in 3D space. That means the networks can be more efficient and robust to deformations of the shape\, but it complicates learning directional information\, because there is no global coordinate system. We solve this by learning anisotropic operators as combinations of coordinate-independent operators. The second contribution concerns empirical uncertainty for appearance capture. We show how to quantify this uncertainty and how uncertainty can be used to improve data capture and use the strengths of generative AI in a targeted way. The third contribution deals with enforcing constraints in generative methods\, specifically in mesh reconstruction (TetWeave) and stylized vector-image generation. Finally\, we will cover how these contributions can improve generative AI approaches of the future. \nSpeaker Bio: Ruben Wiersma is a postdoctoral researcher in the Interactive Geometry Lab at ETH Zurich and will start as a research scientist at Adobe Research in Paris in June 2026. He obtained his doctorate cum laude at the TU Delft in 2024 and was a research intern at Adobe in 2023. His research in geometry processing and computer graphics has focused on using geometric approaches for machine learning\, object capture\, and shape analysis. In addition\, he has worked on applying techniques from computer graphics to painting analysis in collaboration with art historians and conservators. Outside of research\, Ruben enjoys making music\, creating short films and tinkering with Blender\, and going outdoors. \n 
URL:https://www.ri.cmu.edu/event/title-geometric-perspectives-in-ai/
LOCATION:Graphic Lounge @ Smith Hall 2nd Floor (236)
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/04/4-13-26-Ruben_headshot.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260406T130000
DTEND;TZID=America/New_York:20260406T140000
DTSTAMP:20260911T203540
CREATED:20260402T121047Z
LAST-MODIFIED:20260402T121047Z
UID:150868-1775480400-1775484000@www.ri.cmu.edu
SUMMARY:Video-informed Pose Spaces for Auto-Rigged Meshes
DESCRIPTION:Abstract: Kinematic rigs make 3D meshes editable\, but they do not specify which poses are plausible for a given asset. As a result\, naively manipulating rig parameters can easily produce unrealistic deformations. Artists often address this by manually authoring pose spaces\, but doing so requires substantial effort and expertise. \nIn this talk\, I will first give a brief overview of my research on neural and numerical methods for physical simulation. I will then present Video-informed Pose Spaces (ViPS) for Auto-Rigged Meshes\, a feed-forward generative model that automatically discovers plausible pose spaces for auto-rigged 3D meshes by distilling motion priors from pretrained video diffusion models. Without relying on scarce\, artist-authored 4D datasets\, ViPS supports diverse pose generation\, constrained editing\, smooth interpolation\, and pose-guided video generation. Our work shows that video priors can be turned into practical and controllable tools for articulated 3D content\, with strong generalization to unseen species and skeletal structures. \nSpeaker Bio: Honglin Chen is a fifth-year PhD student in Computer Science at Columbia University\, advised by Prof. Changxi Zheng. Her research lies at the intersection of computer graphics/vision\, physical simulation\, and machine learning. She develops methods for simulating the 3D physical world\, with the goal of making animation and creative tools more realistic\, reliable\, and accessible. She is a recipient of the Roblox Graduate Fellowship and a 2024 WiGRAPH Rising Star in Computer Graphics. \n  \nSponsor: The Carnegie Mellon Graphics Seminar is generously supported by Roblox.
URL:https://www.ri.cmu.edu/event/video-informed-pose-spaces-for-auto-rigged-meshes/
LOCATION:Graphic Lounge @ Smith Hall 2nd Floor (236)
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/04/4-6-26-head_photo_HonglinChen.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260403T143000
DTEND;TZID=America/New_York:20260403T153000
DTSTAMP:20260911T203540
CREATED:20260203T201625Z
LAST-MODIFIED:20260330T183521Z
UID:150310-1775226600-1775230200@www.ri.cmu.edu
SUMMARY:Physical Intelligence for Physical Care: Towards Stakeholder-Informed Caregiving Robots in the Real World
DESCRIPTION:Abstract: How can we build robots that meaningfully assist people with mobility limitations in their daily lives? To support complex caregiving tasks such as robot-assisted feeding\, bathing\, transferring\, and meal preparation\, robots must physically interact with people and objects in dynamic\, unstructured environments while maintaining safety. In this talk\, I will present an overview of projects from the EmPRISE Lab that showcase fundamental advances in physical robot caregiving. I will highlight how we design stakeholder-informed systems with personalized contact-rich control policies and user functionality- and behavior-aware physical robot assistance. I will also share insights from deploying these systems with real users in real-world settings. Together\, these efforts move us closer to building caregiving robots that are not only technically capable\, but are also safe\, deployable\, and responsive to the real needs of people in care settings. \nBio: Tapomayukh “Tapo” Bhattacharjee is an Assistant Professor in the Department of Computer Science at Cornell University where he directs the EmPRISE Lab (https://emprise.cs.cornell.edu/). He completed his Ph.D. in Robotics from Georgia Institute of Technology and was an NIH Ruth L. Kirschstein NRSA postdoctoral research associate in Computer Science & Engineering at the University of Washington. His primary research interests are in the area of physical robot caregiving and physical human-robot interaction. He is the recipient of TRI Young Faculty Researcher Award’24\, NSF CAREER Award’23\, AFCEA 40 under 40 Award’22\, and his work has won Best Paper Award at RSS’25\, Best Paper and Student Paper Award Finalist and Best HRI Paper Award Finalist at ICRA’25\, Best Systems Paper Award Finalist at HRI’24\, Best Demo Award at HRI’24\, Best RoboCup Paper Award at IROS’22\, Best Paper Award Finalist and ABB Best Student Paper Award Finalist at IROS’22\, Best Technical Advances Paper Award at HRI’19\, and Best Demonstration Award at NeurIPS’18. His work has also been featured in many media outlets including the BBC\, Reuters\, New York Times\, IEEE Spectrum\, and GeekWire and his robot-assisted feeding work was selected to be one of the best interactive designs of 2019 by Fast Company.
URL:https://www.ri.cmu.edu/event/physical-intelligence-for-physical-care-towards-stakeholder-informed-caregiving-robots-in-the-real-world/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/02/80JwFIIw.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260330T130000
DTEND;TZID=America/New_York:20260330T140000
DTSTAMP:20260911T203540
CREATED:20260326T124622Z
LAST-MODIFIED:20260326T145451Z
UID:150751-1774875600-1774879200@www.ri.cmu.edu
SUMMARY:Closest Point Geometry Processing
DESCRIPTION:Abstract: Objects can be represented in various forms\, including meshes\, point clouds\, parameterizations\, and neural implicits. Traditionally\, many algorithms are limited to a single specific representation. We focus on geometry processing with any representation supporting closest-point queries\, making these methods universally applicable. Furthermore\, objects can be manifold or nonmanifold\, open or closed\, orientable or not\, and of any codimension or even mixed codimension. \nOur work solves PDEs common in geometry processing using the closest point method (CPM). We develop fundamental extensions of CPM to enable its use for the first time with many applications in geometry processing. The major impediment was the inability to impose interior boundary conditions (IBCs) with CPM. We develop a general framework for IBC enforcement that also only requires closest point queries. We then deviate from the common grid-based CPM and further develop a discretization-free CPM by extending a Monte Carlo method to surface PDEs. This enables CPM to enjoy common benefits of Monte Carlo methods\, e.g.\, localized solutions\, which are useful for view-dependent applications. Finally\, interesting open problems in closest point geometry processing are discussed. \nSpeaker Bio: Nathan King is a Research Scientist at Shapr3D\, where he focuses on geometric modelling and physics simulation. His recent PhD at the University of Waterloo developed computational methods involving closest point representations\, with a particular interest in geometry processing and physics-based animation applications. https://nathandking.github.io/ \n  \nSponsor: The Carnegie Mellon Graphics Seminar is generously supported by Roblox.
URL:https://www.ri.cmu.edu/event/closest-point-geometry-processing/
LOCATION:Graphic Lounge @ Smith Hall 2nd Floor (236)
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/03/3-30-26-NathanKing_Headshot.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260323T130000
DTEND;TZID=America/New_York:20260323T140000
DTSTAMP:20260911T203540
CREATED:20260320T163645Z
LAST-MODIFIED:20260320T163947Z
UID:150645-1774270800-1774274400@www.ri.cmu.edu
SUMMARY:Automatic Sampling for Discontinuities in Differentiable Shaders
DESCRIPTION:Abstract: I will talk about a novel method for differentiating integrals of discontinuous functions\, which frequently arise in inverse graphics\, computer vision\, and machine learning\, and are a key bottleneck for gradient-based optimization. Prior approaches either rely on specialized routines to sample discontinuity boundaries of predetermined primitives\, or use reparameterization techniques that suffer from high variance. In contrast\, my method handles general discontinuous functions expressed as shader programs\, without requiring manually specified boundary sampling procedures. \nThis is achieved through a program transformation that converts discontinuous functions into piecewise constant ones\, enabling efficient boundary sampling via a novel segment snapping technique\, and accurate derivatives at discontinuities by comparing values on either side of the boundary. The method supports both explicit boundaries (e.g.\, polygons\, ellipses\, Bézier curves) and implicit ones (e.g.\, neural networks\, noise-based functions\, swept surfaces). I demonstrate that it enables low-variance\, accurate gradient estimation across applications including painterly rendering\, raster image fitting\, constructive solid geometry\, swept surfaces\, mosaicing\, and ray marching. \nProject website: https://yashbelhe.github.io/asd/index.html \nSpeaker Bio: Yash Belhe is an incoming Research Scientist at Reve. He recently completed his PhD in Computer Science at the University of California\, San Diego\, advised by Ravi Ramamoorthi and Tzu-Mao Li. His research focuses on generative modeling\, differentiable rendering\, automatic differentiation systems\, and neural representations for visual data. His work has received a SIGGRAPH Asia Best Paper Award and a SIGGRAPH Asia Best Paper Honorable Mention. More information is available at https://yashbelhe.github.io/.
URL:https://www.ri.cmu.edu/event/automatic-sampling-for-discontinuities-in-differentiable-shaders/
LOCATION:Graphic Lounge @ Smith Hall 2nd Floor (236)
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/03/YashBelhe-3-23-26.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260320T143000
DTEND;TZID=America/New_York:20260320T153000
DTSTAMP:20260911T203540
CREATED:20260203T201254Z
LAST-MODIFIED:20260325T133237Z
UID:150306-1774017000-1774020600@www.ri.cmu.edu
SUMMARY:Formal Methods for Robotics in the Age of Big Data
DESCRIPTION:Abstract: Formal methods – mathematical techniques for describing systems\, capturing requirements\, and providing guarantees – have been used to synthesize robot control from high-level specification\, and to verify robot behavior. Given the recent advances in robot learning and data-driven models\, what role can\, and should\, formal methods play in advancing robotics? In this talk I will give a few examples for what we can do with formal methods\, discuss their promise and challenges\, and describe the synergies I see with data-driven approaches.\n\nBio: Hadas Kress-Gazit is the Geoffrey S.M. Hedrick Sr. Professor at the Sibley School of Mechanical and Aerospace Engineering at Cornell University\, and the Associate Dean for Diversity and Academic Affairs of Cornell Duffield College of Engineering. She received her Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania in 2008 and has been at Cornell since 2009. Her research focuses on formal methods for robotics and automation\, and more specifically on high-level specifications and synthesis for robot control. Her group has explored different types of robotic systems including modular robots\, soft robots\, and swarms\, and how formal methods can be used for human-robot interaction. She received an NSF CAREER award in 2010\, a DARPA Young Faculty Award in 2012\, Cornell Engineering’s Excellence in teaching award in 2013 and 2019\, and excellence in research award in 2020. She is an IEEE Fellow and has served on DARPA’s Information Science and Technology study group (ISAT)\, as the program chair for Robotics: Science and Systems (RSS) 2018\, the program chair for the International Conference on Robotics and Automation (ICRA) 2022\, and the president of the RSS board (2019-2023)\, among other leadership positions in the robotics community.
URL:https://www.ri.cmu.edu/event/formal-methods-for-robotics-in-the-age-of-big-data/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/02/hadas-kress-gazit.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260316T130000
DTEND;TZID=America/New_York:20260316T140000
DTSTAMP:20260911T203540
CREATED:20260312T174913Z
LAST-MODIFIED:20260313T153457Z
UID:150603-1773666000-1773669600@www.ri.cmu.edu
SUMMARY:Deriving Monte Carlo estimators by rewriting integral programs
DESCRIPTION:Abstract: Integral equations\, such as the rendering equation or the Walk-on-Spheres integrator\, are the natural language for many problems in graphics and physics. As these integrals are often high-dimensional and recursive\, we typically evaluate them using Monte Carlo integration. The best Monte Carlo estimator\, however\, is scene-dependent and frequently merges many separate optimization strategies together in a complex architecture–there is no “one-size fits all” solution. Furthermore\, navigating this design space–by iteratively implementing and testing different estimators for a problem–is difficult and error-prone\, requiring a combination of mathematical derivations and low-level numerics programming. \nThis talk presents Martingale\, a new DSL for programming estimators. Martingale is based on three key ideas. First\, the integral that the user wishes to estimate is represented explicitly in code. Second\, integral transformations (i.e.\, meaning-preserving rewrites of integrals) are reified as compositional metaprograms\, which can be abstracted and reused across problems. Third\, even complex estimators can be derived by first rewriting an integral\, and then applying standard importance sampling techniques. Together\, these ideas enable a new method for building correct-by-construction estimators that are easy to inspect and modify\, and allow us to package high-level estimation strategies into reusable library components. \nSpeaker Bio: Kevin Mu is a fourth year graduate student at the University of Washington\, advised by Zachary Tatlock. He studies programming languages for integration and differentiation\, with applications to computer graphics and scientific computing. \n  \nSponsor: The Carnegie Mellon Graphics Seminar is generously supported by Roblox.
URL:https://www.ri.cmu.edu/event/deriving-monte-carlo-estimators-by-rewriting-integral-programs/
LOCATION:Graphic Lounge @ Smith Hall 2nd Floor (236)
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260313T143000
DTEND;TZID=America/New_York:20260313T153000
DTSTAMP:20260911T203540
CREATED:20260203T201044Z
LAST-MODIFIED:20260314T123429Z
UID:150304-1773412200-1773415800@www.ri.cmu.edu
SUMMARY:Generative Control\, Action Chunking\, and Moravec’s Paradox
DESCRIPTION:Abstract: Moravec’s Paradox observes that AI systems have struggled far more with learning physical actions than symbolic reasoning. Yet just recently\, there has been a tremendous increase in the capability of AI-driven robotic systems\, reminiscent  of the early improvements in language modeling capabilities a few years ago.  In this talk\, we provide mathematical evidence that learning in continuous-control settings\, like robotics\, can be exponentially more challenging than in discrete settings\, like language\, unless certain key algorithmic design choices are made – effectively\, mathematical evidence for Moravec’s claim. We then show that two of the key innovations in modern robot learning – action chunking\, and the  use of generative models\, such as diffusion models\, to parametrize robot actions – can be interpreted as directly mitigating the mechanisms underlying this difficulty. Our perspective runs contrary to many popular justifications for the two methods\, such as capturing multi-modality present in mixed-quality training data.  Finally\, if time permits\, we will describe a new family of interventions\, at the level of deep learning optimization\, that provide yet another lever for addressing  the same challenges. \nBio: Max Simchowitz is an assistant professor at the Machine Learning Department at Carnegie Mellon University with a courtesy appointment in the Robotics Institute. His work studies theoretical foundations and new methodologies for machine learning problems with an interactive\, sequential\, or dynamical component\, currently focusing on reinforcement learning and applications to robotics. His past work has ranged broadly across control\, theoretical reinforcement learning\, optimization and algorithmic fairness. He received his PhD from University of California\, Berkeley in 2021 under Ben Recht and Michael I. Jordan\, and completed his postdoctoral research under Russ Tedrake in the Robot Locomotion Group at MIT. His work has been recognized with an ICML 2018 Best Paper Award\, ICML 2022 Outstanding Paper Award\, and RSS 2023 and ICRA 2024 Best Paper Finalist designations.
URL:https://www.ri.cmu.edu/event/generative-control-action-chunking-and-moravecs-paradox/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2026/02/pic-scaled.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260309T153000
DTEND;TZID=America/New_York:20260309T163000
DTSTAMP:20260911T203540
CREATED:20260303T211052Z
LAST-MODIFIED:20260303T211052Z
UID:150524-1773070200-1773073800@www.ri.cmu.edu
SUMMARY:Nano-optics for smart sensing and display
DESCRIPTION:Abstract: Nano-optical devices provide a new way to control light at the subwavelength scale\, enabling optical functionalities beyond conventional optics. By engineering the nanostructures\, we can tailor the optical response as a function of space\, polarization\, wavelength\, and angle of incidence — effectively turning the optical front end into a controllable\, programmable physical layer. This creates an interesting interplay between optical design and computation: on one hand\, nanooptics can be incorporated and co-designed within the computational pipeline\, enabling new approaches to smart sensing\, imaging\, and display; on the other hand\, computational methods can be used to discover and optimize new classes of optical instruments that go beyond intuitive\, hand designed architectures. \nIn this talk\, I will first introduce the basics of nanooptics\, highlighting key opportunities and current limitations. I will then present several concrete examples: nanooptics for depth sensing\, polarization imaging\, and nanooptics-based new AR display architectures. I will conclude with a view of what it would take to make these systems robust and scalable\, and where collaboration with the computer vision community can have the most impact. \nBio: Zhujun Shi is an Assistant Professor of Physics and Astronomy at the University of Pittsburgh. Her group explores new frontiers in light manipulation using nanophotonics. Prior to joining Pitt\, she was a research scientist at Meta Reality Labs. She received her B.S. in Physics from Tsinghua University in 2015 and her Ph.D. in Physics from Harvard University in 2020. \nHomepage:  https://www.shiphotonics.org/ \nSponsor \nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/nano-optics-for-smart-sensing-and-display/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/03/shi-6.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260220T143000
DTEND;TZID=America/New_York:20260220T153000
DTSTAMP:20260911T203540
CREATED:20260203T200805Z
LAST-MODIFIED:20260225T171508Z
UID:150300-1771597800-1771601400@www.ri.cmu.edu
SUMMARY:Robots as Models for Biology and Biology and Materials for Robots
DESCRIPTION:Abstract: In the last century\, it was common to envision robots as shining metal structures with rigid and halting motion. This imagery is in contrast to the fluid and organic motion of living organisms that inhabit our natural world. The adaptability\, complex control\, and advanced learning capabilities observed in animals are not yet fully understood\, and therefore have not been fully captured by current robotic systems. Furthermore\, many of the mechanical properties and control capabilities seen in animals have yet to be achieved in robotic platforms. In this talk\, I will share an interdisciplinary research vision for robots as models for neuroscience and biology as materials for robots. \nBio: Vickie Webster-Wood is an Associate Professor in the Department of Mechanical Engineering at Carnegie Mellon University with courtesy appointments in the Department of Biomedical Engineering\, the McGowan Institute of Regenerative Medicine\, and the Robotics Institute. She is the director of the C.M.U. Biohybrid and Organic Robotics Group and has a long-term research goal to develop completely organic\, biodegradable\, autonomous robots. She received the NSF CAREER Award in 2021\, leads the SSymBioTIC MURI on Integrated Biohybrid Actuators\, and is a co-Principal Investigator of the NSF C3NS NeuroNex Network\, along with numerous other grants and awards.
URL:https://www.ri.cmu.edu/event/robots-as-models-for-biology-and-biology-and-materials-for-robots/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/png:https://www.ri.cmu.edu/app/uploads/2026/02/vwebster.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260213T143000
DTEND;TZID=America/New_York:20260213T153000
DTSTAMP:20260911T203540
CREATED:20260203T200507Z
LAST-MODIFIED:20260214T040347Z
UID:150298-1770993000-1770996600@www.ri.cmu.edu
SUMMARY:Robot Learning\, With Inspiration From Child Development
DESCRIPTION:Abstract: For intelligent robots to become ubiquitous\, we need to “solve” locomotion\, navigation and manipulation at sufficient reliability in widely varying environments. In locomotion\, we now have demonstrations of humanoid walking in a variety of challenging environments.  In navigation\, we pursued the task of “Go to Any Thing” – a robot\, on entering  a newly rented Airbnb\, should be able to find objects such as TV sets or potted plants. The biggest challenges in robotics today lie in manipulation\, particularly in dexterous manipulation with multi-fingered hands. Learning approaches have been responsible for recent advances\, but they are held up by the lack of “big data” at the scale available in language and vision. I argue that this shortage can be circumvented by taking inspiration from how humans  acquire motor skills in childhood. For dexterous manipulation\, multimodal perception is key – vision\, touch and proprioception. In my view\, visual imitation should be based on 3D/4D reconstruction – then a physics simulator provides a pre-trained world model. The core technology for reconstruction of human bodies\, hands\, and objects now exists with systems like HMR\, HaMeR and SAM 3D.  Visual imitation\, while essential\, is not sufficient\, as policies need to consider contact forces as well. RL in simulation and sim-to-real have been workhorse technologies for us\, assisted by a few technical innovations. I will sketch promising directions for future work. \nBio: Jitendra Malik is Arthur J. Chick Professor of EECS at UC Berkeley\, and VP and Distinguished Scientist at Amazon. His group has conducted research on many different topics in computer vision\, computer graphics\, machine learning and robotics resulting in concepts such as anisotropic diffusion\, high dynamic range imaging\, normalized cuts\, R-CNN and rapid motor adaptation. His publications have received twelve best paper awards\, including six test of time awards – the Longuet-Higgins Prize for papers published at CVPR (three times) and the Helmholtz Prize for papers published at ICCV (three times). He has mentored more than 80 PhD students and postdoctoral fellows. \nJitendra received the 2016 ACM/AAAI Allen Newell Award\, 2018 IJCAI Award for Research Excellence in AI\, and the 2019 IEEE Computer Society’s Computer Pioneer Award for “leading role in developing Computer Vision into a thriving discipline through pioneering research\, leadership\, and mentorship”. He is a member of the US National Academy of Sciences\, the National Academy of Engineering and Fellow\, American Academy of Arts and Sciences.
URL:https://www.ri.cmu.edu/event/robot-learning-with-inspiration-from-child-development/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/02/malik-scaled.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260202T153000
DTEND;TZID=America/New_York:20260202T163000
DTSTAMP:20260911T203540
CREATED:20260123T150837Z
LAST-MODIFIED:20260123T150837Z
UID:150171-1770046200-1770049800@www.ri.cmu.edu
SUMMARY:From Lab to Reality: Reliable 3D Vision in the Wild
DESCRIPTION:VIRTUAL SEMINAR \nAbstract: While deep learning has revolutionized 3D computer vision\, a significant gap remains between the performance achieved in controlled laboratory settings and that in complex\, uncontrolled real-world environments. This talk addresses the critical challenges of robustness and generalization required to bridge this gap. In this presentation\, I will first discuss our contributions to 3D reconstruction\, including robust multi-view reconstruction\, physically grounded 3D shape generation\, and 3D Gaussian Splatting under sparse-view conditions. Next\, I will cover 3D interaction with a focus on generalizable object pose estimation. I will demonstrate how leveraging different types of reference information can facilitate pose estimation for previously unseen objects in uncontrolled environments. Finally\, I will conclude by outlining future directions toward multi-modal 3D understanding\, unified 3D representations\, and the development of 3D foundation models. \nBio: Chen Zhao is a Postdoctoral Research Fellow at the Computer Vision Lab\, EPFL\, working with Dr. Mathieu Salzmann and Prof. Pascal Fua. Earlier\, he was a PhD candidate at EPFL\, supervised by Dr. Mathieu Salzmann and Prof. Pascal Fua. His research interests lie in 3D computer vision\, with a specific focus on 3D reconstruction\, 3D interaction\, and 3D understanding. \nHomepage:  https://sailor-z.github.io/ \nSponsor:  The VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/from-lab-to-reality-reliable-3d-vision-in-the-wild/
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2026/01/2-2-26-chen.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260202T130000
DTEND;TZID=America/New_York:20260202T140000
DTSTAMP:20260911T203540
CREATED:20260129T183432Z
LAST-MODIFIED:20260129T183432Z
UID:150221-1770037200-1770040800@www.ri.cmu.edu
SUMMARY:Why You Don’t Need Sparsity for Efficient Geometric Computing
DESCRIPTION:Abstract: Sparsity is one of the most commonly relied-upon tools in geometric computing; beyond its immediate evocation of efficient linear algebraic operations\, it also more geometrically applies when culling regions to accelerate spatial queries. However\, I argue that there are a large class of problems for which sparsity imposes undesirable properties on the solution\, and we must instead look towards dense methods. I first present some work on applying this principle to design smooth distance functions for collections of simplices\, which smoothly combines all constituent distances rather than selecting the smallest one. This formulation not only offers better isosurfaces around geometrically disjoint representations like point clouds\, but also provably underestimates the exact distance to the original geometry. Acceleration methods for such “kernel sums” requires adaptive methods that are ill-suited for acceleration on the GPU\, so I will then discuss a stochastic reformulation of the Barnes-Hut approximation method commonly used for such problems\, which provides superior GPU performance at comparable accuracy to its deterministic counterpart. Finally\, I will discuss future directions to broaden the applicability and ease of use of dense adaptive methods. \nSpeaker Bio: Abhishek Madan is a final-year PhD student at the University of Toronto\, supervised by David Levin. His research concerns methods for maximizing the use of non-mesh geometric representations for downstream applications\, as well as numerical techniques to support such methods on massively parallel hardware. He has completed research internships at Adobe and NVIDIA. Previously\, he did his undergraduate degree in Software Engineering at the University of Waterloo. \nSponsor: The Carnegie Mellon Graphics Seminar is generously supported by Roblox. \n 
URL:https://www.ri.cmu.edu/event/why-you-dont-need-sparsity-for-efficient-geometric-computing/
LOCATION:Smith Hall 236\, PA
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251215T153000
DTEND;TZID=America/New_York:20251215T163000
DTSTAMP:20260911T203540
CREATED:20251203T162327Z
LAST-MODIFIED:20251210T163815Z
UID:149661-1765812600-1765816200@www.ri.cmu.edu
SUMMARY:Should we skip attention?
DESCRIPTION:Abstract: Transformers are ubiquitous. They influence nearly every aspect of modern AI. However\, the mechanics of their training remain poorly understood. This poses a problem for the field due to the immense amounts of data\, computational power\, and energy being invested in the training of these networks. I highlight a recent intriguing empirical result from our group. Specifically\, selfattention catastrophically fails to train unless it is paired with a skip connection. This contrasts with other components of a transformer that continue to demonstrate good performance (albeit suboptimal) when skip connections are removed. In this talk\, I explore why this is the case and what could be done to enhance the fundamental training efficiency of modern transformers. We even showcase some practical cases in which removing self-attention completely can lead to significantly improved performance. \nBio: Simon Lucey Ph.D. is the Director of the Australian Institute for Machine Learning (AIML) and a professor in the School of Computer and Mathematical Sciences\, at the University of Adelaide. He is also Director of the CommBank Foundational AI Research Centre. Prior to this he was an associate research professor at Carnegie Mellon University’s Robotics Institute (RI) in Pittsburgh USA; where he spent over 10 years as an academic. He was also Principal Research Scientist at the autonomous vehicle company Argo AI from 2017-2022. He has received various career awards\, notably the AmCham AI Scientist of the year in 2024. He is also currently a member of the Australian Government’s AI Expert Group\, and their National Robotics Strategy committee. Simon’s research interests span AI\, machine learning\, computer vision and robotics. \n  \nSponsor \nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/should-we-skip-attention/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/12/12-12-25-Lucy.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251208T153000
DTEND;TZID=America/New_York:20251208T163000
DTSTAMP:20260911T203540
CREATED:20251202T190520Z
LAST-MODIFIED:20251206T151245Z
UID:149651-1765207800-1765211400@www.ri.cmu.edu
SUMMARY:What Can We Learn from a Million Models?
DESCRIPTION:Abstract: Machine learning has transformed many fields by learning from large collections of data. Yet\, it is rarely applied to its own outputs: the models themselves. Today\, with millions of publicly available models\, a natural question arises: what can we do with so many models? In this talk\, I will motivate two core applications that leverage this untapped potential\, demonstrating their utility in the context of computer vision: (i) identifying emerging trends in model design\, and (ii) reducing the need to train models from scratch through model recycling. To support these goals\, I introduce the Model Atlas: a structured graph that represents models\, their attributes\, and the weight-space transformations that interconnect them. My research into weight-space learning enables the construction of this atlas by treating models themselves as data and inferring properties such as functionality\, performance\, and lineage directly from their weights. I will present key observations and methodologies that make weight-space learning possible at scale. As a visual prelude\, you can explore the repository under study at: https://horwitz.ai/model-atlas . \nBio: Eliahu Horwitz is a Google PhD Fellow in Machine Learning and ML Foundations and a final-year PhD candidate in Computer Science at The Hebrew University of Jerusalem\, advised by Prof. Yedid Hoshen. His research centers on learning representations of neural network weights and understanding model populations directly in weight space. He is particularly interested in how weight-space learning can enable new downstream capabilities\, such as model forensics\, model discovery\, and interpretability\, and in how treating models as data points can advance broader areas of machine learning. Eliahu is also a recipient of the Israeli Council for Higher Education Scholarship and has previously interned at Google Research. \nHomepage:  https://horwitz.ai \nSponsor \nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/what-can-we-learn-from-a-million-models/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/12/12-8-25.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251121T150000
DTEND;TZID=America/New_York:20251121T160000
DTSTAMP:20260911T203540
CREATED:20250915T203414Z
LAST-MODIFIED:20251125T191630Z
UID:148862-1763737200-1763740800@www.ri.cmu.edu
SUMMARY:How to Coordinate Thousands of Robots Efficiently and Robustly
DESCRIPTION:Abstract: \nLarge-scale robot fleets are increasingly deployed in warehouses\, factories\, transportation systems\, and emerging robotics applications. Coordinating hundreds or thousands of robots in shared\, cluttered spaces creates fundamental challenges in maintaining safety\, preventing deadlocks\, and minimizing congestion. In this talk\, I will present our recent work on scalable imitation learning methods for coordinating 10k robots\, automatic environment optimization techniques for alleviating traffic congestion\, and asynchronous execution frameworks that guarantee safe\, robust\, and deadlock-free multi-robot operations.\n\nBio: \nJiaoyang Li is an Assistant Professor in the Robotics Institute at Carnegie Mellon University. Her research lies at the intersection of artificial intelligence\, robotics\, and optimization\, with a particular focus on scalable multi-robot planning and coordination. She received her Ph.D. in Computer Science from the University of Southern California in 2022 and her B.Eng. in Automation from Tsinghua University in 2017. She is a recipient of the NSF CAREER Award\, best dissertation awards from ICAPS\, AAMAS\, and USC\, and multiple best paper awards from ICRA\, ICAPS\, and MRS.
URL:https://www.ri.cmu.edu/event/how-to-coordinate-thousands-of-robots-efficiently-and-robustly/
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/09/profile-scaled.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251114T143000
DTEND;TZID=America/New_York:20251114T153000
DTSTAMP:20260911T203540
CREATED:20250902T170114Z
LAST-MODIFIED:20251125T172342Z
UID:148675-1763130600-1763134200@www.ri.cmu.edu
SUMMARY:Just Asking Questions
DESCRIPTION:Abstract: In the age of deep networks\, “learning” almost invariably means “learning from examples”. We train language models with human-generated text and labeled preference pairs\, image classifiers with large datasets of images\, and robot policies with rollouts or demonstrations. When human learners acquire new concepts and skills\, we often do so with richer supervision\, especially in the form of language—we learn new concepts from examples accompanied by descriptions or definitions\, and new skills from demonstrations accompanied by instructions. Crucially\, language-based supervision involves not only instructions but *questions*—students ask questions to elicit the most useful pieces of supervision\, and teachers ask questions to probe student knowledge and encourage them to acquire new skills or aspects of understanding on their own. This talk will focus on a few recent projects focused on building computational models that can ask good questions for both learning and teaching\, with applications spanning LM alignment\, policy learning\, and education. This is joint work with Belinda Li\, Alex Tamkin\, Noah Goodman\, Andi Peng\, Ilia Sucholutsky\, Nishanth Kumar\, Julie A Shah\, Andreea Bobu\, Alexis Ross\, Gabe Grand\, Valerio Pepe and Josh Tenenbaum. \nBio: Jacob Andreas is an associate professor at MIT in the Department of Electrical Engineering and Computer Science as well as the Computer Science and Artificial Intelligence Laboratory. His research aims to understand the computational foundations of language learning\, and to build intelligent systems that can learn from human guidance. Jacob earned his Ph.D. from UC Berkeley\, his M.Phil. from Cambridge (where he studied as a Churchill scholar) and his B.S. from Columbia. He has received a Sloan fellowship\, an NSF CAREER award\, MIT’s Junior Bose and Kolokotrones teaching awards\, and paper awards at ACL\, ICML and NAACL.
URL:https://www.ri.cmu.edu/event/just-asking-questions/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/09/head_small.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251103T153000
DTEND;TZID=America/New_York:20251103T163000
DTSTAMP:20260911T203540
CREATED:20251027T174614Z
LAST-MODIFIED:20251027T174614Z
UID:149194-1762183800-1762187400@www.ri.cmu.edu
SUMMARY:From Video Generation to Video World Models
DESCRIPTION:Abstract:\nVideo diffusion models have achieved remarkable success in content creation\, yet they still fall short of simulating interactive worlds that respond to users in real time. This talk examines the fundamental challenges preventing these models from evolving into true world simulators. I will present a series of works — CausVid\, Self-Forcing\, MotionStream\, and State-Space World Model — that collectively mark a paradigm shift from non-causal diffusion models to autoregressive–diffusion hybrids capable of streaming long-duration videos with real-time interactivity. These advances move beyond passive video generation toward dynamic\, immersive experiences\, unlocking new possibilities across gaming\, robotics\, live video editing\, and augmented/virtual reality. \nBio: Xun Huang was a Research Scientist at Adobe\, NVIDIA\, as well as an Adjunct Professor at Carnegie Mellon University. He is currently the Founder and CEO of a stealth startup. He obtained his Ph.D. from Cornell University in 2020 under the advisement of Professor Serge Belongie. His doctoral research was recognized with the Fellowship from NVIDIA\, Adobe\, and Snap. His research interests lie broadly in deep generative models\, with a recent focus on video world models. \nHomepage:  xunhuang.me \nSponsor \nThe VASC seminar is generously sponsored by HeyGen\, an all-in-one AI-powered video generation platform that leverages advances in computer vision\, generative modeling\, and multimodal learning to make high-quality video creation both scalable and accessible.
URL:https://www.ri.cmu.edu/event/from-video-generation-to-video-world-models/
LOCATION:3305 Newell-Simon Hall
CATEGORIES:Seminar,VASC Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/10/11-3-25.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251031T143000
DTEND;TZID=America/New_York:20251031T153000
DTSTAMP:20260911T203540
CREATED:20250902T164414Z
LAST-MODIFIED:20251030T145800Z
UID:148671-1761921000-1761924600@www.ri.cmu.edu
SUMMARY:Toward Generalist Humanoid Robots: Recent Advances\, Opportunities\, and Challenges
DESCRIPTION:Abstract: In an era of rapid AI progress\, leveraging accelerated computing and big data has unlocked new possibilities to develop generalist AI models. As AI systems like ChatGPT showcase remarkable performance in the digital realm\, we are compelled to ask: Can we achieve similar breakthroughs in the physical world — to create generalist humanoid robots capable of performing everyday tasks? In this talk\, I will outline our data-centric research principles and approaches for building general-purpose robot autonomy in the open world. I will present our recent work leveraging real-world\, synthetic\, and web data to train foundation models for humanoid robots. Furthermore\, I will discuss the opportunities and challenges of building the next generation of intelligent robots.\n\nBio: Yuke Zhu is an Associate Professor in the Computer Science Department of UT-Austin\, where he directs the Robot Perception and Learning (RPL) Lab. He is also a Director and Distinguished Research Scientist at NVIDIA Research\, where he co-leads the Generalist Embodied Agent Research (GEAR) lab. He focuses on developing intelligent algorithms for generalist robots and embodied agents to reason about and interact with the real world. He obtained his Ph.D. degree from Stanford University. He received the NSF CAREER Award\, the IEEE RAS Early Academic Career Award\, and various faculty fellowships and research awards from Amazon\, JP Morgan\, and Sony Research.
URL:https://www.ri.cmu.edu/event/toward-generalist-humanoid-robots-recent-advances-opportunities-and-challenges/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/09/yukezhu.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251024T143000
DTEND;TZID=America/New_York:20251024T153000
DTSTAMP:20260911T203540
CREATED:20250902T163833Z
LAST-MODIFIED:20251024T220347Z
UID:148668-1761316200-1761319800@www.ri.cmu.edu
SUMMARY:Bringing Dexterity to Robot Hands in the Real World
DESCRIPTION:Abstract:  Dexterous manipulation is a grand challenge of robotics\, and fine manipulation skills are required for many robotics applications that we envision.   In this overview talk\, I will discuss my view of some major factors that contribute to dexterity and discuss how we can incorporate them into our robots and systems.\n\nBio:  Nancy Pollard is a Professor in the Robotics Institute and the Computer Science Department at Carnegie Mellon University. She received her PhD in Electrical Engineering and Computer Science from the MIT Artificial Intelligence Laboratory\, where she developed grasp and manipulation planning algorithms for the Stanford/JPL and Utah/MIT dexterous hands. Prof. Pollard spent the next few decades studying human and robot dexterity\, with emphasis on bringing human manipulation strategies with performance guarantees to humanoid robots with dexterous hands.  She received the NSF CAREER award for research on “Quantifying Humanlike Enveloping Grasps”\,  the Okawa Research Grant for “Studies of Dexterity for Computer Graphics and Robotics\,” and was a recent recipient of an NSF Convergence Accelerator award for “Bio-Inspired Design of Robot Hands for Use-Driven Dexterity.”   She has led the development of several generations of dexterous soft robotic hands\, is a founder of FuturHand Robotics and leads the CMU Foam Hands Laboratory.
URL:https://www.ri.cmu.edu/event/bringing-dexterity-to-robot-hands-in-the-real-world/
LOCATION:1403 Tepper School Building
CATEGORIES:RI Seminar,Seminar
ATTACH;FMTTYPE=image/jpeg:https://www.ri.cmu.edu/app/uploads/2025/09/nsp-crop.jpg
END:VEVENT
END:VCALENDAR