BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN X-WR-CALNAME:Calendar - Department of Computer Science X-WR-TIMEZONE:Eastern Time (US & Canada) BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53506703533129 DTSTART:20260811T180000Z DTEND:20260811T190000Z DESCRIPTION:Ethan Johnson\, "Securing and Accelerating Hypervisors with Vir tual Instruction Set Computing"\n\nAdvisor: Prof. John Criswell (Computer Science) \n\nCommittee: Prof. Chen Ding (Computer Science)\, Prof. Michae l L. Scott (Computer Science)\, Prof. Emmett Witcher (UT Austin)\n\nChair: William R. Donaldson (Laboratory for Laser Energetics)\n\nModern cloud co mputing promises a compelling bargain: by virtualizing and containerizing our digital application workloads\, we can safely and efficiently enable m utually distrustworthy tenants to share the same physical hardware by exte nding the same time-sharing techniques that have long been the foundation of multitasking operating systems. The widespread deployment and adoption of virtualization has delivered massive gains in economies of scale\, modu larity\, and resiliency\, enabling even the smallest tenants to fluidly ac cess tailored yet staggeringly powerful computing resources while benefiti ng from levels of redundancy and operational assurance that were once the exclusive province of large enterprises with full-time IT divisions. Today \, even hobbyists and undergraduate students routinely deploy network appl ications to public clouds like Amazon Web Services (AWS) and Microsoft Azu re\, enjoying their own private slice of enterprise-level datacenter infra structure for a few dollars a month.\n\nThis entire concept is premised on the idea that virtualized\, shared systems can provide strong security bo undaries between tenants. In modern clouds\, the lion's share of that secu rity responsibility is placed upon the hypervisor\, the software layer res ponsible for providing each tenant with a virtualized view of a complete c omputer system\, called a "virtual machine" (VM). The hypervisor mediates between those VMs and the physical hardware on which they run\, ensuring t he critical security dimensions of confidentiality\, integrity\, and avail ability are upheld between VMs even as they "live in the same brain"\, com putationally speaking.\n\nBut hypervisors\, like operating system kernels before them\, are ultimately just software---complex\, intricate works of logic\, vulnerable to all manner of mistakes and abstraction violations th at can undermine the security guarantees they are supposed to uphold. Crit ical hypervisor vulnerabilities are discovered and exploited every year\, compromising the valuable data and responsibilities with which users entru st these systems and shaking confidence in the feasibility of deploying se nsitive workloads in public clouds. Many of these vulnerabilities occur at the lowest levels of software abstraction\, calling for solutions that un derstand and address the semantic gaps that arise from their nuanced inter actions with the computer's hardware and other software.\n\nPrior work has shown that virtual instruction set computing (VISC) techniques are a high ly effective way to implement strong security hardening in low-level\, pri vileged-mode operating system software with competitive performance tradeo ffs. This dissertation posits\, and demonstrates\, the thesis that such te chniques can be applied effectively to virtual machine hypervisors\, and i n fact tend to yield much more favorable security/performance tradeoffs in this context due to the high trust and small runtime fraction required of hypervisors compared to operating system kernels. Furthermore\, these tec hniques can be used not only to add hardening to existing threat models\, but also to supplant existing hardware-based isolation relied upon by hype rvisors—and in some contexts\, this has the potential to dramatically im prove performance compared to the conventional non-VISC approaches in comm on use. GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 2506 SUMMARY:PhD Thesis Defense: Ethan Johnson\, Computer Science URL;VALUE=URI:https://events.rochester.edu/event/phd-thesis-defense-ethan-j ohnson-computer-science END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53877724466736 DTSTART:20260918T180000Z DTEND:20260918T190000Z DESCRIPTION:Advancing Computer Vision in the Era of Vision Foundation Model s\n\n \n\nAbstract:\n\nOver the past several decades\, computer vision has witnessed remarkable progress across a broad range of tasks. Recently\, t he field has entered a new era with the emergence of large-scale Vision Fo undation Models (VFMs). By learning general-purpose visual representations from massive data\, VFMs offer new opportunities to address several long- standing challenges in computer vision\, including generalization\, open-v ocabulary understanding\, and the development of unified models. In this t alk\, we will explore the evolving role of VFMs in vision\, spanning sever al paradigms: leveraging frozen VFMs\, adapting VFMs\, developing domain-s pecific VFMs\, and\, ultimately\, using VFMs as agents. Together\, these a pproaches point toward a broader shift in how we build\, adapt\, and deplo y computer vision systems.\n\n \n\nBio:\n\nDr. Xiaoming Liu is Jacqueline Maria Hagan Distinguished Professor at the Department of Computer Science of University of North Carolina at Chapel Hill. He was MSU Foundation Prof essor\, and Anil and Nandita Jain Endowed Professor at the Department of C omputer Science and Engineering of Michigan State University (MSU). He rec eived Ph.D. degree from Carnegie Mellon University in 2004. Before joining MSU in 2012 he was a research scientist at General Electric (GE) Global R esearch. He works on computer vision\, machine learning\, and biometrics e specially on face related analysis and 3D vision. He is an Associate Edito r of IEEE Transactions on Pattern Analysis and Machine Intelligence. He ha s authored more than 200 scientific publications\, and has filed 35 U.S. p atents. His work has been cited over 35000 times according to Google Schol ar\, with an H-index of 90. He is a fellow of IEEE and IAPR. More informa tion of Dr. Liu’s research can be found at http://cvlab.cs.unc.edu GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Xiaoming Liu URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-xiaoming -liu CATEGORIES:Lectures & Talks END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53877744452256 DTSTART:20260921T160000Z DTEND:20260921T170000Z DESCRIPTION:Professor Roshan Peiris of Rochester Institute of Technology wi ll be giving a talk to the Department of Computer Science.\n\n \n\nTalk de tails will be added here closer to the event. GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Roshan Peiris URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-roshan-p eiris CATEGORIES:Lectures & Talks END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53852212270073 DTSTART:20260928T160000Z DTEND:20260928T170000Z DESCRIPTION:Sparse Conv and Graph Fourier Representation for Point Cloud Su per-Resolution\, Prediction\, and Compression \n\n \n\nAbstract: \n\nDue t o the increased popularity of 3D immersive visual communication in augment ed and virtual reality applications\, as well as 3D sensing for digital tu nes and auto-driving\, the interest in capturing high resolution real-worl d point clouds has grown significantly in recent years. Point cloud is a n ew class of signal that is non-uniform and sparse and this present unique challenges to the signal processing\, compression and learning problems. I n this talk\, we present our multi-scale sparse convolutional learning and Graph Frourier Transform (GFT) based framework for large scale point clou d processing\, with applications to the geometry and attributes super-reso lution\, and dynamic point cloud compression with latent space compensatio n. The architecture is memory efficient and can learn a deep networks to h andle large scale point cloud in real world applications. Initial results demonstrated that this framework achieved new state of the art results in geometry super-resolution\, attributes deblocking and super-resolving\, an d dynamic point cloud sequence compression\, and is adopted in the MPEG AI based point cloud coding framework. \n\n \n\nBio:\n\nZhu Li is a professo r with the Dept of Computer Science & Electrical Engineering\, University of Missouri\, Kansas City(UMKC)\, and the director of NSF I/UCRC Center fo r Big Learning (CBL) at UMKC. He received his PhD in Electrical & Computer Engineering from Northwestern University in 2004. He was the AFRL summer faculty at the UAV Research Center\, US Air Force Academy (USAFA)\, 2016-1 8\, 2020-24. He was Senior Staff Researcher with the Samsung Research Amer ica's Multimedia Standards Research Lab in Richardson\, TX\, 2012-2015\, S enior Staff Researcher with FutureWei (Huawei) Technology's Media Lab in B ridgewater\, NJ\, 2010~2012\, Assistant Professor with the Dept of Computi ng\, the Hong Kong Polytechnic University from 2008 to 2010\, and a Princi pal Staff Research Engineer with the Multimedia Research Lab (MRL)\, Motor ola Labs\, from 2000 to 2008. His research interests include point cloud a nd light field compression\, graph signal processing and deep learning in the next gen visual compression\, remote sensing\, image processing and un derstanding. He has 70+ issued or pending patents\, 200+ publications in b ook chapters\, journals\, and conferences in these areas. He is an IEEE se nior member\, Associate Editor-in-Chief (2020~23) and Senior Area Editor ( 2024~) for IEEE Trans on Circuits & System for Video Tech\, Associate Edi tor for IEEE Trans on Image Processing(2020~)\, IEEE Trans.on Multimedia ( 2015-18)\, IEEE Trans on Circuits & System for Video Technology(2016-19). His team won the AFRL sponsored Perception Beyond Visual Spectrum (PBVS) g rand challenge at CVPR 2023 on SAR image recognition\, and thermo image su per-resolution in 2024. He also received the Best Paper Award at IEEE Int' l Conf on Multimedia & Expo (ICME)\, Toronto\, 2006\, and IEEE Int'l Conf on Image Processing (ICIP)\, San Antonio\, 2007. GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Zhu Li URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-zhu-li CATEGORIES:Lectures & Talks END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53877760420629 DTSTART:20261001T180000Z DTEND:20261001T190000Z DESCRIPTION:Professor Frank Ferraro of University of Maryland\, Baltimore C ounty will be giving a talk to the Department of Computer Science.\n\n \n\ nTalk details will be added here closer to the event. GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Frank Ferraro URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-frank-fe rraro CATEGORIES:Lectures & Talks END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53877784447571 DTSTART:20261019T160000Z DTEND:20261019T170000Z DESCRIPTION:Martin Falk of University of Chicago will be giving a talk to t he Department of Computer Science.\n\n \n\nTalk details will be added here closer to the event. GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Martin Falk URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-martin-f alk CATEGORIES:Lectures & Talks END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53877801564276 DTSTART:20261026T160000Z DTEND:20261026T170000Z DESCRIPTION:Kicking Off the Flywheel of AI + XR Innovations with XR Blocks\ n\n \n\nAbstract:\n\nThe concurrent revolutions in generative AI and spati al computing are fundamentally transforming how we work\, communicate\, an d live. While AI research is accelerated by mature frameworks and benchmar ks\, inventing AI-driven XR interactions remains a high-friction process. This raises a critical question: how can we make AI + XR technology more a ccessible and useful to creators?\nThis talk first explores a continuum of research designed to augment human abilities in XR\, including Geollery\, Depth Lab\, Visual Captions\, Sensible Agent\, and Agent Hands. Building upon foundational systems like Visual Blocks and InstructPipe\, we empower creators with visual programming tools that better align with human inten t.\nFinally\, we present XR Blocks (https://xrblocks.github.io)\, a cross- platform framework to accelerate human-centered AI + XR innovation. Driven by the mission of “minimizing code from idea to reality\,” XR Blocks provides core abstractions and samples that empower creators to move from concept to interactive AI + XR applications. We conclude the talk with liv e demonstrations of Vibe Coding XR (https://xrblocks.github.io/gem)\, offe ring a visionary glimpse into the future and the automatic evolution of th e AI + XR flywheel.\n\n \n\nBio:\n\nRuofei Du serves as the Interactive Pe rception & Graphics Lead at Google XR\, where he drives AI + XR innovation s. An established expert in his field\, he served as an Associate Chair on the program committees for both ACM CHI (2021-2026) and UIST (2022-2026)\ , and an Associate Editor for IEEE Transactions on Circuits and Systems fo r Video Technology. Dr. Du's contributions includes 8 US patents and over 45 peer-reviewed publications in top venues across HCI\, Computer Graphics \, and Computer Vision. His research has garnered significant recognition\ , including the Auggie Award at AWE USA 2026\, a Distinguished Paper Award in ACM IMWUT\, Best Paper Award at SIGGRAPH Web3D 2016\, and multiple Hon orable Mentions Awards at CHI and TVCG. He holds a Ph.D. in Computer Scien ce from the University of Maryland\, College Park. Website: https://duruof ei.com GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Ruofei Du URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-ruofei-d u CATEGORIES:Lectures & Talks END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53877812542081 DTSTART:20261102T170000Z DTEND:20261102T180000Z DESCRIPTION:Professor Pengfei Li of Rochester Institute of Technology will be giving a talk to the Department of Computer Science.\n\n \n\nTalk detai ls will be added here closer to the event. GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Pengfei Li URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-pengfei- li CATEGORIES:Lectures & Talks END:VEVENT BEGIN:VEVENT DTSTAMP:20260906T032601Z UID:tag:localist.com\,2008:EventInstance_53877830450298 DTSTART:20261116T170000Z DTEND:20261116T180000Z DESCRIPTION:Professor Junsong Yuan of University at Buffalo will be giving a talk to the Department of Computer Science.\n\n \n\nTalk details will be added here closer to the event. GEO:43.126069;-77.629191 LOCATION:Wegmans Hall\, 1400 SUMMARY:CS Seminar Series: Junsong Yuan URL;VALUE=URI:https://events.rochester.edu/event/cs-seminar-series-junsong- yuan CATEGORIES:Lectures & Talks END:VEVENT END:VCALENDAR