BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Events - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Events
X-ORIGINAL-URL:https://events.ucsc.edu
X-WR-CALDESC:Events for Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20270314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20271107T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260225T090000
DTEND;TZID=America/Los_Angeles:20260225T120000
DTSTAMP:20260421T152903
CREATED:20260210T221905Z
LAST-MODIFIED:20260210T221905Z
UID:10009196-1772010000-1772020800@events.ucsc.edu
SUMMARY:Liu\, C. (CSE) - Enabling LLM Unlearning at Inference Time by Decomposing Detection and Intervention
DESCRIPTION:Machine unlearning addresses the “right to be forgotten” under GDPR and enables privacy\, copyright\, and safety compliance in large language models. Training-based unlearning can remove targeted behavior on benchmarks\, but it scales poorly\, can degrade utility\, and can fail under adversarial prompting that recovers supposedly forgotten content. This prospectus proposes inference-time behavioral unlearning: rather than modifying weights to “erase” knowledge\, we detect when a query targets forgotten content and intervene in generation so the system behaves like a model never trained on that content. We formalize this approach as Detect-Intervene Decomposition and instantiate it with three complementary methods operating at the embedding\, token\, and reasoning levels under different access capabilities. Comprehensive experiments across entity unlearning\, hazardous knowledge removal\, and copyright protection demonstrate that our methods match or exceed training-based approaches while being orders of magnitude faster and preserving model utility. As LLMs increasingly operate as services with restricted weight access\, inference-time unlearning provides the only practical path for responsible AI deployment that respects privacy\, safety\, and legal requirements. \nEvent Host: Chris Liu\, Ph.D. Student\, Computer Science and Engineering \nAdvisor: Yang Liu \nZoom – https://ucsc.zoom.us/j/94799852992?pwd=EBFQe4U2lRNro1oJ8F36bgORhT2xSv.1 \nPasscode –  242384
URL:https://events.ucsc.edu/event/liu-c-cse-enabling-llm-unlearning-at-inference-time-by-decomposing-detection-and-intervention/
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/01/ph.d.-presentation-graphic-option-1-1.jpg
LOCATION:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260225T110000
DTEND;TZID=America/Los_Angeles:20260225T121500
DTSTAMP:20260421T152903
CREATED:20260224T172405Z
LAST-MODIFIED:20260224T172405Z
UID:10009274-1772017200-1772021700@events.ucsc.edu
SUMMARY:CSE Colloquium: Agile and evolvable software construction in the era of rapidly evolving hardware accelerator designs
DESCRIPTION:Presenter\n\nCharith Mendis\, Siebel School of Computing and Data Science\, University of Illinois at Urbana-Champaign\n\nAbstract\n\nModern AI workloads have become exceedingly abundant and important in the current computing landscape. As a result\, there have been numerous software and hardware innovations aimed at accelerating these workloads. However\, we observe a subtle disconnect between the software and hardware communities. Most software innovations target well-established hardware platforms such as CPUs (e.g.\, x86\, ARM) and GPUs (e.g.\, NVidia GPUs)\, while hardware innovations produce plenty of other tensor accelerator designs (e.g.\, Gemmini\, Feather\, Trainium) each year.\n\nWe asked the question\, why aren’t the software community using these accelerators or even evaluating on them? The simple yet undeniable reason is the lack of standardized software tooling compared to CPUs and GPUs. For an architecture to be used\, properly designed compiler backends\, correctness\, and performance testing tools should be abundant (e.g.\, CUDA ecosystem).\n\nIn this talk\, I will describe how we bridge this gap by automatically generating the necessary software tools for a large class of accelerators through the Accelerator Compiler Toolkit (ACT) ecosystem. Central to ACT is an ISA definition language\, TAIDL\, that for the first time standardizes the hardware-software interfaces for a large class of accelerators. Departing from the traditional approach of manually constructing test oracles\, performance models\, or retargetable compiler backends\, we instead introduce agile and evolvable methodologies to automatically generate such necessary tooling using both formal methods and machine learning techniques for any TAIDL-defined accelerator interface. I will show how such automation enables rapid software prototyping\, making rapidly evolving accelerator designs usable by the software community.\n\nBio\n\nCharith Mendis is an Assistant Professor in the Siebel School of Computing and Data Science at the University of Illinois at Urbana-Champaign. His broad research interests are at the intersection of compilers\, programming languages\, and machine learning. He received his Ph.D. and Master’s from the Massachusetts Institute of Technology and his B.Sc. from the University of Moratuwa. He is the recipient of the DARPA Young Faculty Award\, the NSF CAREER Award\, the Google ML and Systems Junior Faculty Award\, the Outstanding Advisor award at UIUC\, the William A. Martin Outstanding Master’s Thesis Award at MIT\, and the University Gold Medal for his B.Sc. He has won numerous paper awards\, including a Distinguished Paper Award at POPL\, a Best Student Paper Award at the IEEE BigData conference\, an honorable mention for the Best Artifact Award at SIGMOD\, a Best Paper Award at ML for Systems workshop at ISCA\, and an IEEE Top Picks Honorable Mention.\n\nHosted by: Professor Nikos Tziavelis\n\nLocation: Engineering 2\, E2-180 (Refreshments such as fruit\, pastries\, tea\, and coffee will be available for guests.)\n\nZoom: https://ucsc.zoom.us/j/93445911992?pwd=YkJ2TQtF79h0PcNXbEcpZLbpK0coiY.1&jst=3 
URL:https://events.ucsc.edu/event/cse-colloquium-agile-and-evolvable-software-construction-in-the-era-of-rapidly-evolving-hardware-accelerator-designs/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Lectures & Presentations
ATTACH;FMTTYPE=image/png:https://events.ucsc.edu/wp-content/uploads/2026/02/BElogoWHITE.png
GEO:37.0009723;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Engineering 2 Engineering 2 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Engineering 2 1156 High Street:geo:-122.0632371,37.0009723
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260225T150000
DTEND;TZID=America/Los_Angeles:20260225T170000
DTSTAMP:20260421T152903
CREATED:20260211T203445Z
LAST-MODIFIED:20260218T010402Z
UID:10009206-1772031600-1772038800@events.ucsc.edu
SUMMARY:February 25\, 2026 | Works-in-Progress with Geoffrey Bowker
DESCRIPTION:Wednesday\, February 25\, 2026 \n3:00 – 5:00 PM \nHumanities 1\, Room 210 or Zoom (Registration) \nJoin SJRC scholars in Humanities 1\, room 210 or on Zoom for an open discussion of works-in-progress! This is a wonderful chance to engage with one another’s ideas\, and support our own internal work. \nAt this session\, we will hear from Geoffrey Bowker\, Emeritus Professor in Irvine and Science & Justice Advisor about works-in-progress and ongoing work on the death of infrastructure\, AI\, and underwater network cables and his collaborative comic book on Actor Network Theory. SJRC members Warren Sack and Dimitris Papadopolous will act as “warm up” discussants. \nContact Colleen Stone (colleen@ucsc.edu) or Maria Puig de la Bellacasa (puig@ucsc.edu) for the readings\, including a new comic book on the graveyard of machines! \nRegister for Zoom here. \nGeoffrey C. Bowker is Emeritus Professor at the School of Information and Computer Science\, University of California at Irvine\, where he directed a laboratory for Values in the Design of Information Systems and Technology. He was also Professor of and Senior Scholar in Cyberscholarship at the University of Pittsburgh School\, and Executive Director\, Center for Science\, Technology and Society\, Santa Clara. He was awarded the prestigious 4S Bernal Prize in 2024 for his distinguished\, career-long contributions to the field of Science and Technology Studies (STS). His book Memory Practices in the Sciences (MIT Press 2008) won the 2007 Ludwig Fleck Prize of the Society for Social Studies of Science\,  and was awarded “Best Information Science Book” by the American Society for Information Science and Technology (ASIS&T). \nCo-sponsored by earthecologies x technoscience conversations\, History of Consciousness
URL:https://events.ucsc.edu/event/february-25-2026-works-in-progress-with-geoffrey-bowker/
CATEGORIES:Seminars
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260225T173000
DTEND;TZID=America/Los_Angeles:20260225T190000
DTSTAMP:20260421T152903
CREATED:20260130T054047Z
LAST-MODIFIED:20260209T232119Z
UID:10009139-1772040600-1772046000@events.ucsc.edu
SUMMARY:Exploring Research Pathways at Baskin Engineering
DESCRIPTION:Curious how being part of a research lab can supercharge your experience as a Baskin Engineer?   \nJoin us for this informative event to learn about opportunities to solve open-ended problems\, build deeper technical skills\, and learn how to think like an engineer. \nWe’ll kick things off with a quick overview of the kinds of research opportunities available to undergrads and how to get started\, then you’ll hear directly from students who’ve worked in research labs as undergraduates. They’ll share what they actually did day-to-day\, the skills they built (technical and professional)\, and how research shaped their confidence\, career goals\, and next steps. We’ll then have pizza and networking to end the evening. \nWhether you’re aiming for industry\, graduate school\, or just want hands-on experience that goes beyond coursework\, this panel will help you understand how undergraduate research can set you apart—academically\, professionally\, and personally! \n\nRegister via Handshake. \nYOU BELONG HERE\nPrograms and services are open to all\, consistent with state and federal law\, as well as the University of California’s nondiscrimination policies. Every initiative—whether a student service\, faculty program\, or community event—is designed to be accessible\, inclusive\, and respectful of all identities. To learn more\, please visit UC Nondiscrimination Statement or Nondiscrimination Policy for UC Publications.
URL:https://events.ucsc.edu/event/exploring-research-pathways-at-baskin-engineering/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Seminars
ATTACH;FMTTYPE=image/png:https://events.ucsc.edu/wp-content/uploads/2026/01/BElogoWHITE.png
GEO:37.0009723;-122.0632371
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Engineering 2 Engineering 2 1156 High Street Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=Engineering 2 1156 High Street:geo:-122.0632371,37.0009723
END:VEVENT
END:VCALENDAR