BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Events - ECPv6.17.2//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:20260121T110000
DTEND;TZID=America/Los_Angeles:20260121T123000
DTSTAMP:20260105T205329Z
CREATED:20260105T203936Z
LAST-MODIFIED:20260105T205329Z
UID:10008262-1768993200-1768998600@events.ucsc.edu
SUMMARY:CSE Colloquium - Constraining Chaos: Toward Faithful and Semantic Decoding in Language Models
DESCRIPTION:Presenter: Loris D’Antoni\, UC San Diego \nAbstract:\nLanguage models excel at producing fluent text\, but in domains like code and math\, fluency isn’t enough — outputs must obey strict syntactic and semantic rules. A new wave of research is rethinking decoding itself: not as a process of sampling words\, but as a negotiation between probability\, structure\, and meaning. In this talk\, I’ll explore how grammar and semantics can be embedded into the decoding loop\, how we can sample from the true model conditional distribution under constraints\, and how programmable abstractions make it possible to enforce properties like type safety or program invariants. The result is a vision of decoding that is faithful to the model yet governed by rules\, pointing toward a future where LLMs generate not just plausible text\, but reliably correct output. \nBio:\nLoris D’Antoni is a Jacobs Faculty Scholar and Associate Professor in the Department of Computer Science and Engineering at the University of California San Diego. His research helps people build trustworthy software. His work has introduced new frameworks for verifying and synthesizing programs—ranging from resilient network configurations to robust decision-making systems—and\, more recently\, methods for aligning language models with user intent. \nHe is the recipient of an NSF CAREER Award and a Microsoft Research Faculty Fellowship\, and was selected as a Vilas Associate at the University of Wisconsin-Madison. He has also received Google\, Amazon\, and Meta Faculty Awards\, and the Morris and Dorothy Rubinoff Dissertation Award. His papers have earned several best paper awards and nominations\, including at TACAS\, ESOP\, ICDCN\, and SBES. \nLoris received his B.S. and M.S. in Computer Science from the University of Torino\, and his Ph.D. in Computer Science from the University of Pennsylvania. Before joining UC San Diego\, he was a faculty member at the University of Wisconsin–Madison. \nHosted by: Professor Nikos Tziavelis \nLocation: Engineering 2\, Room E2-180 \n*Light refreshments such as coffee\, pastries\, and fruit will be available. \nZoom: https://ucsc.zoom.us/j/93445911992?pwd=YkJ2TQtF79h0PcNXbEcpZLbpK0coiY.1&jst=3
URL:https://events.ucsc.edu/event/cse-colloquium-constraining-chaos-toward-faithful-and-semantic-decoding-in-language-models/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Lectures & Presentations,Seminars
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/01/ldantoni-scaled.jpg
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