BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Events - ECPv6.18.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://live-events-ucsc.pantheonsite.io
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:20261023T144000
DTEND;TZID=America/Los_Angeles:20261023T154500
DTSTAMP:20261022T211345Z
CREATED:20261015T174218Z
LAST-MODIFIED:20261022T211345Z
UID:10017824-1792766400-1792770300@live-events-ucsc.pantheonsite.io
SUMMARY:CSE Colloquium: Relational Attention for Data-Efficient Language Modeling
DESCRIPTION:Title: Relational Attention for Data-Efficient Language Modeling \nPresenter: Adrian Brasoveanu\, UCSC Linguistics (Joint work with Ece Takmaz and Jakub Dotlačil) \nAbstract: We present Relational BabyLM\, a system submission to the BabyLM 2026 challenge that combines two cognitively motivated inductive biases in a single decoder-only Transformer. Architecturally\, we replace standard self-attention with a Dual Attention Transformer (DAT)\, which separates the routing of object-level (“sensory”) lexical features from structural/relational information (Altabaa and Lafferty\, 2025; Altabaa et al.\, 2024; Webb et al.\, 2024; Kerg et al.\, 2022; Webb et al.\, 2021). Relational attention (RA) disentangled from self-attention greatly increases data efficiency and out-of-training-sample generalization on purely relational tasks\, but language modeling requires object-level and relational information to be integrated as well as disentangled\, and RA-based LMs have remained largely unexplored. BabyLM’s data-constrained training and comprehensive evaluation is an ideal testing ground for whether that data efficiency transfers. As a training intervention\, we add a Next-Latent Prediction (NextLat; Teoh et al. 2026) objective that encourages hidden states to compress history incrementally into a dense belief state. Architecture is the dominant factor for structural linguistic generalization; the objective is secondary but still significant. DAT’s three relational attention types (full RA vs. the simpler RCA and DisRCA variants) are largely interchangeable at 10M words; full RA pulls ahead at 100M. We also introduce a novel symbol-retrieval mechanism (RoPE-based\, as opposed to learned\, relative symbols) that matches learned symbol libraries while adding no parameters. On the strict (100M-word) track\, our best model ranks 6th of 55 overall and 3rd of 55 on the leaderboard’s NLP-task subset at the time of writing; our two strongest models outperform the GPT-2 baseline on most benchmarks\, with one attaining the highest EWoK score among strict-track entries. \nPaper: https://arxiv.org/abs/2609.20530 \nCode: https://github.com/abrsvn/babylm_dat_2026 \nBio: I am a  professor in computational (psycho)linguistics focusing largely on natural language semantics and pragmatics at UCSC. I was also associate campus provost (tout court for 2 years\, then of strategic initiatives for 1 year) in the UCSC EVC office between 2021 and 2024.  For some more of my recent work\, see https://github.com/abrsvn/. \nHosted by: Professor Daniel Fremont and Professor Leilani Gilpin \nDate and Time: Fridays from 2:40 – 3:45 pm \nLocation: Engineering 2\, Room E2-180 (Refreshments such as fruit\, pastries\, coffee\, and tea will be provided.) \nZoom Option: https://ucsc.zoom.us/j/95300285113?pwd=62tnEPUtRrsmbW7SHTavaRbaF2afSr.1
URL:https://live-events-ucsc.pantheonsite.io/event/cse-colloquium-relational-attention-for-data-efficient-language-modeling/
LOCATION:Engineering 2\, Engineering 2 1156 High Street\, Santa Cruz\, CA\, 95064
CATEGORIES:Lectures & Presentations,Seminars
ATTACH;FMTTYPE=image/jpeg:https://live-events-ucsc.pantheonsite.io/wp-content/uploads/2026/10/Adrian.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
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20261103T100000
DTEND;TZID=America/Los_Angeles:20261103T120000
DTSTAMP:20261019T183247Z
CREATED:20261019T183247Z
LAST-MODIFIED:20261019T183247Z
UID:10017827-1793700000-1793707200@live-events-ucsc.pantheonsite.io
SUMMARY:Education in the Age of AI: Faculty Panel and Workshop
DESCRIPTION:CITRIS and the Banatao Institute at UC Santa Cruz and the Humanities Institute invite you to a faculty panel and workshop discussing the evolving role of artificial intelligence in education. The event will be held on Tuesday\, November 3\, 2026\, from 10 AM to 12 PM in the College 9/John R. Lewis College Multipurpose Room. All students\, faculty\, and staff are welcome\, and admission is free. \nThe panel discussion will be moderated by Pranav Anand\, Faculty Director of The Humanities Institute and Professor of Linguistics\, and the panel will feature: \n\nLeilani Gilpin\, Professor of Computer Science and Engineering\nZac Zimmer\, Professor of Literature\nLauren Lyons\, Professor of Philosophy\nAdam Smith\, Professor of Computational Media\n\nPanelists will discuss how AI impacts teaching and learning\, with questions including: \n\nWhat does education mean in the age of AI?\nWhat is the impact of AI use on critical thinking?\nWhat is the difference between producing good work and learning something?\nShould students opt out of AI use altogether\, embrace it\, or something in between?\nAre there ways to engage with this technology ethically?\nIf I don’t use AI\, will I ever get a job?\nWhat are the realistic impacts of AI on entry-level careers in my field?\nWho should decide how AI is used in education?\nWhat should be done about AI specifically at UC Santa Cruz?\n\nFollowing the panel\, attendees will participate in small-group workshops to share their opinions on these issues and collectively brainstorm potential paths forward. This event is the first in a proposed series focused on AI and education\, with future events building on the outcomes of this initial convening. \nPlease use our registration form to let us know you are planning to attend. Registration is not required to participate\, but it will help us estimate attendance and plan for the event. For questions\, please contact CITRIS at citris@ucsc.edu.
URL:https://live-events-ucsc.pantheonsite.io/event/education-in-the-age-of-ai-faculty-panel-and-workshop/
LOCATION:Colleges Nine and John R. Lewis College Multi-purpose Room\, 615 College Nine Road\, Santa Cruz\, CA\, 95064
ATTACH;FMTTYPE=image/png:https://live-events-ucsc.pantheonsite.io/wp-content/uploads/2026/10/EDUCATION-IN-THE-AGE-OF-AI.png
GEO:37.0009703;-122.0577323
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Colleges Nine and John R. Lewis College Multi-purpose Room 615 College Nine Road Santa Cruz CA 95064;X-APPLE-RADIUS=500;X-TITLE=615 College Nine Road:geo:-122.0577323,37.0009703
END:VEVENT
END:VCALENDAR