BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Events - ECPv6.16.5.1//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:20260713T100000
DTEND;TZID=America/Los_Angeles:20260713T120000
DTSTAMP:20260707T160215Z
CREATED:20260707T160215Z
LAST-MODIFIED:20260707T160215Z
UID:10015010-1783936800-1783944000@events.ucsc.edu
SUMMARY:Scott\, J. (CSE) - Mechanistic Specialization Does Not Guarantee Performance: Evidence from Dual AttentionTransformers
DESCRIPTION:Dual Attention Transformers (DATs) extend decoder-only Transformers with a dedicated relational-attention stream\, making them a natural architecture for abstract identity rules such asABA and ABB. Surprisingly\, we find that comparably sized GPT-2 models outperform DATs on these tasks. We investigate this gap with two complementary mechanistic analyses. First\, causal mediation analysis shows that DATs exhibit stronger evidence of hypothesized symbolic mechanisms: symbol abstraction\, symbol induction\, and retrieval\, than GPT-2. Second\, a routing analysis shows why this specialization does not translate into better behavior: DATs make more wrong-copy errors\, can attend to the correct source token while still predicting the wrong token\, and show weak direct contribution from relational attention to the correct-versus-wrong outputmargin. Ablating positive-routing heads hurts performance\, while amplifying those headsimproves DAT more than matched controls. These results show that explicit relational attentioncan shape internal organization without guaranteeing task success. For identity-rule tasks\, performance depends not only on whether relational information is represented\, but whether it is routed to the final output position in a form that affects the next-token prediction. Because pretrained DAT and GPT-2 models differ in training data\, tokenizer\, and other implementation details\, these findings should be interpreted as evidence about the mechanisms used by existing models rather than as a definitive architectural comparison. Follow-up experiments will address these confounders through controlled training comparisons that match data\, scale\, and evaluation conditions across architectures. \nEvent Host: Jonathan Scott\, Ph.D. Student\, Computer Science & Engineering \nAdvisor: Leilani Gilpin \nZoom: https://ucsc.zoom.us/j/95404396322?pwd=0e0AegKSxhcFDDKrn08muHcqfHs6WW.1 \nPasscode: 985103
URL:https://events.ucsc.edu/event/scott-j-cse-mechanistic-specialization-does-not-guarantee-performance-evidence-from-dual-attentiontransformers/
CATEGORIES:Ph.D. Presentations
ATTACH;FMTTYPE=image/jpeg:https://events.ucsc.edu/wp-content/uploads/2026/04/ph.d.-presentation-graphic-option-1.jpg
LOCATION:
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260713T183000
DTEND;TZID=America/Los_Angeles:20260713T200000
DTSTAMP:20260625T175931Z
CREATED:20260625T175931Z
LAST-MODIFIED:20260625T175931Z
UID:10014991-1783967400-1783972800@events.ucsc.edu
SUMMARY:July Slugs and Steins with Assistant Professor Aide Macias-Munoz
DESCRIPTION:Unlocking the blueprint for regeneration: Insights from Hydra\nRegeneration\, the ability to heal and regrow lost body parts\, varies across species\, tissues\, and even cell types. To harness regenerative ability for medicine\, we need to understand the genetic mechanisms that are similar across regenerating species. My lab uses Hydra\, a small freshwater relative of jellyfish\, to investigate how the genome controls this extraordinary process. Hydra possess remarkable regenerative abilities\, including the capacity to regenerate head and foot when cut in half and to rebuild a complete animal from clusters of cells. By studying gene expression and gene regulation during regeneration\, we aim to identify the genetic programs that drive this process. In this talk\, I will discuss what Hydra can teach us about the evolution and genetic basis of regeneration. \nAide Macias-Muñoz is an Assistant Professor in the Department of Ecology and Evolutionary Biology at UC Santa Cruz. Her research seeks to understand how complex traits\, including regeneration and eyes\, have evolved across animals. She is particularly interested in deciphering whether similar or different genes are used to encode these traits in different species. She holds a B.A. in Integrative Biology with a minor in Chicana/o Studies from the University of California\, Berkeley and a Ph.D. from the University of California\, Irvine. \nREGISTER
URL:https://events.ucsc.edu/event/july-slugs-and-steins-with-assistant-professor-aide-macias-munoz/
CATEGORIES:Lectures & Presentations
ATTACH;FMTTYPE=image/png:https://events.ucsc.edu/wp-content/uploads/2025/10/slugs-and-steins-blackthorn-banner.png
LOCATION:
END:VEVENT
END:VCALENDAR