BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//უნივერსიტეტის ღონისძიებების პორტალი - ECPv6.2.8.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://events.iliauni.edu.ge/en/
X-WR-CALDESC:Events for უნივერსიტეტის ღონისძიებების პორტალი
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Dubai
BEGIN:STANDARD
TZOFFSETFROM:+0400
TZOFFSETTO:+0400
TZNAME:+04
DTSTART:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Dubai:20250503T130000
DTEND;TZID=Asia/Dubai:20250503T140000
DTSTAMP:20260419T105849
CREATED:20250502T080726Z
LAST-MODIFIED:20250502T102650Z
UID:10005723-1746277200-1746280800@events.iliauni.edu.ge
SUMMARY:Importance and relevance of embedding models\, their construction\, and the methodology for selecting the appropriate architecture
DESCRIPTION:On May 3\, Ilia State University will host an event as part of Tbilisi AI Meetups: \n“Importance and relevance of embedding models\, their construction\, and the methodology for selecting the appropriate architecture.” \nIn the age of powerful large language models\, embeddings remain a critical component in retrieval\, recommendation\, and understanding systems. This session explores why embeddings still matter\, how they’re built\, and how to choose the right architecture for your domain and application. \nAgenda Highlights: \n\nContext length limitations and the rise of RAG;\nWhy LLMs aren’t ideal for embedding generation;\nCausal attention vs contrastive learning;\nSparse vs dense retrieval (TF-IDF\, SPLADE\, hybrid approaches);\nBi-Encoders vs Cross-Encoders vs Late Interaction;\nLatent interaction models and HNSW search;\nContrastive learning\, triple loss\, Siamese networks;\nSpeed vs accuracy trade-offs;\nDomain-specific embedding tuning (e.g.\, code vs text);\nEvaluation with BEIR and MTEB benchmarks.\n\n\nSpeaker: Sandro Barnabishvili \nDate & Time: Saturday\, May 3\, 13:00 \nRegister Here: https://lu.ma/n16g786u \nLocation: Ilia State University\, T Building\, Auditorium #102
URL:https://events.iliauni.edu.ge/event/02-05-2025-tbilisiaimeetups/
CATEGORIES:Events
ATTACH;FMTTYPE=image/png:https://events.iliauni.edu.ge/wp-content/uploads/2025/05/AI-meetups_web_new_eng.png
END:VEVENT
END:VCALENDAR