BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Darpass - Your pass to Tech Armenia - ECPv6.15.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://darpass.com
X-WR-CALDESC:Events for Darpass - Your pass to Tech Armenia
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:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Dubai:20241219T183000
DTEND;TZID=Asia/Dubai:20241219T210000
DTSTAMP:20260501T182128
CREATED:20241126T115338Z
LAST-MODIFIED:20241126T115338Z
UID:3409-1734633000-1734642000@darpass.com
SUMMARY:ML OpenTalk December 2024
DESCRIPTION:YandexHall  and YerevaNN are excited to present ML OpenTalk December 2024 – Erik Arakelyan’s talk on “How to Reason Robustly\, Verifiably\, and Faithfully with LLMs.” \nDecember 19\, 7:00 PM\nYandexHall\, Moskovyan 35\, Yerevan\nRegister here to secure your spot\, link in the event.\nStay updated with YandexHall events:\nTelegram: https://t.me/yandex_hall \nSpeaker: Erik Arakelyan\, [LinkedIn](https://www.linkedin.com/in/erik-arakelyan-a6a84470/)\, [Google Scholar](https://scholar.google.it/citations?hl=en&user=63BfrxMAAAAJ)\nAbout Erik\nErik Arakelyan is a Machine Learning researcher doing a Ph.D. at the University of Copenhagen (UCPH)\, specializing in topics of Neuro-symbolic AI\, query answering over Knowledge Graphs\, Large Language Models\, and Explainability in NLP. Erik was a visiting researcher at Amazon working on grounded LLM reasoning and knowledge-based completion at Alexa AI and Amazon AGI. Creating scalable pipelines for experimentation and inference over KGs and researching multi-hop reasoning with retrieval-based augmentation over LLMs. \nAbout the talk\nDuring the talk\, Erik will explain ways to improve large language models (LLMs)’ reasoning\, or “thinking\,” through problems to give accurate answers.\nWe’ll focus on key areas: \n\n ensuring models are faithful (sticking closely to facts)\,\n verifiable (answers can be checked)\, and\n logical (making sense).\n\nStarting with what we mean by “reasoning” for LLMs\, we’ll look at how to train and guide models to make smart\, context-aware responses.\nAgenda\n6:30 PM Registration\n7:00 PM Talk and Q&A\n8:15 PM – 8:45 PM Networking \n  \nYou can find more tech events happening in Armenia here
URL:https://darpass.com/event/ml-opentalk-december-2024/
LOCATION:Yandex Hall\, 35 Moskovyan Str.\, Yerevan\, Armenia
CATEGORIES:Tech Events In Armenia
ATTACH;FMTTYPE=image/jpeg:https://darpass.com/wp-content/uploads/2024/11/ML-OpenTalk-December-2024.jpg
END:VEVENT
END:VCALENDAR