BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Human AI collaboration for science and engineering
DTSTART:20241107T100000
DTEND:20241107T110000
DTSTAMP:20260412T060350Z
UID:8c03ecd5836ebf84e237775a427f9f9890f388835d8f285f4f762591
CATEGORIES:Conferences - Seminars
DESCRIPTION:Masaki Adachi\, Doctoral Student\, Oxford\, UK\nAbstract\nPowe
 rful AI\, such as LLMs\, holds immense potential to enhance human capabili
 ties\, particularly in science and engineering. But how can we truly colla
 borate with AI? Unlike traditional tools such as simulations\, AI is more 
 adaptive and can interpret our intentions\, much like human colleagues. Th
 is makes alignment a unique and critical challenge for effective collabora
 tion. However\, achieving alignment faces deep mathematical and philosophi
 cal challenges. AI decisions can be unreliable in high-stakes applications
 \, requiring human oversight\, yet human feedback itself is often imperfec
 t. In this talk\, we explore approaches to understanding and addressing th
 ese challenges in both single- and multi-agent systems\, with a focus on a
 pplications in Bayesian optimization.\n\nBiography\nMasaki Adachi is a fin
 al-year PhD student in the Machine Learning Research Group at the Universi
 ty of Oxford\, under the supervision of Michael A. Osborne. He also serves
  as an assistant manager in the data science team at Toyota Motor Corporat
 ion. His research interests include Bayesian optimization\, Bayesian quadr
 ature\, preference learning\, social choice theory\, and materials discove
 ry.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR