BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230831T095754Z
LOCATION:Sanada I
DTSTART;TZID=Europe/Stockholm:20230626T163000
DTEND;TZID=Europe/Stockholm:20230626T183000
UID:submissions.pasc-conference.org_PASC23_sess120@linklings.com
SUMMARY:MS2G - Large Language Models for Autonomous Discovery
DESCRIPTION:Minisymposium\n\nThis minisymposium brings together a communit
 y of scientific researchers to discuss how advances in high-performance co
 mputing (HPC) and large language models (LLMs) can accelerate scientific d
 iscovery, particularly in biological domains. LLMs have recently demonstra
 ted powerful expressivity in domains outside of natural languages, such as
  protein-sequence models, gene-sequence modeling, and drug design. However
 , applying LLMs to scientific domains presents numerous challenges, includ
 ing the need for large-scale HPC resources, new methods for probing our un
 derstanding of models, and techniques to ground the output of LLMs in scie
 ntific literature and theory. Confirmed speakers include Professor Connor 
 Cooley (MIT), Professor Ellen Zhong (Princeton), and Professor Burkhard Ro
 st (Technical University at Munich), who will present their research on th
 e application of LLMs to a broad range of scientific disciplines. Through 
 discussing both the domain and computational advances alongside current ob
 stacles, the symposium aims to develop a clear research agenda forward for
  incorporating LLMs into scientific discovery.\n\nProtein Language Models 
 for Mapping Structure-Function Relationships\n\nThe Rostlab aims to use ev
 olutionary information (EI) combined with machine learning (ML) and artifi
 cial intelligence (AI) to predict aspects of protein function and structur
 e from sequence. The use of EI and ML allowed a breakthrough in secondary 
 structure prediction 30 years ago, and it has been t...\n\n\nBurkhard Rost
  (Technical University of Munich)\n---------------------\nGroup Discussion
 : How Large Language Models Will Influence Autonomous Discovery\n\nThis wi
 ll be the summary discussion at the end of the minisymposium to stimulate 
 discussions on how large language models and foundation models will influe
 nce our thinking into the future of experimental design.\n\n\nArvind Raman
 athan (Argonne National Laboratory, University of Chicago)\n--------------
 -------\nTransforming Chemistry: The Impact of Large Language Models on Ch
 emical Research\n\nThis talk investigates the transformative role of large
  language models (LLMs) in chemistry, focusing on how those models help us
  consolidate, incorporate context, and reduce barriers. We will discuss ho
 w LLMs challenge the common understanding of "no free lunch" theorems by s
 olving diverse tasks, r...\n\n\nKevin Jablonka (EPFL)\n-------------------
 --\nUsing In-Context Learning and Frozen Large Language Models for Bayesia
 n Optimization of Catalysts\n\nLarge Language Models (LLM) are advanced ar
 tificial intelligence (AI) systems capable of understanding and generating
  human-like text. In this study, we demonstrate how in-context learning wi
 th frozen LLMs can predict chemical properties directly from experimental 
 procedures. We developed a promptin...\n\n\nMayk Caldas Ramos, Shane Micht
 avy, Marc Porosoff, and Andrew White (University of Rochester)\n\nDomain: 
 Life Sciences\n\nSession Chair: Arvind Ramanathan (Argonne National Labora
 tory, University of Chicago)
END:VEVENT
END:VCALENDAR