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:20260421T090515Z
LOCATION:Bldg. 6 - Room 002
DTSTART;TZID=Europe/Stockholm:20260630T144500
DTEND;TZID=Europe/Stockholm:20260630T151500
UID:submissions.pasc-conference.org_PASC26_sess141_msa167@linklings.com
SUMMARY:Chemical Sciences in the Age of LLMs
DESCRIPTION:Philippe Schwaller (EPFL)\n\nChemistry faces a fundamental cha
 llenge: the space of possible molecules and materials is nearly infinite, 
 yet discovering useful new ones requires navigating costly cycles of desig
 n, synthesis, and testing. In this talk, I will show how language models —
  the same technology behind modern AI assistants — can be adapted to "spea
 k" the language of chemistry and dramatically accelerate this discovery pr
 ocess. We explore how small, specialized models can learn to propose novel
  molecules atom by atom, while respecting real-world constraints like avai
 lable building blocks and preferred chemical reactions. We then turn to la
 rge language models and show how they can reason about chemistry, plan syn
 thetic routes, and even assess whether a proposed synthesis is practically
  feasible. Finally, we present a general framework that uses language mode
 l representations to efficiently guide experimental optimization across di
 verse scientific domains — from drug discovery to materials science — with
  minimal data. Together, these advances illustrate how AI and chemistry ar
 e converging to help scientists explore chemical space faster and more cre
 atively than ever before.\n\nDomain: Chemistry and Materials, Computationa
 l Methods and Applied Mathematics\n\nSession Chairs: Mattia Turchi (Empa) 
 and Ivan Lunati (Empa)\n\n
END:VEVENT
END:VCALENDAR
