BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:"Machine learning in chemistry and beyond" (ChE-605) seminar by Dr
 . Wenhao Gao: Navigating synthesizable chemical space with generative AI
DTSTART:20251028T170000
DTEND:20251028T180000
DTSTAMP:20260925T060309Z
UID:42239387f37ce7c5814b0107ac3464f47f3620ccd6a2f4efbaaf3b9b
CATEGORIES:Conferences - Seminars
DESCRIPTION:Wenhao Gao is an incoming Assistant Professor in Chemical and 
 Biomolecular Engineering at the University of Pennsylvania. He is currentl
 y a postdoctoral researcher at Stanford University with Prof. Grant Rotsko
 ff and Stefano Ermon. Wenhao received his Ph.D. from MIT\, where he was ad
 vised by Prof. Connor W. Coley. His research focuses on developing artific
 ial intelligence methods that integrate chemical and physical principles t
 o enable systematic and scalable molecular discovery for applications in d
 rug design and sustainable materials. He has been recognized with numerous
  honors\, including the Google PhD Fellowship\, Takeda Fellowship\, D. E. 
 Shaw Research Fellowship\, CAS Future Leaders recognition\, and Forbes 30 
 Under 30 Asia in Healthcare and Science.\nThe discovery of functional mole
 cules plays a fundamental role in advancing chemical science and engineeri
 ng\, yet it remains a costly and time-intensive process. Recent advances i
 n computational methods\, particularly in generative artificial intelligen
 ce\, have introduced a new approach\, generative molecular design\, which 
 holds the promise of efficiently identifying molecules with desired proper
 ties. However\, despite significant progress\, their practical impact in r
 eal-world applications has been limited. In this talk\, I will present our
  efforts to address critical bottlenecks in generative molecular design\, 
 namely synthetic accessibility and sample efficiency. I will present the d
 evelopment of benchmarks that capture real-world complexity and the develo
 pment of chemistry-tailored solutions to enhance the practicality of gener
 ative algorithms. Taken together\, these advances aim to close the gap bet
 ween computational innovation and practical feasibility\, paving the way f
 or the accelerated\, AI-driven discovery of novel functional molecules.
LOCATION:https://epfl.zoom.us/j/68447908297?pwd=OU5JUGJUSUhZc0ZNYjQ2WENvYI
 NRdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR