BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:AI Center Seminar - AI for Science series - Dr. Alex Tong
DTSTART:20260211T143000
DTEND:20260211T160000
DTSTAMP:20260428T153617Z
UID:9946ba8c85aaf010e04b2fd79df09e1f63869341bae2511080db4705
CATEGORIES:Conferences - Seminars
DESCRIPTION:Alex Tong\nThe talk is organized by the EPFL AI Center and 
 the EPFL Laboratory of Protein Design and Immunoengineering (LPDI) as part
  of the AI for Science seminar series.\n\nHosting professor: Prof. Bruno C
 orreia (LPDI)\n\nTitle\nControlling Generative Models\n\nAbstract\nGenerat
 ive modeling excels at mimicking data distributions\, but scientific disco
 very often requires sampling from a modified distribution. In this talk\, 
 I will motivate and present a framework for controlling flow models to con
 trol sampling on a distribution level. I will demonstrate how this approac
 h can be adapted to two distinct challenges in the natural sciences: (1) g
 uiding generation to control for multiple functional properties for design
 \, and (2) steering dynamics to sample from unnormalized energy densities 
 for equilibrium sampling. Together\, these methods illustrate the versatil
 ity of flows for both finding new\, optimized structures and exploring the
  physical landscapes of existing ones.\n\nBio\nAlexander Tong is a Princi
 pal Investigator at Aithyra in Vienna\, Austria. His research sits at the 
 intersection of machine learning and biology\, with a focus on generative 
 modeling\, flow matching\, and optimal transport. He applies these techniq
 ues to problems in protein design and cellular dynamics. Previously\, Alex
  was a postdoctoral researcher at Mila in Montreal\, where he worked with 
 Yoshua Bengio\, and he completed his PhD in Computer Science at Yale Unive
 rsity in 2021. He also co-founded Dreamfold\, a company focused on generat
 ive protein design.
LOCATION:ELE 117 https://plan.epfl.ch/?room==ELE%20117 https://epfl.zoom.u
 s/j/66703579322?pwd=Pl7r2XbUyRlVZVphBmms8W5KSMvB1K.1
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR