BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Generative Ai.rplane - Thomas Gessey-Jones (physicsx.ai)
DTSTART:20250130T140000Z
DTEND:20250130T150000Z
UID:TALK224998@talks.cam.ac.uk
CONTACT:Sri Aitken
DESCRIPTION:Many scientific and engineering problems are fundamentally lin
 ked to geometry\, for example\, designing a part to maximise strength or m
 odelling fluid flow around an airplane wing. Thus\, there is substantial i
 nterest in developing machine learning models that can not only operate on
  or output geometric data\, but generate new geometries. Such models have 
 the potential to revolutionise advanced industries from materials manufact
 uring to medical imaging. However\, constructing and training these models
  presents a range of novel challenges. In this talk\, we will discuss Ai.r
 plane\, a generative geometry model for aircraft from PhysicsX\, using it 
 as a case study to illustrate some of these challenges and the approaches 
 taken to tackle them. Among other topics\, we shall consider how to encode
  geometry for ML\, the difficulties of dataset curation\, the advantages o
 f geometric foundation models\, and how to predict scalar and field proper
 ties of these geometries. For a sneak peek\, you can explore the Ai.rplane
  model yourself already at https://airplane.physicsx.ai\, and design your 
 own aircraft in seconds.
LOCATION:East 1\, West Hub
END:VEVENT
END:VCALENDAR