BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Using AI to Code Downstream Tasks for a Remote Sensing Foundation 
 Model - Srinivasan Keshav\, University of Cambridge
DTSTART:20251017T120000Z
DTEND:20251017T130000Z
UID:TALK239350@talks.cam.ac.uk
CONTACT:114742
DESCRIPTION:*Abstract*\n\nFoundation models allow the rapid evaluation of 
 downstream tasks with task-specific training. In recent months\, it has be
 come increasingly possible to use off-the-shelf coding AIs to write even m
 oderately complex code. In this talk\, I will discuss my use of Claude cod
 e and the Tessera foundation model for evaluating the above ground biomass
  in an urban reforestation project\, highlighting areas where AI worked we
 ll\, and where it still falls short. \n\n*Bio*\n\nSrinivasan Keshav is the
  Robert Sansom Professor of Computer Science at the University of Cambridg
 e\, focusing on the intersection of computer science and sustainability. H
 e earned his PhD from UC Berkeley and has held roles at Bell Labs\, Cornel
 l University\, and the University of Waterloo. A Fellow of the Royal Socie
 ty of Canada\, ACM\, and IEEE\, Keshav is recognized for his contributions
  to networking and sustainability. His research includes innovations in en
 ergy systems\, carbon footprint reduction\, and forest conservation using 
 remote sensing. Keshav emphasizes practical applications of computer scien
 ce to global challenges\, fostering collaborative solutions in smart grids
  and biodiversity conservation.\n
LOCATION:Room GS15 at the William Gates Building and on Zoom: https://cl-c
 am-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&amp\;fr
 om=addon 
END:VEVENT
END:VCALENDAR