BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Roku: Beyond Generative AI: Achieving Complete Control in Synthesi
 sing Testing Data with Unreal Engine - Zukang Liao\, Software Engineer and
  former intern at Roku
DTSTART:20250217T130500Z
DTEND:20250217T135500Z
UID:TALK225763@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:Whilst generative AI has advanced significantly in recent year
 s\, when it comes to accountability and assurance of AI systems\, the chal
 lenge of achieving precise control in synthesizing testing data for algori
 thm development remains significant. This session will provide an exciting
  opportunity to uncover how thorough tests are done in the industry before
  we can deploy AI/CV algorithms in real-world applications! We will delve 
 into:\n\n•	Unreal Engine’s advanced capabilities for precise parameter
 ization and simulation of nuanced real-world scenarios\, such as subtle li
 ghting changes\, tree swaying\, and controlled object movements\, which en
 sures a higher degree of realism and reproducibility in testing environmen
 ts.\n\n•	Generation of testing videos tailored for IoT camera algorithms
 \, with a specific focus on motion detection\, motion zone suggestion\, an
 d event detection.\n\n•	Insights from testing - Understanding what tests
  reveal about the performance and reliability of algorithms\, enabling dev
 elopers to refine and optimize AI models for real-world challenges\n\nAlso
  in attendance will be members of Roku’s  Early Career Recruiting team t
 o discuss our current internship and graduate opportunities. \n\nAttendees
  can sign up via the below link:\nhttps://app.ripplematch.com/t/f93dba87\n
 \nSome catering will be provided following the talk
LOCATION:FW26\, William Gates Building
END:VEVENT
END:VCALENDAR