BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Image Restoration without Clean Data\, RL for Particle Physics - T
 roy Vu\; Yong Sheng Koay 
DTSTART:20251111T153000Z
DTEND:20251111T163000Z
UID:TALK240772@talks.cam.ac.uk
CONTACT:Rachel Zhang
DESCRIPTION:Topic 1: Noise2Noise: Learning Image Restoration without Clean
  Data\nOverview: A simple and powerful conclusion: it is possible to learn
  to restore images by only looking at corrupted examples\, at performance 
 at and sometimes exceeding training using clean data\, without explicit im
 age priors or likelihood models of the corruption.\n\nTopic 2: RL + Theore
 tical Particle Physics: Building Theories is Like Playing Chess\nOverview:
  I will discuss a broad overview of how reinforcement learning is being us
 ed to design new theories in particle physics\, targeting open questions t
 hat the Standard Model cannot fully explain.\n\nPapers that will be discus
 sed/mentioned:\n\n- Quark Mass Models and Reinforcement Learning [2103.047
 59] \n- Exploring the flavor structure of quarks and leptons with reinforc
 ement learning [2304.14176] \n- Reinforcement learning-based statistical s
 earch strategy for an axion model from flavor [2409.10023] \n- Towards Bey
 ond Standard Model Model-Building with Reinforcement Learning on Graphs [2
 407.07184\, 2407.07203] \n- Towards AI-assisted Neutrino Flavor Theory Des
 ign [2506.08080]\n\nIt is not necessary to read the above literature befor
 e the session!
LOCATION:MR4\, Centre for Mathematical Sciences\, Wilberforce Rd\, Cambrid
 ge CB3 0WA
END:VEVENT
END:VCALENDAR