20–31 Oct 2025
University of Tokyo
Asia/Tokyo timezone

Conditional Generation of LArTPC Images Using Latent Diffusion

30 Oct 2025, 09:35
25m
Koshiba Hall (University of Tokyo)

Koshiba Hall

University of Tokyo

7-3 Hongo, Bunkyo City, Tokyo 113-0033
Long talk (25min. + 10min. Q/A) Foundation Models

Speaker

Zev Imani

Description

Given the challenges in LArTPC event reconstruction, we have taken the first steps towards creating an end-to-end inference pipeline to go from 2D images to event properties. Inspired by the success of denoising diffusion probabilistic models (DDPMs), we have developed a method of conditionally generating 2D LArTPC images. By utilizing a modified latent diffusion model, we have demonstrated the ability to generate single-particle events of a specified momentum with quality comparable to traditional Geant4 simulations.

Presentation materials

There are no materials yet.