# Sittipon Kumda

- Institution: CERN
- Department: Summer Student Lecture Programme General
- Speaker: Sittipon Kumda
- Year: 2025
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3023157)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

## Secondary Vertex Reconstruction with Maskformer The High-Luminosity Large Hadron Collider will generate data in a challenging high pile-up environment, making the reconstruction of secondary vertices, crucial for identifying heavy-flavor quarks and searching for new physics, extremely difficult. This project addresses this by developing an end-to-end machine learning pipeline using the MaskFormer architecture. The core contribution was creating a highly efficient data conversion module to transform `.root` physics data into the ML-friendly `.h5` format. Following this foundational step, the project involves training the model and analyzing its results to ensure physics-accurate predictions. Further enhancements will be explored through advanced techniques such as hyper-parameter tuning, pre-training strategies, and post-training optimizations to maximize the model's performance and scientific potential..

0:00:00 Slide 1

0:02:18 Slide 2

0:03:54 Slide 3

0:05:10 Slide 4

0:06:50 Slide 5

0:07:52 Slide 6

0:09:44 Slide 7

0:13:34 Slide 8

## Lectures

1. [Sittipon Kumda](https://invisiblenetwork.ai/learn/cern/3023157/2de6ae750d5e), 15 min (CERN's player)