A naukri.com initiative
Arxiv
2M
105
Image Credit: Arxiv
Flow Matching Beyond Kinematics: Generating Jets with Particle-ID and Trajectory Displacement Information
- Researchers have introduced a generative model trained on the JetClass dataset.
- The model generates jets at the constituent level and is a permutation-equivariant continuous normalizing flow (CNF) trained with flow matching technique.
- The model can generate ten different jet types by being conditioned on the jet type.
- The generative model goes beyond the kinematic features and includes additional features such as particle-ID and track impact parameter.
Read Full Article
6 Likes
For uninterrupted reading, download the app