Jet Generation

Jet generation in particle physics focuses on efficiently simulating the sprays of particles (jets) produced in high-energy collisions, crucial for analyzing experimental data and searching for new physics. Current research emphasizes developing fast and accurate generative models, employing architectures like deep sets, normalizing flows, generative adversarial networks (GANs), and transformer-based methods, often incorporating techniques like quantization-aware training for hardware acceleration. These advancements aim to significantly reduce the computational cost of simulations, enabling faster analysis of the massive datasets generated by experiments like the Large Hadron Collider and improving the sensitivity of new physics searches.