English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The diffusion model has demonstrated promising results in image generation,recently becoming mainstream and representing a notable advancement for manygenerative modeling tasks. Prior applications of the diffusion model for bothfast event and detector simulation in high energy physics have shownexceptional performance, providing a viable solution to generate sufficientstatistics within a constrained computational budget in preparation for theHigh Luminosity LHC. However, many of these applications suffer from slowgeneration with large sampling steps and face challenges in finding the optimalbalance between sample quality and speed. The study focuses on the latestbenchmark developments in efficient ODE/SDE-based samplers, schedulers, andfast convergence training techniques. We test on the public CaloChallenge andJetNet datasets with the designs implemented on the existing architecture, theperformance of the generated classes surpass previous models, achievingsignificant speedup via various evaluation metrics.

Choose Your Diffusion: Efficient and flexible ways to accelerate the diffusion model in fast high energy physics simulation