EveNet
An event-level model that mixes self-supervised learning with physics labels; its authors use it to rediscover the Upsilon meson in CMS open data.
- Made by
- Ting-Hsiang Hsu, Bai-Hong Zhou, Qibin Liu and others
- Field
- Collider physics
- Learns from
- 500 million simulated collision events
- Size
- Not stated
- Open weights
- Not stated
- First public
- Jan 2026
- Source
- arxiv.org/abs/2601.17126
How it relates to Flare
The closest earlier model to what CERN describes: pretrained on whole simulated events rather than single jets.
Every figure here is from the source above, checked 17 October 2026. Something changed? Email [email protected].