Machine-learned particle flow (MLPF)
Rebuilds the particles in a collision from raw tracks and calorimeter hits in one learned step, replacing hand-written particle-flow rules.
- Made by
- Joosep Pata, Farouk Mokhtar, Michael Kagan and others (CMS)
- Field
- Collider physics
- Learns from
- Simulated detector events
- Size
- Not stated
- Open weights
- Not stated
- First public
- Jan 2021
- Source
- arxiv.org/abs/2606.14373
How it relates to Flare
Proof inside CMS that one trained model can do a large share of reconstruction. A June 2026 paper argues MLPF already works as a foundation model.
Links
Every figure here is from the source above, checked 17 October 2026. Something changed? Email [email protected].