TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.20.1.004
TI  - Extrapolating jet radiation with autoregressive transformers
PY  - 2026/01/12
UR  - https://www.scipost.org/SciPostPhys.20.1.004
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 20
IS  - 1
SP  - 004
A1  - Butter, Anja
AU  - Charton, François
AU  - Mariño Villadamigo, Javier
AU  - Ore, Ayodele
AU  - Plehn, Tilman
AU  - Spinner, Jonas
AB  - Generative networks are an exciting tool for fast LHC event generation with fixed number of particles. Autoregressive transformers allow us to generate events containing variable numbers of particles, very much in line with the physics of QCD jet radiation, and offer the possibility to generalize to higher multiplicities. We show how transformers can learn a factorized likelihood for jet radiation and extrapolate in terms of the number of generated jets. For this extrapolation, bootstrapping training data and training with modifications of the likelihood loss can be used.
ER  -

@Article{10.21468/SciPostPhys.20.1.004,
	title={{Extrapolating jet radiation with autoregressive transformers}},
	author={Anja Butter and François Charton and Javier Mariño Villadamigo and Ayodele Ore and Tilman Plehn and Jonas Spinner},
	journal={SciPost Phys.},
	volume={20},
	pages={004},
	year={2026},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.20.1.004},
	url={https://scipost.org/10.21468/SciPostPhys.20.1.004},
}