A lightweight autoencoder pre-trained on LHC track data transfers to collider and out-of-domain scientific tasks, matching a transformer within ~2% at about 46x lower per-epoch training cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Lightweight Foundation Model for Collider Physics with Multi-Domain Adaptation
A lightweight autoencoder pre-trained on LHC track data transfers to collider and out-of-domain scientific tasks, matching a transformer within ~2% at about 46x lower per-epoch training cost.