Full
PoLAr-MAE masked-autoencoder pretrained on LArTPC (PILArNet) point clouds (masked point reconstruction + energy infilling): ViT-S encoder, MAE decoder, reconstruction heads. Use the encoder as a backbone / warm-start.
1import pimm
2model = pimm.from_pretrained("hf://deeplearnphysics/polar-mae-pretrain")
Repackaged from the original
PoLAr-MAE release checkpoints into the
pimm export format. Inherits the source repo license.
