LaMM pre-trains neural network potentials on about 300 million mixed labeled and unlabeled structures using denoising pseudo-forces and a load-balanced multi-GPU pipeline, improving HME21 fine-tuning accuracy and speed.
Equiformerv2: Improved equivariant transformer for scaling to higher- degree representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
LaMM: Semi-Supervised Pre-Training of Large-Scale Materials Models
LaMM pre-trains neural network potentials on about 300 million mixed labeled and unlabeled structures using denoising pseudo-forces and a load-balanced multi-GPU pipeline, improving HME21 fine-tuning accuracy and speed.