LGA employs latent-space interpolation from universal interatomic potentials for crossover in crystal structure prediction, raising HfO2 ground-state recovery to 60-95% and identifying unreported periodic structures in perovskite superlattices.
Univer- sally converging representations of matter across scientific foundation models
4 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
4
Pith papers citing it
3
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
AI weather models may simulate the atmosphere via particle positions in latent space whose updates follow gradient flow on a learned free energy functional rather than conventional physical equations.
Different uMLIPs encode chemical space in distinct ways, with high cross-model feature reconstruction errors, and fine-tuning preserves strong pre-training bias in the latent features.
This perspective article develops a definition of foundational MLIPs and poses six open questions that the authors believe will define future research in machine-learned interatomic potentials.
citing papers explorer
-
Latent Genetic Algorithm for Crystal Structure Prediction
LGA employs latent-space interpolation from universal interatomic potentials for crossover in crystal structure prediction, raising HfO2 ground-state recovery to 60-95% and identifying unreported periodic structures in perovskite superlattices.
-
The physics of AI weather models
AI weather models may simulate the atmosphere via particle positions in latent space whose updates follow gradient flow on a learned free energy functional rather than conventional physical equations.
-
Comparing the latent features of universal machine-learning interatomic potentials
Different uMLIPs encode chemical space in distinct ways, with high cross-model feature reconstruction errors, and fine-tuning preserves strong pre-training bias in the latent features.
-
Six Open Questions in Machine-Learned Interatomic Potential Foundation Models
This perspective article develops a definition of foundational MLIPs and poses six open questions that the authors believe will define future research in machine-learned interatomic potentials.