A Gaussian process surrogate gate inserted between generative crystal models and property oracles matches or exceeds ungated fine-tuning while using roughly one-fifth the oracle calls for heat capacity and bulk modulus.
Advances in Neural Information Processing Systems (NeurIPS) , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
bispectrum library delivers selective G-bispectra for seven groups with reduced costs (O(|G|) for finite groups, O(L^2) for spheres), sub-millisecond GPU times, and superior benchmark performance versus standard pooling in low-data regimes.
citing papers explorer
-
Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Design
A Gaussian process surrogate gate inserted between generative crystal models and property oracles matches or exceeds ungated fine-tuning while using roughly one-fifth the oracle calls for heat capacity and bulk modulus.
-
bispectrum: Selective $G$-Bispectra Made Practical
bispectrum library delivers selective G-bispectra for seven groups with reduced costs (O(|G|) for finite groups, O(L^2) for spheres), sub-millisecond GPU times, and superior benchmark performance versus standard pooling in low-data regimes.