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.
arXiv preprint arXiv:2512.04562 (2025)
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
A joint diffusion framework for crystal structures and local electronic descriptors improves inverse materials design success rates and structural quality over structure-only models under band-gap and formation-energy conditioning.
81-92% of chemically valid and metastable crystals from generative models are training duplicates or substitution-derived, with low-symmetry cases showing interpolation and high-symmetry cases showing memorization.
MatMind is a unified LLM-based generative model for crystals that reports lowest MAE on energy above hull, bulk modulus and band gap while achieving 65.3% S.U.N. rate on unconditional generation.
FMwC computes per-sample confidence scores for flow matching models via closed-form propagation of input-dependent multiplicative noise variance along the sampling ODE, supporting filtering, editing, and adaptive stepping.
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.
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.
-
Inverse Materials Design via Joint Generation of Crystal Structures and Local Electronic Descriptors
A joint diffusion framework for crystal structures and local electronic descriptors improves inverse materials design success rates and structural quality over structure-only models under band-gap and formation-energy conditioning.
-
Substitution-Based Analysis of Structural Novelty for Generative Models of Materials
81-92% of chemically valid and metastable crystals from generative models are training duplicates or substitution-derived, with low-symmetry cases showing interpolation and high-symmetry cases showing memorization.
-
MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science
MatMind is a unified LLM-based generative model for crystals that reports lowest MAE on energy above hull, bulk modulus and band gap while achieving 65.3% S.U.N. rate on unconditional generation.
-
Flowing with Confidence
FMwC computes per-sample confidence scores for flow matching models via closed-form propagation of input-dependent multiplicative noise variance along the sampling ODE, supporting filtering, editing, and adaptive stepping.
-
PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.
- Inverse Design of Inorganic Compounds with Generative AI