mlsanityData to 7 Oct 2026

Chemical filters for ultra-high-throughput materials screening and generation

arXiv 2607.17910 ↗First posted 20 Jul 2026cond-mat.mtrl-sci cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative artificial intelligence is rapidly transforming materials design by enabling de novo exploration of immense chemical spaces. Yet a large proportion of AI-generated compositions remain implausible, violating established chemical principles, which limits the reliability and interpretability of generative materials design. Here, we introduce a chemical validity operator that recasts heuristic chemical rules as a configurable algorithmic prior for evaluating and guiding generative materials discovery. Built on the open-source SMACT package, a data-informed oxidation-state model exposes tunable thresholds, allowing users to interpolate continuously between permissive and conservative chemical constraints, while supporting both exploratory and conservative materials-design workflows. Benchmarking six state-of-the-art generative models for inorganic crystals shows that most reproduce stoichiometry but under-represent realistic oxidation-state combinations, and that filtering removes compositions reliant on rarely observed oxidation states while preserving low-energy compounds near the convex hull. Beyond screening, the same operator can also serve as a reinforcement-learning reward, steering a latent diffusion model towards chemically grounded compositions. By encoding chemical heuristics and observations, this work establishes a foundation for oxidation-state-aware generative models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 20 Jul 2026.

Builds on

12 of 33 references.

References · 12

  1. 2020Denoising Diffusion Implicit Modelscited by 9,655
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 268
  4. 2023Crystal Structure Prediction by Joint Equivariant Diffusioncited by 142
  5. 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materialscited by 75
  6. 2024Space Group Constrained Crystal Generationcited by 71
  7. 2022Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraintscited by 30
  8. 2025LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Modelscited by 20
  9. 2025Guiding Generative Models to Uncover Diverse and Novel Crystals via Reinforcement Learningcited by 19
  10. 2025Artificial Intelligence and Generative Models for Materials Discovery -- A Reviewcited by 8
  11. 2025Enhancing Materials Discovery with Valence Constrained Design in Generative Modelingcited by 2
  12. 2025Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spacescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Establishing baselines for generative discovery of inorganic crystals
  2. 2026OxiGen: Oxidation-State-Aware Crystal Generation
  3. 2026Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design
  4. 2025Introducing physics-informed generative models for targeting structural novelty in the exploration of chemical space
  5. 2024Unleashing the power of novel conditional generative approaches for new materials discovery
  6. 2026Reinforcement Learning on the Discrete Composition Channel of a Crystal Generator: Validated Gains and Reward Hacking
  7. 2026Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation
  8. 2025Autonomous Inorganic Materials Discovery via Multi-Agent Physics-Aware Scientific Reasoning