LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911375831334912 |
|---|---|
| author | Betala, Siddharth Gleason, Samuel P. Ramlaoui, Ali Xu, Andy Channing, Georgia Levy, Daniel Fourrier, Clémentine Kazeev, Nikita Joshi, Chaitanya K. Kaba, Sékou-Oumar Therrien, Félix Hernandez-Garcia, Alex Mercado, Rocío Krishnan, N. M. Anoop Duval, Alexandre |
| author_facet | Betala, Siddharth Gleason, Samuel P. Ramlaoui, Ali Xu, Andy Channing, Georgia Levy, Daniel Fourrier, Clémentine Kazeev, Nikita Joshi, Chaitanya K. Kaba, Sékou-Oumar Therrien, Félix Hernandez-Garcia, Alex Mercado, Rocío Krishnan, N. M. Anoop Duval, Alexandre |
| contents | Generative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented exploration of chemical space. Yet, the lack of standardized evaluation frameworks makes it challenging to evaluate, compare, and further develop these ML models meaningfully. In this work, we introduce LeMat-GenBench, a unified benchmark for generative models of crystalline materials, supported by a set of evaluation metrics designed to better inform model development and downstream applications. We release both an open-source evaluation suite and a public leaderboard on Hugging Face, and benchmark 12 recent generative models. Results reveal that an increase in stability leads to a decrease in novelty and diversity on average, with no model excelling across all dimensions. Altogether, LeMat-GenBench establishes a reproducible and extensible foundation for fair model comparison and aims to guide the development of more reliable, discovery-oriented generative models for crystalline materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04562 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models Betala, Siddharth Gleason, Samuel P. Ramlaoui, Ali Xu, Andy Channing, Georgia Levy, Daniel Fourrier, Clémentine Kazeev, Nikita Joshi, Chaitanya K. Kaba, Sékou-Oumar Therrien, Félix Hernandez-Garcia, Alex Mercado, Rocío Krishnan, N. M. Anoop Duval, Alexandre Machine Learning Generative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented exploration of chemical space. Yet, the lack of standardized evaluation frameworks makes it challenging to evaluate, compare, and further develop these ML models meaningfully. In this work, we introduce LeMat-GenBench, a unified benchmark for generative models of crystalline materials, supported by a set of evaluation metrics designed to better inform model development and downstream applications. We release both an open-source evaluation suite and a public leaderboard on Hugging Face, and benchmark 12 recent generative models. Results reveal that an increase in stability leads to a decrease in novelty and diversity on average, with no model excelling across all dimensions. Altogether, LeMat-GenBench establishes a reproducible and extensible foundation for fair model comparison and aims to guide the development of more reliable, discovery-oriented generative models for crystalline materials. |
| title | LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.04562 |