arXiv Machine Learning June 11, 2026 By Philipp Hoellmer, Stefano Martiniani

Open Materials Generation with Inference-Time Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2602. 00424v2 Announce Type: replace Abstract: Continuous-time generative models for crystalline materials enable inverse materials design by learning to predict stable crystal structures, but incorporating explicit target properties into the generative process remains challenging.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv Machine Learning

Aug 10

CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction

arXiv:2608. 06582v1 Announce Type: new Abstract: Flow-based generative models can efficiently produce candidate structures for crystal structure prediction (CSP), but their pretrained objectives do not directly optimize downstream target recovery.

By Kaixiang Su, Hongfei Xue, Qiang Zhu

reinforcement-learning

arXiv AI

Jun 9

MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science

arXiv:2606. 07712v1 Announce Type: cross Abstract: Progress in AI-driven crystal materials science has so far been carried by narrow architectures purpose-built for individual tasks -- graph neural networks for property prediction, diffusion and flow-matching models for crystal generation -- each excelling within its niche yet unable to act as a shared backbone across the full spectrum of materials problems.

By Zhan'ao Yao, Boxuan Zhang, Jingyuan Shu, Xiaoyu Wu, Rongyan Wang, Linjing Li, Dajun Zeng, Yudong Yao, Tingwei Chen, Youwei Wang, Xiaolin Zhao, Jiahui Shi, Jianjun Liu

llms diffusion reinforcement-learning

arXiv Machine Learning

Jun 2

Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design

arXiv:2606. 02507v1 Announce Type: cross Abstract: Inverse materials design is shifting materials discovery from forward prediction to targeted proposal of candidates that satisfy objectives under physical constraints.

By Anand Babu, Rog\'erio Almeida Gouv\^ea, Gian-Marco Rignanese

diffusion reinforcement-learning multimodal

arXiv Machine Learning

2d ago

Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Prediction

arXiv:2609.39773v1 Announce Type: new Abstract: Crystal structure governs material properties, making crystal structure prediction (CSP) a fundamental problem in materials science. Generative models...

By Thomas Egg, Harry Winston Sullivan, Maya M. Martirossyan, Philipp H\"ollmer, Cheng Zeng, Adrian Roitberg, Mingjie Liu, Richard Hennig, Sapna Sarupria, Ellad B. Tadmor, Stefano Martiniani

reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 17

Adaptable Method for Crystal Design across Diverse Constraints and Objectives with Pretrained Property Predictors

arXiv:2410. 08562v5 Announce Type: replace-cross Abstract: Advanced crystal design can accelerate materials discovery across applications from photovoltaics to spintronics.

By Akihiro Fujii, Yoshitaka Ushiku, Koji Shimizu, Anh Khoa Augustin Lu, Satoshi Watanabe

arXiv Machine Learning

Sep 23

OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery

arXiv:2609.26402v1 Announce Type: new Abstract: The discovery of novel inorganic materials drives technological breakthroughs in critical fields such as computing and energy storage. Generative AI ha...

By Thomas Egg, Harry Winston Sullivan, Ellad B. Tadmor, Stefano Martiniani

diffusion fine-tuning efficiency benchmarks

One email a morning, machine-written

Related stories

CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction

MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science

Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design

Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure Prediction

Adaptable Method for Crystal Design across Diverse Constraints and Objectives with Pretrained Property Predictors

OMatG-flash: An All-Atom Flow Map with Reinforce Adjoint Matching for Scalable Materials Discovery