arXiv Machine Learning
Jul 24
Boltzmann generators for amorphous particle systems
arXiv:2512. 16607v2 Announce Type: replace-cross Abstract: Sampling configurations in thermodynamic equilibrium is a long-standing challenge in statistical physics.
ATLAS: A Foundation Neural Sampler for Amorphous Materials
arXiv:2607. 19198v1 Announce Type: cross Abstract: Amorphous materials exhibit exceptional mechanical and functional properties, yet their rugged energy landscapes are notoriously difficult to sample.
Related stories
arXiv AI
Jun 3
Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation
arXiv:2604. 13354v2 Announce Type: replace-cross Abstract: The discovery of inorganic crystal structures with targeted properties is a significant challenge in materials science.
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.
arXiv Machine Learning
Jun 24
Scalable Physics-Inspired Transformers for Spin Glasses
arXiv:2606. 22984v2 Announce Type: replace-cross Abstract: Efficient sampling of the Boltzmann distribution in frustrated spin glasses is central to statistical mechanics and combinatorial optimization.
arXiv Machine Learning
Aug 4
Tunneling the Loss Landscape: Bypassing Memorization with Monte Carlo Parameter Swapping
arXiv:2608. 01833v1 Announce Type: cross Abstract: Grokking is a striking phenomenon in neural network training, where a model can undergo a prolonged period of pure memorization before abrupt generalization.
arXiv Machine Learning
Jun 11
Open Materials Generation with Inference-Time Reinforcement 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.
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.
arXiv Machine Learning
Jun 2
Latent Diffusion Pretraining for Crystal Property Prediction
arXiv:2606. 00776v1 Announce Type: new Abstract: Fast and accurate prediction of crystal properties is a central challenge in new materials design.
arXiv Machine Learning
Jul 7
AquaGen: Scaling generative models to molecular dynamics precision on thousands of atoms
arXiv:2607. 03513v1 Announce Type: cross Abstract: We present AquaGen, the first all-atom, explicit solvent, periodic-boundary-condition-aware generative model that produces molecular configurations from the Boltzmann distribution at a fraction of the cost of molecular dynamics (MD).
arXiv Machine Learning
Jun 4
SPLIT-PINN: Separable Probability Learning Technique via Physics-Informed Neural Networks for High-Dimensional Probabilistic Modeling
arXiv:2606. 04000v1 Announce Type: cross Abstract: We present a probabilistic modeling framework for incorporating small-scale spatial heterogeneity into macroscopic descriptions of material behavior for polycrystalline metallic materials.
arXiv Machine Learning
Aug 11
From Independent to Correlated Diffusion: Generalized Generative Modeling with Probabilistic Computers
arXiv:2603. 27996v2 Announce Type: replace Abstract: Diffusion models have emerged as a powerful framework for generative tasks in deep learning.
arXiv Machine Learning
Jul 30
Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
arXiv:2607. 27077v1 Announce Type: new Abstract: Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability.