Let CSP Be Your ANCHOR: Adaptive Crystal Search over Frozen Structure Priors
cond-mat.mtrl-sci, cs.LG, physics.comp-ph
Submitted: 2026-09-27
Updated: 2026-09-30
Terminology
Sources
- Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
- LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
- Exploration by Random Network Distillation
- Accelerating inverse materials design using generative diffusion models with reinforcement learning
- Kinetic Langevin Diffusion for Crystalline Materials Generation
- Open Materials Generation with Inference-Time Reinforcement Learning
- Open Materials Generation with Stochastic Interpolants
- Composable Crystals: Controllable Materials Discovery via Concept Learning
- FlowMM: Generating Materials with Riemannian Flow Matching
- General-purpose LLMs as Constrained Crystal Composition Generators
- Episodic Curiosity through Reachability
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LeMat-Bulk: aggregating, and de-duplicating quantum chemistry materials databases
- Score-Based Generative Modeling through Stochastic Differential Equations
- Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control
- Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
- Crystal Diffusion Variational Autoencoder for Periodic Material Generation
- MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
- CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models
Related papers
- Mode-selective electron-phonon coupling drives charge density waves in the kagome metals YRu 3 Si 2 and LaRu 3 Si 2
- Restoring the Surface Magnetic Gap in MnBi 2 Te 4
- ATLAS: A Foundation Neural Sampler for Amorphous Materials
- A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics
- Nonlinear dynamics in magnonic Fabry-P' e rot resonators: Low-power neuron-like activation and transmission suppression
- AES-Debye: an Accurate, Efficient, and Scalable Engine for Debye Scattering Calculations