CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction
cs.LG
Submitted: 2026-08-06
Updated: 2026-08-30
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Training Diffusion Models with Reinforcement Learning
- Space Group Constrained Crystal Generation
- WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry
- Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control
- A Periodic Bayesian Flow for Material Generation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks