← Back to all news
arXiv Machine Learning By Chengqian Zhang, Yucheng Jin, Duo Zhang, Tiejun Li, Han Wang

CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models

Read the original on arXiv Machine Learning →

CrystalREPA is a plug‑and‑play framework that aligns the atom‑wise hidden states of crystal generative encoders with frozen universal machine‑learning interatomic potential (MLIP) representations using an element‑aware contrastive objective. By doing so, it transfers stability‑aware atomistic priors to generative models with minimal training overhead and no extra inference cost, consistently improving thermodynamic stability, structural validity, and fidelity across multiple generative frameworks and benchmark datasets. The study also shows that an MLIP’s suitability as a teacher is better predicted by the distinguishability of its atom‑wise representation space than by its leaderboard accuracy, providing a practical, accuracy‑independent selection criterion. whyItMatters":"The approach demonstrates a practical method to enhance crystal generative models’ ability to produce stable, realistic structures by leveraging existing MLIP knowledge without incurring additional inference costs."

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.

Related stories

arXiv AI
Oct 19

CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation

CrystalReasoner (CrysReas) is an end‑to‑end large language model framework that generates crystal structures from natural language instructions by incorporating physical priors as thinking tokens—such as crystallographic symmetry, local coordination, and predicted properties—before producing atomic coordinates. It then uses reinforcement learning with a multi‑objective reward to enforce physical validity, chemical consistency, and thermodynamic stability, and includes task‑specific rewards for property‑conditioned generation. Empirical results show that CrysReas outperforms prior methods, triples the S.U.N. ratio, and adapts reasoning length with increasing atom counts.

By Yuyang Wu, Stefano Falletta, Delia McGrath, Sherry Yang
llmsdiffusionreinforcement-learningsafety
More like this →
arXiv Machine Learning
Sep 23

Deep Generative Crystal Structure Prediction: A Benchmark Study and a Controlled Test of Prototype Dependence

The study benchmarks 12 deep generative crystal structure prediction models against the template-based TCSP 2.0 on 180 test structures, finding that template retrieval achieves the highest top‑1 success (68.3%). Most generative predictions overlap with template substitutions, and removing entire stoichiometric prototype families from training reduces accuracy by 50‑78%, indicating strong prototype dependence. Only a small subset of predictions remain after such removal, suggesting limited genuine de‑novo capability.

By Lai Wei, Rongzhi Dong, Ying Feng, Madeline Miklos, Jianjun Hu
diffusionbenchmarks
More like this →
arXiv AI
Sep 30

Where Should Physics Enter a Molecular Crystal Generator?

The paper introduces CrystAF, an all‑atom crystal flow‑map generation model, and evaluates where physics should be incorporated into generative crystal structure models. By applying physics‑informed post‑training, the authors improve molecular validity and crystal packing without altering sampling speed, while inference‑time corrections further refine the structures. The study demonstrates that post‑training and inference‑time physics are complementary, and that the post‑training approach transfers to other generators such as Clari‑M and MolCrystalFlow.

By Haocheng Tang, Junmei Wang, Wengong Jin
safety
More like this →