AtomWorld-Mem is a memory‑restored atomistic world model that reconstructs hidden world states from incomplete crystal snapshots, enabling more accurate long‑horizon atomistic evolution. It uses spatial encoders to capture multi‑scale keyframes and integrates short‑term event memory with long‑term structural memory to predict future states. The restored state guides vacancy‑mediated events in kinetic Monte Carlo simulations, improving progress under fixed event budgets while preserving fidelity across energetic, structural, and transport observables, and it transfers zero‑shot across unseen alloy‑temperature scenarios.
By Tian Luo, Ruge Zhang, Haozhi Han, Yifrng Chen, Yunquan Zhang, Yunxin Liu, Ting Cao, Kun Li
AtomWorld-Mirror is a time‑aware macro‑step world model that compresses short micro‑event segments into physically reachable transitions between key atomic states, predicting sparse structural edits and accumulated physical time through latent macro‑step dynamics. By enforcing local reachability, inventory conservation, and continuous‑time consistency, the model replaces explicit micro‑event replay with macro‑step inference, enabling substantially faster long‑term materials evolution simulations. Across five atomic systems—including Cu‑rich RPV steel irradiation aging, Cu‑Zr metallic glass, and Li₃N‑based anti‑perovskite solid electrolyte—the approach achieves speed‑ups of 10³ to 10⁴ times over traditional event‑by‑event simulation.
By Ziming Pan, Ruge Zhang, Haozhi Han, Junkai Zhou, Xingyuan Chen, Yifeng Chen, Yunquan Zhang, Ting Cao, Yunxin Liu, Kun Li
AtomWorld-Mirror introduces a time‑aware macro‑step world model that condenses short micro‑event segments into physically reachable transitions between key atomic states. By predicting sparse structural edits and accumulated physical time through latent macro‑step dynamics, it replaces explicit micro‑event replay with efficient macro‑step inference. Experiments on five atomic systems—including Cu‑rich RPV steel, Cu‑Zr metallic glass, and Li₃N‑based solid electrolytes—show speedups of 10³ to 10⁴ times over traditional event‑by‑event simulation while maintaining structural validity and time semantics.
arXiv:2608. 14076v1 Announce Type: cross Abstract: Transition-state (TS) structures define the energetic barriers and mechanistic pathways of elementary chemical reactions, yet their identification remains computationally demanding because conventional saddle-point searches require expensive quantum-mechanical calculations.
By Kaipeng Zeng, Wenxi Zhai, Shengrui Xu, Jie Zhao, Bowen Li, Shiyue Wang, Junchi Yan, Tong Zhu
The paper introduces OrbFlow, an SE(3)-equivariant generative model that predicts Gaussian-type orbital coefficients for electron density using flow matching. By training with a two-phase trajectory curriculum, OrbFlow improves accuracy on QM9 and MD benchmarks, reducing density errors significantly compared to previous models. The predicted densities also accelerate self-consistent field procedures, cutting iterations by up to 68% and accurately reproducing dipole and quadrupole moments without additional SCF calculations.
By Chenxing Liang, Chengdong Wang, Yuchao Lin, Xiaofeng Qian, Shuiwang Ji
arXiv:2606. 03199v1 Announce Type: new Abstract: Organic crystal structure prediction (CSP) is a requirement for computational modelling of organic solids, but traditionally costs several CPU-years per molecule.
By Alston Lo, Luka Mucko, Austin H. Cheng, Andy Cai, Alastair J. A. Price, Wojciech Matusik, Al\'an Aspuru-Guzik
arXiv:2605.24073v2 Announce Type: replace-cross
Abstract: Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately sim...
By Ihor Neporozhnii, Sjoerd Hoogland, Oleksandr Voznyy
The paper introduces two closed‑form projection operators that enforce physical validity in biomolecular diffusion models during inference. One operator resolves inter‑chain van der Waals clashes, while the other restores ligand geometry, including bond lengths, angles, planarity, and chirality. These lightweight, model‑agnostic corrections preserve structural accuracy and ligand placement across multiple benchmarks without adding runtime or memory overhead.
By Qurat-ul-ain, Yee Whye Teh, Charlotte M. Deane, Matteo Cagiada
The article reviews strategies for modeling chemical disorder in materials, addressing the gap between experimental descriptions of disorder and the detailed configurations required for atomistic simulations and AI workflows. It evaluates traditional approaches such as mean-field theories, cluster expansion, and Monte Carlo, alongside emerging AI-powered methods like universal interatomic potentials and generative models. The review also discusses how AI can accelerate computational schemes and enable disorder-native capabilities, providing a roadmap for integrating disorder into realistic AI-accelerated materials discovery.
By Jiayu Peng, Peichen Zhong
arXiv:2610.19630v1 Announce Type: cross
Abstract: Automated materials discovery requires evaluating large pools of candidate configurations, with density functional theory (DFT) as a major throughput...
By Kun Ryu, Yeo Jin Jung, Shyue Ping Ong, Claire Donnat, Ying Shirley Meng
Automated materials discovery requires evaluating large pools of candidate configurations, with density functional theory (DFT) as a major throughput bottleneck. Pretrained machine-learned interatomic...
arXiv:2510. 16165v2 Announce Type: replace Abstract: A key question in benchmarking generative crystal reconstruction models is how the amount and type of crystallographic information provided to a generative model affects its ability to reconstruct atomic structures.
By Charles Rhys Campbell, Aldo H. Romero, Kamal Choudhary