The paper introduces two Hessian-based data augmentation techniques—UniAug and ModeAug—to improve machine‑learning interatomic potentials (MLIPs). These methods use simple Taylor expansions to generate augmented configurations without modifying training objectives or increasing computational overhead. Experiments on both non‑equilibrium and equilibrium datasets show that the augmentations enhance model accuracy and provide practical guidelines for specific tasks.
By Bumju Kwak, Jeonghee Jo
arXiv:2509.21624v4 Announce Type: replace
Abstract: Molecular Hessians, the second derivatives of the potential energy, are fundamental to many workflows in computational chemistry. Usually, accurate...
By Andreas Burger, Luca Thiede, Nikolaj R{\o}nne, Varinia Bernales, Nandita Vijaykumar, Tejs Vegge, Arghya Bhowmik, Alan Aspuru-Guzik
arXiv:2512. 21227v3 Announce Type: replace-cross Abstract: In recent years, generative artificial intelligence has made significant advances in the design of crystalline materials, giving rise to approaches based on graph neural networks, diffusion models, and large language models.
By Xiao-Qi Han, Ze-Feng Gao, Wen-Kao Li, Peng-Jie Guo, Zhong-Yi Lu
arXiv:2602. 04861v2 Announce Type: replace-cross Abstract: Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading to erroneous behavior in downstream simulations that standard energy and force regression evaluations can miss.
By Ryan Liu, Eric Qu, Tobias Kreiman, Samuel M. Blau, Aditi S. Krishnapriyan
arXiv:2509. 21624v3 Announce Type: replace Abstract: Fundamental tasks in computational chemistry, from transition state search to vibrational analysis, rely on molecular Hessians, which are the second derivatives of the potential energy.
By Andreas Burger, Luca Thiede, Nikolaj R{\o}nne, Varinia Bernales, Nandita Vijaykumar, Tejs Vegge, Arghya Bhowmik, Alan Aspuru-Guzik
arXiv:2606. 00794v1 Announce Type: cross Abstract: Merging first-principles calculations with machine learning (ML), we aim to accelerate the exploration of catalytic behaviour in novel materials.
By Pavlo Melnyk, Anmar Karmush, M{\aa}rten Wadenb\"ack, Ania Beatriz Rodr\'iguez-Barrera, Johanna Rosen, Michael Felsberg, Jonas Bj\"ork
arXiv:2606. 18691v1 Announce Type: new Abstract: Pre-trained materials foundation models, or machine learning interatomic potentials, leverage general physicochemical knowledge to effectively approximate potential energy surfaces.
By Youngwoo Cho, Seunghoon Yi, Wooil Yang, Sungmo Kang, Young-woo Son, Jaegul Choo, Joonseok Lee, Soo Kyung Kim, Hongkee Yoon
arXiv:2606. 14498v1 Announce Type: cross Abstract: Predicting the Kohn-Sham Hamiltonian with machine learning can accelerate density functional theory while retaining access to molecular orbitals, energy levels, and electronic-structure observables that energy-only surrogates cannot resolve.
By Yunhong Lou, Xihang Yue, Xinran Wei, Tianqi Deng, Linchao Zhu
arXiv:2602. 16908v2 Announce Type: replace-cross Abstract: Allegro is a machine learning interatomic potential model designed to predict atomic properties in molecules using E(3) equivariant neural networks.
By G. Laskaris, D. Morozov, D. Tarpanov, A. Seth, J. Procelewska, G. Sai Gautam, A. Sagingalieva, R. Brasher, A. Melnikov
The paper presents a semi‑local framework that learns long‑range electrostatics and polarization for machine‑learning interatomic potentials using polarizable atomic multipoles. Local equivariant descriptors predict environment‑dependent monopoles, dipoles, and quadrupoles, while a non‑self‑consistent linear response captures residual charge transfer and polarization. Across multiple benchmarks and MLIP architectures, this multipole hierarchy systematically improves potential energy surface accuracy and yields physically meaningful electrical responses, including accurate Born effective charges, infrared and Raman spectra, and surface‑specific vibrational signatures.
By Yoonjae Park, Dongjin Kim, Daniel S. King, Nam H. {\DJ}\`ao, Roya Savoj, Sebastien Hamel, Xiaoyu Wang, Bingqing Cheng
The paper introduces ADAPT, a lightweight machine‑learning force field that replaces graph neural networks with a direct coordinates‑in‑space Transformer encoder to model all pairwise atomic interactions. Applied to silicon point defects, ADAPT reduces force prediction error by about 22% and energy prediction error by roughly 40% compared to a state‑of‑the‑art GNN model, while also cutting computational cost. This approach addresses common GNN issues such as oversmoothing, oversquashing, and poor long‑range interaction representation, which are especially problematic for point defect modeling.
By Evan Dramko, Yihuang Xiong, Yizhi Zhu, Geoffroy Hautier, Thomas Reps, Christopher Jermaine, Anastasios Kyrillidis
The paper presents a neural operator that learns the Kohn–Sham map, directly predicting electron density from the Kohn–Sham potential without orbital diagonalization. Using a domain‑invariant SE(3)‑equivariant Fourier neural operator trained on 8,504 molecules and solids, the model achieves quasi‑linear scaling self‑consistent field (SCF) convergence across diverse systems—including organic molecules, insulators, and metals—while reproducing Kohn–Sham DFT accuracy for densities, spectra, and structural observables. This enables large‑scale simulations, such as magnesium dislocation densities with 82,500 valence electrons, on a single GPU.
By Danish Khan, Maurice D. Hanisch, Nikolai Argatoff, Evan Xie, Sandeep Sharma, Anima Anandkumar