{"total":14,"items":[{"citing_arxiv_id":"2605.22698","ref_index":13,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Machine Learning Interatomic Potentials: Advancing Open-Source Software for Efficient and Scalable Molecular Simulation","primary_cat":"physics.chem-ph","submitted_at":"2026-05-21T16:40:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"mlip v2 is a new software release that integrates API redesign, e3j backend, eSEN model, improved charge modeling, and expanded simulation capabilities to support larger-scale molecular modeling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19050","ref_index":37,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Generative Pseudo-Force Fields for Molecular Generation","primary_cat":"cs.LG","submitted_at":"2026-05-18T19:14:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17147","ref_index":9,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Spatial statistics for screening molecular structures","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-16T20:42:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Spatial statistics on voxelized structures using FFT correlations and PCA yield low-dimensional convex features that support accurate predictions with as few as 10 training samples.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"global properties dictated by 3D electron distributions, such as polarizability and thermodynamic stability in complex per- and polyfluoroalkyl substances (PFAS) [94], underscoring their applicability across chemically diverse domains. In parallel, a large body of work has focused on increasingly expressive deep architectures for atomistic learning, including message-passing graph neural networks [20, 56, 112], equivariant graph networks [9, 25], and 3D CNNs operating directly on voxelized charge densities [ 15, 91, 114] or atomic neighborhoods [8, 9, 15, 20, 36, 49, 69, 74, 100-102, 112-114]. While these models can achieve high accuracy on benchmark datasets, they typically require105-107 trainable parameters and DFT-generated training sets in the 103-105 range to avoid overfitting, fundamentally limiting"},{"citing_arxiv_id":"2605.13788","ref_index":5,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs","primary_cat":"cs.LG","submitted_at":"2026-05-13T17:08:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Force-aware Neural Tangent Kernels combined with chunked acquisition provide scalable and distribution-robust active learning for MLIPs, outperforming baselines on OC20 and remaining competitive on other benchmarks.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"Final columns are final-round RMSE in meV for energy and meV Å−1 for forces. AUC is the discrete sum of RMSE over acquisition steps. Best (lowest) values are in bold. All descriptor based methods use LCMD acquisition. Bias Method Energy AUC (↓) Force AUC (↓) Final E RMSE (↓) Final F RMSE (↓) Inter (Reaction) Random 633.3 [129.7] 7865.2 [1807.8] 6.3 [3.7] 123.7 [65.3] Committee-E 571.7 [108.7] 7165.5 [543.5] 4.5 [2.5] 83.8 [12.8] Tanimoto 587.2 [168.8] 6973.8 [1498.2] 8.5 [3.5] 118.3 [25.7] SOAP 313.2 [72.8] 4909.8 [816.2]2.8 [0.8]58.3 [11.3] Activation245.3 [35.3] 3916.8 [217.8]3.2 [0.8] 56.0 [11.0] NTK 261.3 [22.3] 3945.3 [393.3]2.8 [1.2] 54.3 [11.3] NTK-F 329.7 [41.3] 4395.5 [467.5] 3.5 [0.5] 59.5 [13.5] NTK-EF 343.2 [71.2] 4287.7 [352.3] 3.3 [1.3] 59."},{"citing_arxiv_id":"2605.13262","ref_index":3,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:43:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02685","ref_index":17,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Unified microscopic picture of cation and anion migration in MAPbI$_3$","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-04T15:01:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Molecular dynamics simulations find that both I and MA defects in MAPbI3 diffuse rapidly at room temperature with barriers of 0.15-0.20 eV, with MA interstitials moving via concerted mechanisms and no MA vacancy migration observed.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"; Islam, M. S. Ionic transport in hybrid lead iodide per- ovskite solar cells.Nat. Commun.2015,6, 7497, Publisher: Nature Publishing Group. (16) Yang, T.-Y.; Gregori, G.; Pellet, N.; Gr¨ atzel, M.; Maier, J. The Signifi- cance of Ion Conduction in a Hybrid Organic-Inorganic Lead-Iodide-Based Per- ovskite Photosensitizer.Angew. Chem. 2015,54, 7905-7910. (17) Yuan, Y.; Chae, J.; Shao, Y.; Wang, Q.; Xiao, Z.; Centrone, A.; Huang, J. Pho- tovoltaic Switching Mechanism in Lateral Structure Hybrid Perovskite Solar Cells.Adv. Energy Mater.2015,5, 1500615. (18) Yu, H.; Lu, H.; Xie, F.; Zhou, S.; Zhao, N. Native Defect-Induced Hysteresis Behavior in Organolead Iodide Perovskite Solar Cells. Adv. Funct. Mater."},{"citing_arxiv_id":"2604.26593","ref_index":65,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertainty","primary_cat":"cs.LG","submitted_at":"2026-04-29T12:22:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PiGGO integrates a learned graph neural ODE as the continuous-time dynamics model within an extended Kalman filter to enable online virtual sensing and uncertainty-aware state estimation for nonlinear dynamic systems with unknown model form and sparse sensing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24563","ref_index":9,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Enhancing molecular dynamics with equivariant machine-learned densities","primary_cat":"physics.chem-ph","submitted_at":"2026-04-27T14:49:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DenSNet learns the Hohenberg-Kohn map to electron density with equivariant networks and delta-learning, then maps density to energy, producing stable MD trajectories whose infrared spectra match experiment and DFT on ethanol, ethanethiol, resorcinol, and polythiophene oligomers.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"dimensional potential-energy surfaces.Physical Review Letters, 98(14):146401, 2007. doi: 10.1103/PhysRevLett.98.146401. [8] Stefan Chmiela, Alexandre Tkatchenko, Huziel E Sauceda, Igor Poltavsky, Kristof T Sch¨ utt, and Klaus-Robert M¨ uller. Machine learning of accurate energy-conserving molecular force fields.Science Advances, 3(5):e1603015, 2017. doi: 10.1126/sciadv. 1603015. [9] Simon Batzner, Albert Musaelian, Lixin Sun, Mario Geiger, Jonathan P Mailoa, Mordechai Kornbluth, Nicola Molinari, Tess E Smidt, and Boris Kozinsky. E(3)- equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature Communications, 13:2453, 2022. doi: 10.1038/s41467-022-29939-5. [10] Ilyes Batatia, D' avid P' eter Kov' acs, Gregor NC Simm, Christoph Ortner, and G' abor"},{"citing_arxiv_id":"2604.21494","ref_index":35,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Data-Driven Thermal and Mechanical Modeling of Defective Covalent Organic Frameworks","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-23T09:54:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"QCOF ML potentials tuned on COF data outperform general MACE models for defective systems and reveal higher thermal defect sensitivity in CTF-1 versus COF-LZU1 with nearly invariant low-strain mechanics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20821","ref_index":23,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Autonomous Emergence of Hamiltonian in Deep Generative Models","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-04-22T17:46:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A symmetry-equivariant generative model trained on thermal snapshots of a 1D O(3) spin glass recovers the microscopic Hamiltonian parameters with 99.7% cosine similarity to ground truth through linear inversion of its learned score field.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08250","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"SMC-AI: Scaling Monte Carlo Simulation to Four Trillion Atoms with AI Accelerators","primary_cat":"physics.comp-ph","submitted_at":"2026-04-09T13:41:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"SMC-AI scales Monte Carlo simulations to 4 trillion atoms on AI hardware clusters, achieving 32 times larger systems and 1.3 times higher throughput than prior records while decoupling ML models from the simulation core.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"hierarchy to avoid unnecessary data movement. With these innovations, SMC-X has demonstrated per-chip performance [35] that exceeds all prior works [21], as shown in Tab. I. TABLE I COMPARISON OF THE PERFORMANCE OF ATOMISTIC SIMULATIONS(MCANDMD)ACHIEVINGDFT-LEVEL ACCURACY(10MEV/ATOM). Application Potential System Chips Machine Atoms Throughput (TP) (billion) (billion atom·step/s) WL-LSMS [24] DFT Fe 36,866 Opteron Jaguar 0.0000011.23×10 −6 SNAP ML-IAP [17] SNAP C 27,900 V100 Summit 2028.9 DeePMD-kit [25] DeepPotential Cu 27,360 V100 Summit 3.49.09 DeePMD-kit [25] DeepPotential Cu 9,936 A64FX Fugaku 1.11.49 DeePMD-kit [25] DeepPotential H 2O 27,360 V100 Summit 3.911.2 DeePMD-kit [25] DeepPotential H 2O 9,936 A64FX Fugaku (part) 1.52.17"},{"citing_arxiv_id":"2604.07276","ref_index":31,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Making Room for AI: Multi-GPU Molecular Dynamics with Deep Potentials in GROMACS","primary_cat":"cs.DC","submitted_at":"2026-04-08T16:40:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GROMACS now runs multi-GPU DeePMD inference for molecular dynamics, reaching 40-66% strong scaling efficiency up to 32 devices on a 15k-atom protein system with over 90% time in inference.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.03046","ref_index":44,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing","primary_cat":"cs.LG","submitted_at":"2025-10-03T14:28:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.14665","ref_index":118,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Accurate and scalable exchange-correlation with deep learning","primary_cat":"physics.chem-ph","submitted_at":"2025-06-17T15:56:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Skala is a neural XC functional trained on wavefunction data that beats state-of-the-art hybrids on main-group chemistry benchmarks at semi-local computational cost.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"URL https://pubs.acs.org/doi/10.1021/acs.jpca.4c07807. 21 [117] K. A. Peterson, T. B. Adler, and H.-J. Werner. Systematically convergent basis sets for explicitly correlated wavefunctions: The atoms H, He, B-Ne, and Al-Ar.The Journal of Chemical Physics, 128(8):084102, Feb. 2008. ISSN 0021-9606. doi: 10.1063/1.2831537. URLhttps://doi.org/10.1063/1.2831537. [118] P. Pracht, F. Bohle, and S. Grimme. Automated exploration of the low-energy chemical space with fast quantum chemical methods.Physical Chemistry Chemical Physics, 22(14):7169-7192, Apr. 2020. ISSN 1463-9084. doi: 10.1039/C9CP06869D. URL https://pubs.rsc.org/en/content/articlelanding/ 2020/cp/c9cp06869d. Publisher: The Royal Society of Chemistry. [119] M."}],"limit":50,"offset":0}