{"total":23,"items":[{"citing_arxiv_id":"2606.27636","ref_index":82,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoTAR: Topology and Atomic State Reconstruction in Condensed Phases","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-26T01:23:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CoTAR reconstructs molecular topology from atomic positions in non-reactive condensed-phase systems using a GNN-HMM hybrid, reporting 0.906 F1 on classical MD data and raising uMLIP valid-snapshot rate from 38.6% to 84.7% after few-shot fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21632","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fine-Tuning a Universal Machine-Learned Interatomic Potential for Oxygen Plasma Interactions with WS$_2$","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-19T17:36:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Pretrained UMA model reproduces chemisorbed S and O coverage under 15 eV O+ and O2+ bombardment on WS2 without fine-tuning; fine-tuning lowers energy MAE to 4.5e-3 eV/atom and force MAE to 0.076 eV/Å.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22698","ref_index":12,"ref_count":1,"confidence":0.9,"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":"2605.18472","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Flowing with Confidence","primary_cat":"stat.ML","submitted_at":"2026-05-18T14:28:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FMwC computes per-sample confidence scores for flow matching models via closed-form propagation of input-dependent multiplicative noise variance along the sampling ODE, supporting filtering, editing, and adaptive stepping.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16612","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation","primary_cat":"cs.AI","submitted_at":"2026-05-15T20:27:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16214","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bridging Atomistic Simulation and Experimental Processing Timescales with Goal-Directed Deep Reinforcement Learning","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-15T17:28:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An E(3)-equivariant deep RL framework lets an O2 agent discover kinetically plausible diffusion and dissociation pathways in disordered Si/a-SiO2 without hand-crafted reaction coordinates or collective variables.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15630","ref_index":63,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Reweighting free energy profiles between universal machine learning interatomic potentials for fast consensus building","primary_cat":"physics.chem-ph","submitted_at":"2026-05-15T05:30:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A reweighting method with mean energy-gap approximation transfers PMFs between MLIPs to recover target reaction and activation free energies at low cost for a 601-atom Li+ transport system across DFT levels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14154","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TSAgent: An Agentic Workflow for Autonomous Transition State Search","primary_cat":"physics.chem-ph","submitted_at":"2026-05-13T22:08:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13788","ref_index":54,"ref_count":2,"confidence":0.9,"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":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13594","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Assessing foundational atomistic models for iron alloys under Earth's core conditions","primary_cat":"physics.geo-ph","submitted_at":"2026-05-13T14:30:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Foundational atomistic models reproduce some structural and dynamical properties of iron alloys under core conditions but none consistently match first-principles benchmarks due to missing explicit treatment of thermal electronic excitations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09394","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Systematic Fine-Tuning of MACE Interatomic Potentials for Catalysis","primary_cat":"physics.chem-ph","submitted_at":"2026-05-10T07:43:42+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Fine-tuned MACE MLIPs achieve lower mean absolute errors on catalytic reaction energies and barriers than from-scratch models, with a large fine-tuned model performing best on both metallic and oxide systems including out-of-distribution cases.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"over previous approaches [11-13]. For heterogeneous catalysis, the reliance on large datasets to train MLIPs such as the Open Catalyst datasets [14] \"out of the box\" might be a limitation, as performance remains heavily dependent on data availability and quality, which may restrict their generalizability when determining bothE r and Ea Wood, et al. [15] have used a mixture of experts model to train a family of universal models (UMA) on a combined dataset comprised of OC22 (oxide electrocatalysts) [16], OC25 (solid-liquid interfaces) [17], OMOL (molecules) [18], OpenDac [19] and OMAT (bulk inorganic materials)[20]and is able to estimateE r within 0.1 eV of DFT, for 74 % ofE r reported in AdsorbML task."},{"citing_arxiv_id":"2605.08988","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials","primary_cat":"cs.LG","submitted_at":"2026-05-09T15:12:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new benchmark finds that state-of-the-art ML interatomic potentials struggle with compositional generalization, producing errors an order of magnitude higher on unseen molecular combinations than on training-like cases.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"We use our benchmark to evaluate a diverse set of state-of-the-art MLIPs. These include invariant message-passing networks (SchNet [40]), models incorporating explicit geometric features (GemNet [18, 17], DimeNet++ [16]), rotationally equivariant architectures (PAINN [39], NequIP [6], eSCN [32]), MACE [ 4]), and equivariant transformers (EquiFormerV2 [ 25]). We also evaluate UMA (Small) [42] and MACE-MP-0 (Small, Medium, Large) [5], as representative foundation models. Evaluating foundation models against our PBE labels presents distinct challenges. Total energies are tied to dataset-specific atomic-energy references, level-of-theory choices, and DFT-code implementa- tions, all of which inevitably differ between our labels and the pre-training data of any foundation"},{"citing_arxiv_id":"2605.08885","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning","primary_cat":"cs.LG","submitted_at":"2026-05-09T11:07:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Structural pruning of SO(3) equivariant atomistic models from large checkpoints yields 1.5-4x fewer parameters and 2.5-4x less pre-training compute than small models trained from scratch, while outperforming them on most Matbench Discovery metrics and downstream tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Advincula, Mark Asta, Matthew Avaylon, William J Baldwin, et al. A foundation model for atomistic materials chemistry.arXiv preprint arXiv:2401.00096, 2023. [3] Yutack Park, Jaesun Kim, Seungwoo Hwang, and Seungwu Han. Scalable parallel algorithm for graph neural network interatomic potentials in molecular dynamics simulations.J. Chem. Theory Comput., 20 (11):4857-4868, 2024. doi: 10.1021/acs.jctc.4c00190. [4] Brandon M Wood, Misko Dzamba, Xiang Fu, Meng Gao, Muhammed Shuaibi, Luis Barroso-Luque, Kareem Abdelmaqsoud, Vahe Gharakhanyan, John R Kitchin, Daniel S Levine, et al. Uma: A family of universal models for atoms.arXiv preprint arXiv:2506.23971, 2025. [5] Benjamin Rhodes, Sander Vandenhaute, Vaidotas Šimkus, James Gin, Jonathan Godwin, Tim Duignan,"},{"citing_arxiv_id":"2605.03964","ref_index":49,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs","primary_cat":"cs.LG","submitted_at":"2026-05-05T16:48:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Kernels from pretrained MLIP latent spaces outperform standard acquisition methods in active learning for reactive chemistry, reducing required labels by 38% for energy error and 28% for force error.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00640","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Knowing when to trust machine-learned interatomic potentials","primary_cat":"cs.LG","submitted_at":"2026-05-01T13:21:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PROBE recasts MLIP uncertainty quantification as selective classification by training a compact discriminative classifier on frozen per-atom backbone embeddings, yielding a reliability probability that tracks actual error better than ensemble disagreement.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27685","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VibroML: an automated toolkit for high-throughput vibrational analysis and dynamic instability remediation of crystalline materials using machine-learned potentials","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-30T10:20:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VibroML automates remediation of dynamic instabilities in crystalline materials by combining MLIPs with genetic algorithms for polymorph search, finite-temperature MD validation, and compositional alloying to yield stable structures from databases like Alexandria.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24607","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Errors that matter: Uncertainty-aware universal machine-learning potentials calibrated on experiments","primary_cat":"physics.chem-ph","submitted_at":"2026-04-27T15:32:37+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PET-UAFD ensemble of ML potentials, calibrated on experimental cohesive energies and moduli, matches experimental accuracy on liquid properties and supplies uncertainty estimates via the PET-EXP protocol.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12607","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Hierarchical generative modeling for the design of multi-component systems","primary_cat":"physics.comp-ph","submitted_at":"2026-04-14T11:32:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A closed-loop framework jointly optimizes molecular composition and geometry in multi-component systems, demonstrated by a 30% reduction in activation barrier for a Claisen rearrangement via post-hoc validation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.01642","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Benchmarking Chemically Scalable Machine-Learning Interatomic Potentials for Large-Scale Simulations of Multicomponent Alloys","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-02T05:41:09+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[18] M. Neumann, J. Gin, B. Rhodes, S. Bennett, Z. Li, H. Choubisa, A. Hussey, and J. Godwin, Orb: A fast, scalable neural network potential, arXiv preprint arXiv:2410.22570 (2024). [19] D. Wines and K. Choudhary, Chips-ff: Evaluating uni- versal machine learning force fields for material proper- ties, ACS Materials Letters7, 2105-2114 (2025). 13 [20] B. M. Wood, M. Dzamba, X. Fu, M. Gao, M. Shuaibi, L. Barroso-Luque, K. Abdelmaqsoud, V. Gharakhanyan, J. R. Kitchin, D. S. Levine, K. Michel, A. Sriram, T. Co- hen, A. Das, A. Rizvi, S. J. Sahoo, Z. W. Ulissi, and C. L. Zitnick, Uma: A family of universal models for atoms (2026), arXiv:2506.23971 [cs.LG]. [21] Z. Fan, Z. Zeng, C. Zhang, Y. Wang, K."},{"citing_arxiv_id":"2603.21942","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Suiren-1.0 Technical Report: A Family of Molecular Foundation Models","primary_cat":"physics.chem-ph","submitted_at":"2026-03-23T12:59:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Suiren-1.0 is a family of three molecular foundation models (Base, Dimer, ConfAvg) pre-trained on 70M+ DFT samples and distilled to achieve claimed state-of-the-art performance on quantum property prediction tasks from 2D inputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.17709","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UBio-MolFM: A Universal Molecular Foundation Model for Bio-Systems","primary_cat":"physics.chem-ph","submitted_at":"2026-02-13T04:38:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UBio-MolFM achieves ab initio-level fidelity on large out-of-distribution biomolecular systems using a new multi-fidelity dataset, E2Former-V2 architecture, and three-stage curriculum learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.16331","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Accuracy and Efficiency Benchmarks of Pretrained Machine Learning Potentials for Molecular Simulations","primary_cat":"physics.chem-ph","submitted_at":"2026-01-22T21:32:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Benchmarks of 15 MLIPs show parameter count and training set size correlate with accuracy, architecture drives speed and memory, and explicit Coulomb terms provide no benefit.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.05717","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Comparing the latent features of universal machine-learning interatomic potentials","primary_cat":"physics.chem-ph","submitted_at":"2025-12-05T13:45:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Different uMLIPs encode chemical space in distinct ways, with high cross-model feature reconstruction errors, and fine-tuning preserves strong pre-training bias in the latent features.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}