La bu cikip klip mlip yayinlamadan once hersey yolundaydi !! El attigi herseyi cunup ediyor !! @MilliTakimlar

🍁 MAPLE = machine-learning potentials, Gaussian-style inputs. opt · TS search · IRC · MD · freq — on UMA, MACE, AIMNet2 & ANI. One toolkit for the whole reaction landscape. github.com/ClickFF/MAPLE maplechem.org/ #compchem #MLIP

Work of @DishaBrahma1997 @avs_nikhil on Aqueous ZnCl2 solutions using a MACE MLIP we built. Varied Zn coordination geometries. 15-30% ⬆️ in hydration water dipole moments. Non-monotonic water residence times with # of Cl- in Zn shell. More in @JPhysChem pubs.acs.org/doi/10.1021/acs…

Six Open Questions in Machine-Learned Interatomic Potential Foundation Models arxiv.org/abs/2606.07327 機械学習分子間ポテンシャル（MLIP）の基盤モデルに関する6つの未解決問題を整理・考察した総説 お、未解決問題だぞ、チャレンジしような

読んでみたが、面白かった。データの数だけじゃなくて多様性大事とか、長距離相互作用はGNN層深くするだけじゃ不十分そうとか、色々詰め込んだら予測精度向上するけど、DFTより1桁は早くないとMLIP使う意味ないよね、とか色々と書いてあってよかった

あと、基盤モデルを称するMLIPがあるけど、「確かに大規模データで学習してるけど、マルチモーダルでもマルチタスクでもないし、これ基盤モデル名乗ってええんか？」と思ってたが同じようなこと思っている人いたんやね。

📝 Happy to write a News & Views article (doi.org/10.1038/s43588-026-0…) for the paper on the Open Materials 2024 (OMat24) inorganic materials dataset and models from the @AIatMeta FAIR Chemistry Team (@OpenCatalyst) just published in @NatComputSci. Many data-driven atomistic simulations require AI models to describe materials beyond ideal, near-equilibrium structures. At high temperature, near defects, or under realistic processing conditions, atomic environments can become strongly distorted and far from equilibrium. This is why OMat24 (doi.org/10.1038/s43588-026-0…) is a very helpful contribution: it is one of the largest-scale materials-centric open efforts aimed at making universal machine learning interatomic potentials (MLIPs) more reliable precisely when materials are driven out of their equilibrium “comfort zone.” This connects closely to the systematic softening problem highlighted by @Bowen_D_ and co-workers in their earlier 2025 work in npj Computational Materials (doi.org/10.1038/s41524-024-0…), where MLIPs can underestimate energies, forces, and phonons for distorted structures. OMat24 addresses this issue in a data-centric way, by expanding training data to include large-scale off-equilibrium atomic configurations so that models can better learn how materials respond when they are strongly perturbed. The impact of OMat24 is already visible from how quickly it has become a central and widely used resource for the universal MLIP community, including benchmarking efforts on the Matbench Discovery leaderboard (matbench-discovery.materials…). To me, this work is a timely reminder that progress in atomistic machine learning depends not only on model architectures, but also on the physical coverage and design of the datasets used to train them. Looking ahead, I am excited to see how these ideas extend toward more realistic materials chemistry, including defects, surfaces, reactive interfaces, magnetic and charge-dependent systems, higher-fidelity DFT data and methods, and more data-efficient ways to train and reuse large MLIP models and materials informatics datasets. Many thanks to @JPanPanJ for the invitation. Congratulations to @zackulissi, @mshuaibii, @xiangfu_ml, and others in the FAIR Chemistry Team on this important contribution to the AI for Materials research community. 🎉 #MaterialsInformatics #MachineLearning #AIforScience #OpenScience

🚀We're excited to release mlip v2, a major upgrade to our open-source machine learning interatomic potential library. Access faster kernels, a new model architecture, richer physics, and more simulation modes, all in one unified, modular framework 🧵

LiTEN-FF: An equivariant NN foundation model for biomolecular simulations. Using linear tensorized attention to efficiently capture many-body interactions. @NatureComms #MLIP #MachineLearing #ForceField #quantumchem #EGNN #AIforScience #MolecularDynamics #DrugDiscovery