The paper investigates whether machine learning models can uncover physical patterns in atomistic data without relying on traditional physics-based inductive biases such as geometric locality or graph structures. By training a general-purpose architecture on molecular simulation data, the authors demonstrate that the model autonomously learns interatomic interaction strengths resembling classical electrostatics and identifies interaction cutoffs aligned with established physical models. The study also reports predictable neural scaling behavior and competitive accuracy on certain metrics compared to physics-informed architectures, suggesting that explicit priors may only be necessary when empirically justified.
arXiv:2607. 29158v1 Announce Type: cross Abstract: We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations.
arXiv:2607. 03039v1 Announce Type: new Abstract: Neural networks are increasingly used to infer hidden physical structure from dynamical observations, yet it remains unclear whether their out-of-distribution performance reflects transferable physical rule learning.
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.
arXiv:2605. 29283v2 Announce Type: replace-cross Abstract: Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution.
arXiv:2509. 13805v4 Announce Type: replace-cross Abstract: Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining.
arXiv:2606. 00401v1 Announce Type: cross Abstract: Simulating large molecular systems comprising thousands of atoms requires highly scalable methodologies.
arXiv:2606. 30961v1 Announce Type: cross Abstract: Advances in deep learning architectures and representations have enabled ML-driven chemical property prediction, but state-of-the-art (SOTA) models have remained largely confined to independent codebases and lack support for diverse chemical species.
arXiv:2606. 31332v1 Announce Type: new Abstract: Protein automodeling from cryo-EM density maps faces unique challenges in enforcing physicochemical validity and managing conformational heterogeneity.
BOOM is a new benchmark for evaluating out‑of‑distribution (OOD) molecular property predictions in machine learning. It provides chemically‑informed tests across common property prediction tasks and assesses over 150 model‑task combinations. The study shows that current models, including chemical foundation models, struggle to generalize OOD, with the best model still exhibiting three times higher error than in‑distribution predictions.
arXiv:2604. 09320v2 Announce Type: replace-cross Abstract: Mechanistic understanding and rational design of complex chemical systems depend on fast and accurate predictions of electronic structures beyond individual building blocks.
arXiv:2606. 30170v1 Announce Type: cross Abstract: Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets.
arXiv:2603. 14700v2 Announce Type: replace-cross Abstract: Machine learning interatomic potentials (MLIPs) have become widely used tools in atomistic simulations.