arXiv:2606. 19133v1 Announce Type: cross Abstract: Scalable prediction of optical spectra is a critical component of high-throughput materials screening for optoelectronic applications such as solar cells.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper introduces a new way to evaluate materials graph neural networks (GNNs) by measuring how many trainable parameter‑space directions are needed to achieve good performance. Using random‑subspace intrinsic‑dimension analysis, the authors train CGCNN, ALIGNN, and DimeNet++ on six prediction tasks and plot recovery curves that separate final accuracy from the dimensional demand required to reach it. The study finds that different tasks and architectures vary in how sensitive they are to dimensional restriction, revealing insights that final error metrics alone miss.
arXiv:2607. 24818v1 Announce Type: cross Abstract: Accurate prediction of crystal properties remains a key challenge in computational materials science.
EquiPocket is an E(3)-equivariant Graph Neural Network designed to predict ligand binding sites on proteins. It processes proteins as geometric graphs, extracting local surface atom geometry, modeling chemical and spatial relationships, and performing equivariant message passing to capture surface geometry. A dense attention output layer mitigates issues caused by variable protein sizes, and experiments show the method outperforms current state‑of‑the‑art approaches.
arXiv:2607. 08996v1 Announce Type: cross Abstract: Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties.
arXiv:2606. 00776v1 Announce Type: new Abstract: Fast and accurate prediction of crystal properties is a central challenge in new materials design.
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.