AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interaction Potentials

Yuanchang Zhou, Siyu Hu, Xiangyu Zhang, Hongyu Wang, Guangming Tan, Weile Jia

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Machine-learned interatomic potentials

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dim-wise softmax (per-feature-dimension attention weights) (ablation)MatRIS-S · WBM subset, MPTrj-trainedEf MAE (meV/atom): 28.4 -> 28.0Improved
add separable (two-direction) attention (ablation)MatRIS-S · WBM subset, MPTrj-trainedEf MAE (meV/atom): 29.1 -> 28.4Improved
add learnable envelope function (ablation)MatRIS-S · WBM subset, MPTrj-trainedEf MAE (meV/atom): 31.3 -> 29.1Improved
add denoising pretraining (ablation)MatRIS-S · WBM subset, MPTrj-trainedEf MAE (meV/atom): 28.0 -> 27.2Improved
add magnetic moment prediction as auxiliary task (ablation)MatRIS-S · WBM subset, MPTrj-trainedEf MAE (meV/atom): 29.7 -> 28.0Improved
add graph-level loss reduction (ablation)MatRIS-S · WBM subset, MPTrj-trainedEf MAE (meV/atom): 30.2 -> 29.7Improved
use MatRIS-M/S invariant model instead of larger equivariant modelsMatRIS vs eSEN-30M-MP / eqV2 S DeNS · Matbench-Discovery (compliant)training efficiency: 13.0x and 6.4x training efficiency at comparable accuracyImproved
MatRIS has more layers than MACE-L (4 and 6 vs 2)MatRIS-S/M · inference time across system sizesinference timeHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy