AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Tensor Decomposition Networks for Accelerating Machine Learning Force Field Computations

Yuchao Lin, Cong Fu, Zachary Krueger, Haiyang Yu, Maho Nakata, Jianwen Xie, Emine Kucukbenli, Xiaofeng Qian, Shuiwang Ji

NeurIPS 2025 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes tensor decomposition networks (TDNs) that replace Clebsch-Gordan tensor products in SO(3)-equivariant MLIPs with low-rank tensor decompositions to accelerate force field computation.

Problem

SO(3)-equivariant machine learning interatomic potentials rely on Clebsch-Gordan tensor products, which are computationally expensive.

Approach

Approximately equivariant networks whose CG tensor products are replaced by low-rank tensor decompositions, trading exact equivariance for speed.

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