AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A Cartesian-3j Framework for Machine Learning Interatomic Potentials

Zemin Xu, Chenyu Wu, Wenbo Xie, Peijun Hu

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 0 citations (OpenAlex)

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
swap spherical tensors for irreducible Cartesian tensors in NequIP/Allegro (cNequIP, cAllegro) (ablation)NequIP, Allegro · 3BPAenergy/force RMSENo clear effect
Cartesianize NequIP at 64(64)-3-3-5 (ablation)NequIP · 3BPAspeed (s/epoch): 15.8 -> 46.4Hurt
Cartesianize NequIP at 64(64)-3-3-5 (ablation)NequIP · 3BPAmemory (MiB): 3968 -> 12486Hurt
Cartesianize Allegro at 256(64)-3-3-3 (ablation)Allegro · 3BPAmemory: 5862 -> OOMHurt
Cartesianize MACE (cMACE) (ablation)MACE · 3BPAenergy/force RMSENo clear effect
Cartesianize MACE at 64-3-3-2-3 (ablation)MACE · 3BPAmemory (MiB): 1610 -> 15890Hurt
Cartesianize MACE at 64-3-3-2-3 (ablation)MACE · 3BPAspeed (s/epoch): 6.7 -> 27.6Hurt
add gated nonlinear interactions in the convolution (ablation)TACE 2-layer OMat24 model · Matbench Discovery thermal conductivitykappa SRME: 0.210 -> 0.158Improved
use nonlinear interactionsCartesian models · 3BPAextrapolationHurt
use only RCTP/RCTC at edge level instead of Cartesian-3j symbolsTACE architecture · MD speedspeedImproved
use larger truncation Lmax=4, ell_max=4 in Cartesian spaceTACE · memorymemoryHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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