AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Planar Symmetric Pattern Generation

Ning Lin, Luxi Chen, Huaguan Chen, Jiacheng Cen, Chongxuan Li, Wenbing Huang, Hao Sun

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations · 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
use proposed symmetric continuous representation instead of basis projection (alpha=0.25)SD 2.1 p1 pattern generation · p1 pattern (n=128)CLIP-A: 3.07 -> 4.20Improved
use proposed representation instead of basis projection (alpha=1.00)SD 2.1 p1 pattern generation · p1 pattern (n=256)CLIP-A: 3.48 -> 3.99Improved
use proposed representation instead of basis projection (alpha=1.00)SD 2.1 p1 pattern generation · p1 pattern (n=64)CLIP-A: 4.05 -> 4.30Improved
enforce symmetry by post-symmetrization instead of generating in symmetric representationGPT-5.2 and Gemini 3 Pro · 17-prompt pattern designCLIP-AHurt
use SDS on symmetric representation instead of CLIP loss baselinetopology design · variable angle p1 (CLIP-A and bulk modulus)CLIP-A and bulk modulusMixed
use SDS on symmetric representation instead of CLIP baseline for p2 and pm groupstopology design · variable symmetryCLIP-A and bulk modulusImproved

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