AI Paper Atlas

Research map / Graph learning / GNN architectures

MAVEN: A Mesh-Aware Volumetric Encoding Network for Simulating 3D Flexible Deformation

Zhe Feng, Shilong Tao, Haonan Sun, Shaohan Chen, Zhanxing Zhu, Yunhuai Liu

ICLR 2026 · Graph learning › GNN architectures · approach: Structural GNN variants · 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
add geometry-aware aggregation coefficients (vs degree averaging) (ablation)MAVEN · Cavity Grasping, full rolloutPosition RMSE: 17.45 -> 15.41Improved
add geometry-aware aggregation coefficients (vs degree averaging) (ablation)MAVEN · Metal Bending, full rolloutStress RMSE: 6683.94 -> 4776.72Improved
add explicit cell/facet geometric input features (vs zero padding) (ablation)MAVEN · Metal Bending, full rolloutPosition RMSE: 1652.31 -> 810.42Improved
add explicit cell/facet geometric input features (vs zero padding) (ablation)MAVEN · Cavity Grasping, full rolloutPosition RMSE: 15.933 -> 15.41Improved
add explicit cell and facet nodes (vs averaging features onto vertices) (ablation)MAVEN · Metal Bending, full rolloutStress RMSE: 10375.86 -> 4776.72Improved
add explicit cell and facet nodes (vs averaging features onto vertices) (ablation)MAVEN · Metal Bending, full rolloutPosition RMSE: 1680.20 -> 810.42Improved
add cell nodes on top of facet-only FIGNetMAVEN vs FIGNet · Metal Bending, full rolloutPosition RMSE: 1030.57 -> 810.42Improved
use MAVEN instead of best node-based baseline as mesh gets coarserMAVEN · DP, CG, MBDaverage improvement: 3.41%, 13.07%, and 18.13%Improved
use MAVEN instead of MGNMAVEN · Deforming Plate, full rolloutPosition RMSE: 23.65 -> 23.41Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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