AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Coordinate Denoising for Non-Equilibrium Molecular Representation Learning

Qianwei Tang, Baile Xu, Jian Zhao, Furao Shen

CVPR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Diffusion for molecular conformations

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 NDeM auxiliary denoising task (ablation)TorchMD-NET · MD17 Aspirin forceforce MAE: 0.2087 -> 0.1654Improved
raise auxiliary weight from 1 to 100 (ablation)NDeM · MD17 Aspirin forceforce MAE: 0.1654 -> 0.1722Hurt
increase max noise sigma from 0.05 to 0.5 (ablation)NDeM · MD17 Aspirin forceforce MAE: 0.1654 -> 0.1887Hurt
add NDeM when fine-tuning from Frad pretrained weights (ablation)Frad · MD17 Aspirin forceforce MAE: 0.2088 -> 0.1774Improved
add NDeM when fine-tuning from SliDe pretrained weights (ablation)SliDe · MD17 Aspirin forceforce MAE: 0.1698 -> 0.1648Improved
output noisy force through the primary force head instead of a separate auxiliary head (ablation)NDeM · MD17force MAEHurt
add NDeM to EquiformerV2 (lambda_E=2)EquiformerV2 · OC20 S2EF testforce MAE (meV/A): 13.8 -> 12.9Improved
add NDeM to EquiformerV2 (lambda_E=4)EquiformerV2 · OC20 S2EF testforce MAE (meV/A): 14.2 -> 13.8Improved
NDeM instead of DeNS on EquiformerV2 (lambda_E=4)EquiformerV2 · OC20 S2EF testforce MAE (meV/A): 13.4 (DeNS) vs 13.8 (NDeM)No clear effect
add NDeM as auxiliary task to TorchMD-NET without pre-trainingTorchMD-NET · QM9 gapMAE (meV): 26.2 (SliDe) -> 26.0Improved
NDeM vs SliDe on QM9 U0NDeM · QM9 U0MAE (meV): 4.28 (SliDe) vs 5.31 (NDeM)Hurt
NDeM on MD17 Benzene and Uracil vs best baselinesTorchMD-NET · MD17force MAE: Benzene 0.1802 vs 0.1691 (SliDe); Uracil 0.0806 vs 0.0760 (Frad)Mixed

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