AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

CryoNet.Refine: A One-step Diffusion Model for Rapid Refinement of Structural Models with Cryo-EM Density Map Restraints

Fuyao Huang, Xiaozhu Yu, Kui Xu, Qiangfeng Cliff Zhang

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Equivariant diffusion for 3D molecules · 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 CryoNet.Refine instead of Phenix.real_space_refineAlphaFold3 models · Protein complexes (110, cryo-EM)CC_mask: 0.54 -> 0.59Improved
use CryoNet.Refine instead of Phenix.real_space_refineAlphaFold3 models · Protein complexes (110, cryo-EM)Rotamer favored (%): 85.42 -> 98.64Improved
use CryoNet.Refine instead of Phenix.real_space_refineAlphaFold3 models · Protein complexes (110, cryo-EM)Rotamer outlier (%): 1.15 -> 0.49Improved
use CryoNet.Refine instead of Phenix.real_space_refineAlphaFold3 models · Protein complexes (110, cryo-EM)Ramachandran outlier (%): 0.02 -> 0.06Hurt
use CryoNet.Refine instead of Phenix.real_space_refineAlphaFold3 models · DNA/RNA-protein complexes (10, cryo-EM)CC_mc: 0.62 -> 0.61Hurt
use CryoNet.Refine instead of Phenix.real_space_refineAlphaFold3 models · DNA/RNA-protein complexes (10, cryo-EM)CC_sc: 0.58 -> 0.67Improved
use one-step diffusion instead of 200-step classical diffusion (ablation)CryoNet.Refine · Classical diffusion vs one-step (27 cases)CC_mask: 0.30 -> 0.59Improved
use one-step diffusion instead of 200-step classical diffusion (ablation)CryoNet.Refine · Classical diffusion vs one-step (27 cases)Angle RMSD (degree): 1.66 -> 0.36Improved
add more recycling iterations beyond 100 (ablation)CryoNet.Refine · PDB 6kswCC metricsNo clear effect
add density loss and geometry loss together (ablation)CryoNet.Refine · benchmarkCC and geometric metricsImproved
run CryoNet.Refine instead of Phenix on CPUruntime · 120 complexesruntime: 65 cases (54.2%)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