AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Protein Autoregressive Modeling via Multiscale Structure Generation

Yanru Qu, Cheng-Yen Hsieh, Zaixiang Zheng, Ge Liu, Quanquan Gu

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Diffusion for protein and antibody design

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 noisy context learning (ablation)PAR (teacher forcing) · 60M PAR unconditionalsc-RMSD: 2.20 -> 1.58Improved
add scheduled sampling on top of noisy context learning (ablation)PAR + NCL · 60M PAR unconditionalsc-RMSD: 1.58 -> 1.48Improved
add noisy context learning (ablation)PAR (teacher forcing) · 60M PAR unconditionalFPSD vs AFDB: 37.64 -> 23.69Improved
add SDE at first scale and ODE at later scales with 2 steps (ablation)PAR all-SDE · length 150time (s): 312 -> 67 (designability 97% -> 97%)Improved
use ODE sampling at all scales instead of SDE at first scale (ablation)PAR S/O/O · length 150designability (%): 96% -> 28%Hurt
halve single-scale SDE steps from 400 to 200 (ablation)Proteina · length 150designability (%): 97% -> 89%Hurt
define scales by length instead of by ratio (ablation)PAR 60M · unconditionalFPSD vs PDB: 310.64 -> 279.63Improved
increase scales from two to three (ablation)PAR 60M · unconditionaldesignability (%): 83.0 -> 85.0Improved
increase scales from three to four (ablation)PAR 60M · unconditionaldesignability (%): 85.0 -> 77.8Hurt
encode prior scales with AR transformer instead of direct input (ablation)PAR 60M · prompted generation (64,128]RMSD vs reference: 3.38 -> 2.72Improved
increase AR transformer size from 60M to 400M (ablation)PAR (decoder 60M) · unconditionaldesignability (%): 92.60 -> 87.80Hurt
increase decoder size from 60M to 400M (ablation)PAR (AR 60M) · unconditionaldesignability (%): 92.60 -> 96.00Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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