AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention

Jiahao Li, Jiayi Dong, Peng Ye, Xiaochi Zhou, Haohai Lu, Fei Wang

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative protein structure design · 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 gene block attention (ablation)SAVE · Heart (dual-condition generation)Wasserstein distance: 8.89 -> 8.30Improved
add gene block attention (ablation)SAVE · Heart (dual-condition generation)MMD: 0.65 -> 0.63Improved
increase gene block size K from 600 to 3200 (ablation)SAVE · Heart (dual-condition generation)Wasserstein distance: 9.70 -> 8.30Improved
increase gene block size K beyond 3200 (4000, 5600) (ablation)SAVE · Heart (dual-condition generation)Wasserstein distance: 8.30 -> 8.37 / 8.41No clear effect
use gene blocks (K=3200) instead of per-gene attention (K=1) (ablation)SAVE · training time under 24GB VRAMtraining time (min): 2391.2 -> 12.5 minImproved
add condition masking (ratio 0.6) (ablation)SAVE · PBMC-IFN perturbation predictionaverage PCC / R2: 0.90 -> 0.96 PCC; 0.75 -> 0.86 R2Improved
use SAVE instead of CFGen on single-condition generationSAVE · PBMC3K and Tabula MurisWasserstein distance: 16.94 vs 19.14 (PBMC3K); 7.39 vs 10.86 (Tabula Muris)Hurt
use SAVE instead of baselines on Dentate gyrusSAVE · Dentate gyrusWasserstein distance: 21.55 -> 9.16Improved
use SAVE for dual-condition generation vs best baselineSAVE · Heart, PBMC, Lung AtlasWasserstein distance: 12.57 -> 8.30; 11.38 -> 5.37; 13.89 -> 4.37Improved
use SAVE on held-out Lung Cancer conditionsSAVE · Lung Cancer (unseen)WD / MMD: WD 5.29 -> 4.63; MMD 1.87 vs 2.11Mixed
use SAVE for perturbation prediction vs strongest baselinesSAVE · PBMC-IFNaverage PCC: 0.94 -> 0.96Improved

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