AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Controllable diffusion-based generation for multi-channel biological data

Haoran Zhang, Mingyuan Zhou, Wesley Tansey

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Diffusion for protein and antibody design · 1 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 channel-wise attention in UNet blocks (latent space) (ablation)multi-channel diffusion model · IMC protein imputationPearson r: 0.541 -> 0.596Improved
add output-space channel attention (ablation)multi-channel diffusion model · IMC protein imputationPearson r: 0.581 -> 0.596Improved
inject condition via SE soft channel attention instead of element-wise addition (ablation)hierarchical feature injection · IMC protein imputationPearson r: 0.516 -> 0.535Improved
add hierarchical conditional feature injection to unconditional base (ablation)diffusion model · IMC protein imputationPearson r: -0.017 -> 0.516Improved
train separately for the single missing channel instead of random masking over all channelsproposed model · IMC breast and lungPearson r: 0.596 -> 0.667 (breast), 0.647 -> 0.703 (lung)Improved
train on union of protein channels (zero-padded) instead of intersection across lung and breast IMC (ablation)proposed model · IMC cross-dataset generalizationaverage Pearson rImproved
distill to 1-step inference with SiDproposed model · gene-to-protein, PBMCr_p: 0.673 -> 0.672No clear effect
use proposed diffusion model instead of ControlNetIMC lung imputation · IMC lungPearson r: 0.537 -> 0.647Improved

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