AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

A Joint Diffusion Model with Pre-Trained Priors for RNA Sequence–Structure Co-Design

Xiner Li, Masatoshi Uehara, Xingyu Su, Gabriele Scalia, Shuiwang Ji

ICLR 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 SVDD value-based inference guidance (ablation)RiboDiff · RNA-protein complexscRMSD (A): 7.43 -> 6.41Improved
add SVDD value-based inference guidance (ablation)RiboDiff · Protein-conditioned RNAGT-RMSD (A): 13.20 -> 12.43Improved
add SVDD value-based inference guidance (ablation)RiboDiff · Protein-conditioned RNAipTM: 0.166 -> 0.187Improved
add SVDD inference guidance (ablation)RiboDiff · Protein-conditioned RNA, Chai-1pTM: 0.520 -> 0.509Hurt
replace from-scratch MMDiff with pretrained RF2NA denoiser in joint diffusionRiboDiff · Single RNA co-designscRMSD (A): 35.77 -> 3.43Improved
replace MMDiff with RiboDiffRiboDiff · Single RNA co-designsuccess rate (%): 8.86 -> 97.38Improved
replace RNA-FrameFlow + gRNAde two-step pipeline with joint co-designRiboDiff · Single RNA co-designscSeqRec (%): 45.65 -> 48.57Improved
replace MMDiff with RiboDiffRiboDiff · RNA-protein complexscRMSD (A): 30.84 -> 7.43Improved
replace RNAFlow-Base with RiboDiffRiboDiff · Conditional RNA design (RF2NA split)GT-SeqRec (%): 27.98 -> 56.26Improved
replace RNAFlow-Base with RiboDiffRiboDiff · Conditional RNA design (sequence similarity split)GT-RMSD (A): 17.48 -> 13.39Improved

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