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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add SVDD value-based inference guidance (ablation) | RiboDiff · RNA-protein complex | scRMSD (A): 7.43 -> 6.41 | Improved |
| add SVDD value-based inference guidance (ablation) | RiboDiff · Protein-conditioned RNA | GT-RMSD (A): 13.20 -> 12.43 | Improved |
| add SVDD value-based inference guidance (ablation) | RiboDiff · Protein-conditioned RNA | ipTM: 0.166 -> 0.187 | Improved |
| add SVDD inference guidance (ablation) | RiboDiff · Protein-conditioned RNA, Chai-1 | pTM: 0.520 -> 0.509 | Hurt |
| replace from-scratch MMDiff with pretrained RF2NA denoiser in joint diffusion | RiboDiff · Single RNA co-design | scRMSD (A): 35.77 -> 3.43 | Improved |
| replace MMDiff with RiboDiff | RiboDiff · Single RNA co-design | success rate (%): 8.86 -> 97.38 | Improved |
| replace RNA-FrameFlow + gRNAde two-step pipeline with joint co-design | RiboDiff · Single RNA co-design | scSeqRec (%): 45.65 -> 48.57 | Improved |
| replace MMDiff with RiboDiff | RiboDiff · RNA-protein complex | scRMSD (A): 30.84 -> 7.43 | Improved |
| replace RNAFlow-Base with RiboDiff | RiboDiff · Conditional RNA design (RF2NA split) | GT-SeqRec (%): 27.98 -> 56.26 | Improved |
| replace RNAFlow-Base with RiboDiff | RiboDiff · Conditional RNA design (sequence similarity split) | GT-RMSD (A): 17.48 -> 13.39 | Improved |
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.
- MMDIFF — MMDiff: Extending Diffusion Transformers for Multi-Modal Generation (ECCV 2026) · better on 9 of 9 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
- RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching (ICML 2024 · similarity 0.91)
- RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design (ICLR 2024 · similarity 0.89)
- TANGO: RNA Topology and Geometry Co-Design (NeurIPS 2026 · similarity 0.89)
- RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching (NeurIPS 2025 · similarity 0.88)
- gRNAde: Geometric Deep Learning for 3D RNA inverse design (ICLR 2025 · similarity 0.88)
- Diffusion on Language Model Encodings for Protein Sequence Generation (ICML 2025 · similarity 0.87)
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.
