Research map / Image generation / Autoregressive and latent generation
Structure-based RNA Design by Step-wise Optimization of Latent Diffusion Model
Qi Si, Xuyang Liu, Penglei Wang, Xin Guo, Yuan Qi, Yuan Cheng
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 step-wise RL fine-tuning to the LDM | LDM · SOLD TEST | MFE: -13.3275 -> -16.8611 | Improved |
| add step-wise RL fine-tuning to the LDM | LDM · CASP15 TEST | SS: 0.5543 -> 0.6957 | Improved |
| add step-wise RL fine-tuning to the LDM | LDM · SOLD TEST | sequence recovery: 0.5728 -> 0.5732 | No clear effect |
| add step-wise RL fine-tuning to the LDM | LDM · SOLD TEST | SS: 0.7269 vs 0.7601 (but RiboDiffusion 0.7632) | Hurt |
| use RNA-FM latent space instead of one-hot sequence diffusion | RiboDiffusion-style LDM · SOLD TEST | sequence recovery: 0.5125 -> 0.5728 | Improved |
| use single-step sampling instead of full trajectory RL | SOLD vs DDPO/DPOK · MFE training | training time per epoch (s): 5953 -> 256 (DDPO) | Improved |
| use single-step sampling instead of full trajectory RL | SOLD vs DDPO/DPOK · LDDT training | training time per epoch (s): 14000 -> 6900 (DDPO) | Improved |
| SOLD vs DDPO on SS reward | SOLD · SOLD TEST | SS: 0.7595 (DDPO) vs 0.7551 (SOLD) | No clear effect |
| SOLD vs DDPO on SS reward | SOLD · CASP15 TEST | SS: 0.6649 -> 0.7010 | Improved |
| RL on MFE reward vs DRAKES | SOLD · SOLD TEST | MFE: -14.2374 -> -19.7428 | Improved |
Closest papers by meaning
- RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching (ICML 2024 · similarity 0.91)
- TANGO: RNA Topology and Geometry Co-Design (NeurIPS 2026 · similarity 0.89)
- Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design (ICLR 2025 · similarity 0.89)
- Bridge-IF: Learning Inverse Protein Folding with Markov Bridges (NeurIPS 2024 · similarity 0.89)
- gRNAde: Geometric Deep Learning for 3D RNA inverse design (ICLR 2025 · similarity 0.88)
- RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design (ICLR 2024 · similarity 0.88)
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.
