# SPID: Distilled Protein Backbone Generation

arXiv: https://arxiv.org/abs/2510.03095 · HTML: https://mlsanity.com/paper/2510.03095/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Stochastic Interpolants: A Unifying Framework for Flows and Diffusions](https://mlsanity.com/paper/2303.08797/) (2023)
- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)
- [Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem](https://mlsanity.com/paper/2206.04119/) (2022)
- [Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models](https://mlsanity.com/paper/2305.18455/) (2023)
- [SE(3) diffusion model with application to protein backbone generation](https://mlsanity.com/paper/2302.02277/) (2023)
- [Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation](https://mlsanity.com/paper/2404.04057/) (2024)
- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [SE(3)-Stochastic Flow Matching for Protein Backbone Generation](https://mlsanity.com/paper/2310.02391/) (2023)
- [Flow map matching with stochastic interpolants: A mathematical framework for consistency models](https://mlsanity.com/paper/2406.07507/) (2024)
- [Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2205.15019/) (2022)
- [Align Your Flow: Scaling Continuous-Time Flow Map Distillation](https://mlsanity.com/paper/2506.14603/) (2025)
- [Proteina: Scaling Flow-based Protein Structure Generative Models](https://mlsanity.com/paper/2503.00710/) (2025)
- [Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds](https://mlsanity.com/paper/2301.12485/) (2023)
- [Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step](https://mlsanity.com/paper/2410.14919/) (2024)
- [Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices](https://mlsanity.com/paper/2410.11795/) (2024)
- [Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2](https://mlsanity.com/paper/2405.15489/) (2024)
- [Efficient Diffusion Models: A Survey](https://mlsanity.com/paper/2502.06805/) (2025)
- [Few-Step Diffusion via Score identity Distillation](https://mlsanity.com/paper/2505.12674/) (2025)
- [A Survey on Pre-Trained Diffusion Model Distillations](https://mlsanity.com/paper/2502.08364/) (2025)

## Built on by (most cited first, 1 of 1)

- [Riemannian MeanFlow](https://mlsanity.com/paper/2602.07744/) (2026)

## Abstract (arXiv)

Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unprecedented capabilities for de novo protein design. However, despite their generation quality, these models are constrained by slow sampling, often requiring hundreds of iterative steps. This computational bottleneck limits their practical utility in large-scale protein discovery, where thousands to millions of candidate structures are needed. To address this challenge, we explore the techniques of score distillation, which has shown great success in reducing the number of sampling steps in the vision domain while maintaining high generation quality. However, a straightforward adaptation of these methods results in unacceptably low designability. We introduce Score Protein identity Distillation (SPID), which resolves this incompatibility by combining few-step generation with inference-time noise scaling. SPID adapts the Score identity Distillation (SiD) framework to both diffusion- and flow-based models without requiring access to pretraining data. Applied to the Proteina flow-matching model, our 16-step generator achieves 94.4% designability, matching the 400-step teacher, while delivering more than a 20-fold reduction in effective backbone-generation time and maintaining comparable diversity and novelty. SPID generalizes across unconditional generation, fold-class conditional generation, and motif scaffolding, and extends to equivariant diffusion architectures, achieving significant reduction in generation time with comparable generation quality to the teacher in all tasks. The resulting reduction in inference cost could facilitate large-scale in silico protein design, thereby advancing diffusion-based models toward real-world protein engineering applications. The PyTorch implementation is available at https://github.com/LY-Xie/SiD_Protein