Flows, straight but not so fast: Exploring the design space of Rectified Flows in Protein Design

• URL: http://arxiv.org/abs/2510.24732v1
• Date: Mon, 13 Oct 2025 07:36:40 GMT
• Title: Flows, straight but not so fast: Exploring the design space of Rectified Flows in Protein Design
• Abstract summary: We show that Rectified Flows (ReFlow) can significantly reduce the required NFEs for a given target quality.<n>We apply ReFlow to improve the low NFE performance of pretrained SE(3) flow matching models for protein backbone generation.
• Score: 12.818279735492945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative modeling techniques such as Diffusion and Flow Matching have achieved significant successes in generating designable and diverse protein backbones. However, many current models are computationally expensive, requiring hundreds or even thousands of function evaluations (NFEs) to yield samples of acceptable quality, which can become a bottleneck in practical design campaigns that often generate $10^4\ -\ 10^6$ designs per target. In image generation, Rectified Flows (ReFlow) can significantly reduce the required NFEs for a given target quality, but their application in protein backbone generation has been less studied. We apply ReFlow to improve the low NFE performance of pretrained SE(3) flow matching models for protein backbone generation and systematically study ReFlow design choices in the context of protein generation in data curation, training and inference time settings. In particular, we (1) show that ReFlow in the protein domain is particularly sensitive to the choice of coupling generation and annealing, (2) demonstrate how useful design choices for ReFlow in the image domain do not directly translate to better performance on proteins, and (3) make improvements to ReFlow methodology for proteins.

Related papers

• SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups [33.76281571675535]
  We introduce SE(3)-MeanFlow, a few-step generative framework that extends MeanFlow from Euclidean space to the Lie group geometry of protein frames.<n>We derive closed-form average-velocity identities for rotations and translations, giving simulation-free training targets.
  arXiv  Detail & Related papers  (2026-07-29T19:58:00Z)
• Riemannian MeanFlow [28.880123107817525]
  We introduce a framework for learning flow maps directly on inference, enabling high-quality generations with as few as one forward pass.<n>We show that few-step flow maps enable efficient reward-guided design through reward look-ahead, where terminal states can be predicted from intermediate steps.
  arXiv  Detail & Related papers  (2026-02-08T00:41:17Z)
• ProteinAE: Protein Diffusion Autoencoders for Structure Encoding [64.77182442408254]
  We introduce ProteinAE, a novel and streamlined protein diffusion autoencoder.<n>ProteinAE directly maps protein backbone coordinates from E(3) into a continuous, compact latent space.<n>We demonstrate that ProteinAE achieves state-of-the-art reconstruction quality, outperforming existing autoencoders.
  arXiv  Detail & Related papers  (2025-10-12T14:30:32Z)
• Distilled Protein Backbone Generation [59.63474232035653]
  Diffusion- and flow-based generative models offer unprecedented capabilities for de novo protein design.<n>These models are limited by their generating speed, often requiring hundreds of iterative steps in the reverse-diffusion process.<n>We show how to appropriately adapt Score identity Distillation (SiD), a state-of-the-art score distillation strategy, to train few-step protein backbone generators.
  arXiv  Detail & Related papers  (2025-10-03T15:25:08Z)
• ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning [49.2607661375311]
  We present ProteinZero, a novel framework that enables computationally scalable, automated, and continuous self-improvement of the inverse folding model.<n>ProteinZero substantially outperforms existing methods across every key metric in protein design.<n> Notably, the entire RL run on CATH-4.3 can be done with a single 8 X GPU node in under 3 days, including reward.
  arXiv  Detail & Related papers  (2025-06-09T06:08:59Z)
• ProtFlow: Fast Protein Sequence Design via Flow Matching on Compressed Protein Language Model Embeddings [8.068149785650649]
  ProtFlow is a fast flow matching-based protein sequence design framework.<n>By compressing and smoothing the latent space, ProtFlow enhances performance while training on limited computational resources.<n>We evaluate ProtFlow across diverse protein design tasks, including general peptides and long-chain proteins, antimicrobial peptides, and antibodies.
  arXiv  Detail & Related papers  (2025-04-15T08:46:53Z)
• Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design [87.58981407469977]
  We propose a novel framework for inference-time reward optimization with diffusion models inspired by evolutionary algorithms.<n>Our approach employs an iterative refinement process consisting of two steps in each iteration: noising and reward-guided denoising.
  arXiv  Detail & Related papers  (2025-02-20T17:48:45Z)
• ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation [24.13216117355207]
  We propose a novel rectified quaternion flow (ReQFlow) matching method for fast and high-quality protein backbone generation.<n>Our method generates a local translation and a 3D rotation from random noise for each residue in a protein chain.<n>We train the model by quaternion flow (QFlow) matching with guaranteed numerical stability and rectify the QFlow model to accelerate its inference and improve the designability of generated protein backbones.
  arXiv  Detail & Related papers  (2025-02-20T15:20:37Z)
• Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation [55.93511121486321]
  We introduce FoldFlow-2, a novel sequence-conditioned flow matching model for protein structure generation.<n>We train FoldFlow-2 at scale on a new dataset that is an order of magnitude larger than PDB datasets of prior works.<n>We empirically observe that FoldFlow-2 outperforms previous state-of-the-art protein structure-based generative models.
  arXiv  Detail & Related papers  (2024-05-30T17:53:50Z)
• SE(3)-Stochastic Flow Matching for Protein Backbone Generation [54.951832422425454]
  We introduce FoldFlow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3mathrmD$ rigid motions. Our family of FoldFlowgenerative models offers several advantages over previous approaches to the generative modeling of proteins.
  arXiv  Detail & Related papers  (2023-10-03T19:24:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.