# EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering

arXiv: https://arxiv.org/abs/2603.11703 · HTML: https://mlsanity.com/paper/2603.11703/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Discrete Flow Matching](https://mlsanity.com/paper/2407.15595/) (2024)
- [Autoregressive Diffusion Models](https://mlsanity.com/paper/2110.02037/) (2021)
- [Protein Design with Guided Discrete Diffusion](https://mlsanity.com/paper/2305.20009/) (2023)
- [Understanding protein function with a multimodal retrieval-augmented foundation model](https://mlsanity.com/paper/2508.04724/) (2025)

## Built on by (most cited first, 4 of 4)

- [Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction](https://mlsanity.com/paper/2605.04119/) (2026)
- [Flexible Flows for Biological Sequence Design](https://mlsanity.com/paper/2606.10543/) (2026)
- [When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows](https://mlsanity.com/paper/2609.18745/) (2026)
- [Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution](https://mlsanity.com/paper/2610.07607/) (2026)

## Abstract (arXiv)

We introduce EvoFlows, a variable-length protein sequence-to-sequence modeling approach designed for protein engineering. Existing protein language models are poorly suited for optimization tasks: autoregressive models require full sequence generation, masked language and discrete diffusion models rely on pre-specified mutation locations, and no existing methods naturally support insertions and deletions relative to a template sequence. EvoFlows learns mutational trajectories between evolutionarily related protein sequences via edit flows, allowing it to perform a controllable number of mutations (insertions, deletions, and substitutions) on a template sequence, predicting not only _which_ mutation to perform, but also _where_ it should occur. Through extensive _in silico_ evaluation on diverse protein families from UniRef and OAS, we show that EvoFlows generates variants that remain consistent with natural protein families while exploring farther from template sequences than leading baselines.