Protein fitness optimization is challenged by a vast combinatorial landscape where high-fitness variants are extremely sparse. Many current methods either underperform or require computationally expensive gradient-based sampling. We present CHASE, a framework that repurposes the evolutionary knowledge of pretrained protein language models by compressing their embeddings into a compact latent space. By training a conditional flow-matching model with classifier-free guidance, we enable the direct generation of high-fitness variants without predictor-based guidance during the ODE sampling steps. CHASE achieves state-of-the-art performance on AAV and GFP protein design benchmarks. Finally, we show that bootstrapping with synthetic data can further enhance performance in data-constrained settings.
@article{arxiv.2602.02425,
title = {Repurposing Protein Language Models for Latent Flow-Based Fitness Optimization},
author = {Amaru Caceres Arroyo and Lea Bogensperger and Ahmed Allam and Michael Krauthammer and Konrad Schindler and Dominik Narnhofer},
journal= {arXiv preprint arXiv:2602.02425},
year = {2026}
}