2025/02/20 by Masatoshi Uehara, Uehara, Masatoshi, Xingyu Su +13 · 1 voice · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Gene Regulatory Network Analysis #Generative Adversarial Networks and Image Synthesis #Model Reduction and Neural Networks
paper · pdf · doi:10.48550/arxiv.2502.14944
To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-guided generation have been recently proposed due to their significance, current approaches predominantly focus on single-shot generation, transitioning from fully noised to denoised states. We propose a novel framework for inference-time reward optimization with diffusion models inspired by evolutionary algorithms. Our approach employs an iterative refinement process consisting of two steps in each iteration: noising and reward-guided denoising. This sequential refinement allows for the gradual correction of errors introduced during reward optimization. Besides, we provide a theoretical guarantee for our framework. Finally, we demonstrate its superior empirical performance in protein and cell-type-specific regulatory DNA design. The code is available at \hrefhttps://github.com/masa-ue/ProDifEvo-Refinementhttps://github.com/masa-ue/ProDifEvo-Refinement.