Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
This addresses the need for improved reward-guided generation in diffusion models, particularly for biological design tasks like protein and DNA optimization, representing an incremental advancement over single-shot methods.
The paper tackles the problem of optimizing downstream reward functions during inference in diffusion models, proposing an iterative refinement framework inspired by evolutionary algorithms that gradually corrects errors, and demonstrates superior performance in protein and DNA design applications.
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 \href{https://github.com/masa-ue/ProDifEvo-Refinement}{https://github.com/masa-ue/ProDifEvo-Refinement}.