Institution profile

EvolutionaryScale

Industry researchnorthamerica · us
Official website
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design

Jul 01, 2025

In biomolecular design, reward functions are often non-differentiable—e.g., derived from physics-based simulations or domain-specific heuristics—posing challenges for reward-guided diffusion model training, including instability, low sample efficiency, and mode collapse. To address this, we propose an iterative policy distillation framework that enables efficient fine-tuning of diffusion models under arbitrary (including non-differentiable) rewards. Our method leverages off-policy data reuse, soft-optimal policy modeling, and KL-divergence-regularized policy updates to stabilize learning and preserve diversity. Compared to existing reinforcement learning–based approaches, it significantly improves training stability and sample efficiency while avoiding mode collapse. We validate the framework across protein, small-molecule, and regulatory DNA design tasks, achieving state-of-the-art reward optimization performance in all settings. Results demonstrate the method’s generality, robustness to diverse reward formulations, and scientific validity in real-world biomolecular design applications.

0 citationsRead paper
Recent publications

Latest Papers

Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design

Jul 01, 2025

In biomolecular design, reward functions are often non-differentiable—e.g., derived from physics-based simulations or domain-specific heuristics—posing challenges for reward-guided diffusion model training, including instability, low sample efficiency, and mode collapse. To address this, we propose an iterative policy distillation framework that enables efficient fine-tuning of diffusion models under arbitrary (including non-differentiable) rewards. Our method leverages off-policy data reuse, soft-optimal policy modeling, and KL-divergence-regularized policy updates to stabilize learning and preserve diversity. Compared to existing reinforcement learning–based approaches, it significantly improves training stability and sample efficiency while avoiding mode collapse. We validate the framework across protein, small-molecule, and regulatory DNA design tasks, achieving state-of-the-art reward optimization performance in all settings. Results demonstrate the method’s generality, robustness to diverse reward formulations, and scientific validity in real-world biomolecular design applications.

0 citationsRead paper