Understanding reinforcement learning-based fine-tuning of diffusion models: A tutorial and review
This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to
optimize downstream reward functions. While diffusion models are widely known to provide …
optimize downstream reward functions. While diffusion models are widely known to provide …
Decoding biology with massively parallel reporter assays and machine learning
Massively parallel reporter assays (MPRAs) are powerful tools for quantifying the impacts of
sequence variation on gene expression. Reading out molecular phenotypes with …
sequence variation on gene expression. Reading out molecular phenotypes with …
Derivative-free guidance in continuous and discrete diffusion models with soft value-based decoding
Diffusion models excel at capturing the natural design spaces of images, molecules, DNA,
RNA, and protein sequences. However, rather than merely generating designs that are …
RNA, and protein sequences. However, rather than merely generating designs that are …
Fine-tuning discrete diffusion models via reward optimization with applications to dna and protein design
Recent studies have demonstrated the strong empirical performance of diffusion models on
discrete sequences across domains from natural language to biological sequence …
discrete sequences across domains from natural language to biological sequence …
Constrained Diffusion Models via Dual Training
Diffusion models have attained prominence for their ability to synthesize a probability
distribution for a given dataset via a diffusion process, enabling the generation of new data …
distribution for a given dataset via a diffusion process, enabling the generation of new data …
Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
Diffusion models have emerged as powerful tools for generative modeling, demonstrating
exceptional capability in capturing target data distributions from large datasets. However …
exceptional capability in capturing target data distributions from large datasets. However …
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
We present a maximum entropy inverse reinforcement learning (IRL) approach for improving
the sample quality of diffusion generative models, especially when the number of generation …
the sample quality of diffusion generative models, especially when the number of generation …
Generative bandit optimization via diffusion posterior sampling
R De Santi, N Liniger, A Krause - openreview.net
Many real-world discovery problems, including drug and material design, can be modeled
within the bandit optimization framework, where an agent selects a sequence of experiments …
within the bandit optimization framework, where an agent selects a sequence of experiments …