论文标题
通过模型预测控制的有条件扩散，并较少明确的指导
Conditional Diffusion with Less Explicit Guidance via Model Predictive Control
论文作者
论文摘要
有条件扩散需要多少明确的指导？我们考虑使用无条件扩散模型和有限的显式指导（例如NOISTER分类器或条件扩散模型）的条件采样问题，该指南仅限于少量时间步骤。我们通过模拟无条件扩散向前并反向宣传显式的指导反馈来探索模型预测控制（MPC）样方法，以实现近似指导。即使在大型模拟距离上，MPC的指南与真实指南具有很高的余弦相似性。当明确的指导仅限于五个时间步骤时，添加MPC步骤可提高生成质量。
How much explicit guidance is necessary for conditional diffusion? We consider the problem of conditional sampling using an unconditional diffusion model and limited explicit guidance (e.g., a noised classifier, or a conditional diffusion model) that is restricted to a small number of time steps. We explore a model predictive control (MPC)-like approach to approximate guidance by simulating unconditional diffusion forward, and backpropagating explicit guidance feedback. MPC-approximated guides have high cosine similarity to real guides, even over large simulation distances. Adding MPC steps improves generative quality when explicit guidance is limited to five time steps.
