CMAD：通过随机最优控制的协作多智能体扩散
CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control
AI总结：
本文提出了一种新的框架，将多模型组合生成问题转化为协作随机最优控制问题，通过联合优化扩散轨迹来实现更有效的生成效果。
摘要：
连续时间生成模型在图像恢复和合成中取得了显著成功。然而，控制多个预训练模型的组合仍是一个开放性挑战。当前方法大多将组合视为概率密度的代数组合，如通过概率密度的产品或专家混合。这种观点假设目标分布已知，这几乎从未发生。在本文中，我们提出了一种不同的范式，将组合生成视为协作随机最优控制问题。与其结合概率密度，我们把预训练的扩散模型视为相互作用的智能体，其扩散轨迹通过最优控制共同引导，朝着其聚合输出上定义的共享目标前进。我们在条件MNIST生成上验证了我们的框架，并将其与一个简单的基线进行比较，该基线在推理时间用每步梯度引导替代了学习的协作控制。
英文摘要：
Continuous-time generative models have achieved remarkable success in image restoration and synthesis. However, controlling the composition of multiple pre-trained models remains an open challenge. Current approaches largely treat composition as an algebraic composition of probability densities, such as via products or mixtures of experts. This perspective assumes the target distribution is known explicitly, which is almost never the case. In this work, we propose a different paradigm that formulates compositional generation as a cooperative Stochastic Optimal Control problem. Rather than combining probability densities, we treat pre-trained diffusion models as interacting agents whose diffusion trajectories are jointly steered, via optimal control, toward a shared objective defined on their aggregated output. We validate our framework on conditional MNIST generation and compare it against a naïve inference-time DPS-style baseline replacing learned cooperative control with per-step gradient guidance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
