引导扩散方向：基于引导扩散桥的表型响应模拟生成建模
Steering Where to Diffuse: Generative Modeling of Phenotypic Response Simulation with Steered Diffusion Bridge
把扩散桥的采样过程形式化为随机动力系统下的最优控制问题，用解析可解的控制策略把生成轨迹引导到指定数据子空间，这一思路可直接迁移到图像/视频扩散中的条件引导与轨迹漂移抑制。
原文依据 we formalize the rule-guided sample generation task as an optimal control problem within a stochastic dynamical system
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论细胞形态变化的模拟长期以来是定量生物学与高通量筛选中的基础任务，有望加速疗法开发，并在经验性临床实践之外阐明疾病机制。然而，庞大的扰动空间给判别式建模带来了挑战，而现有的生成式方法往往集中于同一轨迹子空间，使其生成的路径容易发生漂移。本文提出一种新的引导扩散桥方法，命名为 SimuSDB，用于在两个不同状态域之间定义确定性的概率轨迹，以生成细胞响应。我们首先扩展扩散桥范式，通过引入布朗桥在插值轨迹中保持随机性与多样性。随后，SimuSDB 生成符合表型约束的细胞形态，同时允许表型约束显式地引导生成过程。在推理阶段，我们将规则引导的样本生成任务形式化为随机动力系统内的最优控制问题。由此，该生成模型能够获得解析可解的最优控制策略，并实现受引导的生成，而不会坍缩到同一数据子空间的轨迹上。大量实验表明，SimuSDB 在化学扰动与遗传扰动等多种应用中均具有优越性能。
英文原文摘要 1468 字符
Simulation of cellular morphology change has long been a fundamental task in quantitative biology and high-throughput screening, with the potential to accelerate therapeutic development and elucidate disease mechanisms beyond empirical clinical practice. However, the vast perturbation space poses challenges to the discriminative formulation, and existing generative approaches tend to concentrate on the same trajectory subspace, making their generated paths prone to drift. In this paper, we propose a novel Steered Diffusion Bridge approach, named SimuSDB, to define deterministic probabilistic trajectories between two distinct state domains for cell response generation. We first extend the diffusion bridge paradigm to maintain stochasticity and diversity in interpolation trajectories by introducing Brownian bridges. Then, SimuSDB generates cell morphologies that comply with phenotypic constraints, while allowing the latter to explicitly guide the generative process. For the inference stage, we formalize the rule-guided sample generation task as an optimal control problem within a stochastic dynamical system. This way, the generative model can achieve analytically tractable optimal control strategies and steered generation without collapsing toward the trajectory of the same data subspace. Comprehensive experiments demonstrate the superior performance of SimuSDB across various applications, including chemical perturbation and genetic perturbation.