发表机构
Westlake University; Zhejiang University; University College London（西湖大学; 浙江大学; 伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出三体散射建模（TBSM）用于生成，将能量距离转化为特定相互作用，为单步生成器提供监督。通过在线跟踪条件期望减少噪声，在ImageNet-256上训练单步生成器取得良好结果，确立了跟踪散射作为高维单步生成的途径。
AI 中文摘要
现代生成模型通常依赖对抗性判别器、规定的噪声到数据路径或自回归分解。相反，我们表明适当的分布能量可以诱导样本级运动，并为单步生成器提供直接回归监督。用于生成的三体散射建模（TBSM）将能量距离转化为每个射弹的固定大小相互作用：每个射弹被一个真实源吸引并被一个独立生成的源排斥。基于射弹及其条件，其期望等于$\frac12D_E^2(P_{\theta},Q)$的2-瓦瑟斯坦梯度流速度。一批$B$个冻结目标事件产生$O(B)$个样本级损失，每个损失使用一个参考作为其条件，而不是像漂移模型等方法使用的小批量全对场。在线跟踪这种条件期望可以减少场噪声。使用冻结图像特征中的散射，TBSM在ImageNet-256上训练单步生成器，在NFE = 1时，像素空间的PixelDiT-XL实现FID = 2.23，潜在空间的DiT-XL实现FID = 1.63。我们提供了一个设计图，将扩散相关监督、类似漂移的动力学和类似GAN的目标联系起来。这些结果将跟踪散射确立为高维单步生成的一条途径。代码：此https URL。
英文摘要
Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization. Instead, we show that a proper distributional energy can induce sample-level motion and provide direct regression supervision for a one-step generator. Three-Body Scattering Modeling (TBSM) for generation turns the energy distance into a constant-size per-projectile interaction: each projectile is attracted toward one real source and repelled from one independently generated source. Conditioned on the projectile and its condition, its expectation equals the $2$-Wasserstein gradient-flow velocity of $\frac12D_E^2(P_θ,Q)$. A batch of $B$ frozen-target events yields $O(B)$ sample-level losses, each using one reference for its condition instead of the minibatch-wide all-pairs field used by methods such as Drifting Models. Tracking this conditional expectation online can reduce field noise. Using scattering in frozen image features, TBSM trains one-step generators on ImageNet-256, achieving FID${}=2.23$ with pixel-space PixelDiT-XL and FID${}=1.63$ with latent-space DiT-XL at NFE${}=1$. We provide a design map relating diffusion-related supervision, Drift-like dynamics, and GAN-like objectives. These results establish tracked scattering as a route to high-dimensional one-step generation. Code: https://github.com/sp12138/TBSM.
Comments31 pages, 5 figures, and 4 tables. Code: https://github.com/sp12138/TBSM
