这篇论文用物理中的三体散射思路做生成模型，仅需一步就达到 DiT-XL 的 FID 1.63，比传统扩散模型少很多步。
论文提出三体散射建模 (TBSM)，将能量距离转化为每个抛射体与一个真实源和一个生成源之间的相互作用，避免全对场计算。在 ImageNet-256 上，使用像素空间 PixelDiT-XL 得到 FID 2.23，使用潜空间 DiT-XL 得到 FID 1.63（NFE=1）。该方法通过在线追踪条件期望降低场噪声，为单步生成提供直接回归监督。
Three-Body Scattering for Generative Modeling
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.