| title | Three-Body Scattering for Generative Modeling |
|---|---|
| authors | Peng Sun, Zhenglin Cheng, Deyuan Liu, Jun Xie, Xinyi Shang, Tao Lin |
| date | 2026-07-20 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.18198 |
| upvotes | 14 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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. |
cite
@misc{sun2026three,
title={Three-Body Scattering for Generative Modeling},
author={Peng Sun and Zhenglin Cheng and Deyuan Liu and Jun Xie and Xinyi Shang and Tao Lin},
year={2026},
eprint={2607.18198},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.18198}
}