Generative Modeling via Drifting

2026-02-04 · Mingyang Deng, He Li, Tianhong Li, Yilun Du, Kaiming He arxiv

Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and flow-based models. In this paper, we propose a new paradigm called Drifting Models, which evolve the pushforward distribution during training and naturally admit one-step inference. We introduce a drifting field that governs the sample movement and achieves equilibrium when the distributions match. This leads to a training objective that allows the neural network optimizer to evolve the distribution. In experiments, our one-step generator achieves state-of-the-art results on ImageNet at 256 x 256 resolution, with an FID of 1.54 in latent space and 1.61 in pixel space. We hope that our work opens up new opportunities for high-quality one-step generation.

📄 PDF Abstract BibTeX arXiv:2602.04770

Code (0)

등록된 구현이 없습니다.

Drifting Models for Surrogate Flow Modeling

2026-06-05 · Chris R. Jung, Markus Dörr, Natalie Jüngling, Jennifer Niessner 외 arxiv

While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration. To solve this problem generative surrogates offer better di…

DriftXpress: Faster Drifting Models via Projected RKHS Fields

2026-05-12 · Ali Falahati, Elliot Creager, Gautam Kamath, Shubhankar Mohapatra arxiv

Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative denoising process in diffusion models w…

SymDrift: One-Shot Generative Modeling under Symmetries

2026-05-07 · Samir Darouich, Vinh Tong, Lluís Pastor-Pérez, Tanja Bien 외 arxiv

Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such as rotations in three-dimensional space. Equivariant diffusion and flow matchin…

Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences

2026-03-11 · Jiarui Cao, Zixuan Wei, Yuxin Liu arxiv

We reveal a precise mathematical framework about a new family of generative models which we call Gradient Flow Drifting. With this framework, we prove an equivalence between the recently proposed Drifting Model and the W…

Density Estimation

Kernel-Gradient Drifting Models

2026-05-11 · Maria Esteban-Casadevall, Jorge Carrasco-Pollo, Max Welling, Jan-Willem van de Meent 외 arxiv

We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting models with directions induced by the kernel itself. Standard drifting is…