|国家预印本平台
首页|Continuous Semi-Implicit Models

Continuous Semi-Implicit Models

Continuous Semi-Implicit Models

来源:Arxiv_logoArxiv
英文摘要

Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers, enhance the expressiveness of semi-implicit distributions and can be used to accelerate diffusion models given pretrained score networks. However, their sequential training often suffers from slow convergence. In this paper, we introduce CoSIM, a continuous semi-implicit model that extends hierarchical semi-implicit models into a continuous framework. By incorporating a continuous transition kernel, CoSIM enables efficient, simulation-free training. Furthermore, we show that CoSIM achieves consistency with a carefully designed transition kernel, offering a novel approach for multistep distillation of generative models at the distributional level. Extensive experiments on image generation demonstrate that CoSIM performs on par or better than existing diffusion model acceleration methods, achieving superior performance on FD-DINOv2.

Longlin Yu、Jiajun Zha、Tong Yang、Tianyu Xie、Xiangyu Zhang、S. -H. Gary Chan、Cheng Zhang

计算技术、计算机技术

Longlin Yu,Jiajun Zha,Tong Yang,Tianyu Xie,Xiangyu Zhang,S. -H. Gary Chan,Cheng Zhang.Continuous Semi-Implicit Models[EB/OL].(2025-06-07)[2025-06-24].https://arxiv.org/abs/2506.06778.点此复制

评论