collaborators

5 papers

cs.LG2026

Wasserstein Convergence of ODE-Based Samplers in Decentralized Diffusion Model via Velocity Field Decomposition

Chencheng Tang, Xuanyu Xue, Fangyikang Wang +2

Diffusion models have achieved impressive empirical success in generative tasks, and their convergence theory is now relatively well understood. Motivated by privacy and scalabilit…

cs.CV2026

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation

Wangbo Zhao, Yizeng Han, Jiasheng Tang +6

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investig…

cs.CV2025

Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin

Fangyikang Wang, Hubery Yin, Lei Qian +9

The diffusion models (DMs) have demonstrated the remarkable capability of generating images via learning the noised score function of data distribution. Current DM sampling techniq…

cs.LG2025

Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

Fangyikang Wang, Hubery Yin, Shaobin Zhuang +7

Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into vari…

cs.CV2025

Analyzing and Mitigating Model Collapse in Rectified Flow Models

Huminhao Zhu, Fangyikang Wang, Tianyu Ding +2

Training with synthetic data is becoming increasingly inevitable as synthetic content proliferates across the web, driven by the remarkable performance of recent deep generative mo…