52 citations · 83 across the 12 of their papers we have counts for
7 papers · 1 filter
Representation Fréchet Loss for Visual Generation
Jiawei Yang, Zhengyang Geng, Xuan Ju +2
We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decou…
Improved Mean Flows: On the Challenges of Fastforward Generative Models
Zhengyang Geng, Yiyang Lu, Zongze Wu +3
MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training obje…
One-Step Diffusion Distillation through Score Implicit Matching
Weijian Luo, Zemin Huang, Zhengyang Geng +2
Despite their strong performances on many generative tasks, diffusion models require a large number of sampling steps in order to generate realistic samples. This has motivated the…
One-Step Diffusion Distillation via Deep Equilibrium Models
Zhengyang Geng, Ashwini Pokle, J. Zico Kolter
Diffusion models excel at producing high-quality samples but naively require hundreds of iterations, prompting multiple attempts to distill the generation process into a faster net…
Eliminating Gradient Conflict in Reference-based Line-Art Colorization
Zekun Li, Zhengyang Geng, Zhao Kang +2
Reference-based line-art colorization is a challenging task in computer vision. The color, texture, and shading are rendered based on an abstract sketch, which heavily relies on th…
Deep Equilibrium Optical Flow Estimation
Shaojie Bai, Zhengyang Geng, Yash Savani +1
Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a…
Is Attention Better Than Matrix Decomposition?
Zhengyang Geng, Meng-Hao Guo, Hongxu Chen +3
As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery. However, is hand-crafted…