1 citations · 2 across the 3 of their papers we have counts for
5 papers · 1 filter
One-step Latent-free Image Generation with Pixel Mean Flows
Yiyang Lu, Susie Lu, Qiao Sun +6
Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a latent space. Recent adva…
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…
Is Noise Conditioning Necessary for Denoising Generative Models?
Qiao Sun, Zhicheng Jiang, Hanhong Zhao +1
It is widely believed that noise conditioning is indispensable for denoising diffusion models to work successfully. This work challenges this belief. Motivated by research on blind…
ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen +11
Recent advances in large generative models have greatly enhanced both image editing and in-context image generation, yet a critical gap remains in ensuring physical consistency, wh…
Highly Compressed Tokenizer Can Generate Without Training
L. Lao Beyer, T. Li, X. Chen +2
Commonly used image tokenizers produce a 2D grid of spatially arranged tokens. In contrast, so-called 1D image tokenizers represent images as highly compressed one-dimensional sequ…