290 citations · 1.3k across the 57 of their papers we have counts for
20 papers · 1 filter
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
Min Zhao, Hongzhou Zhu, Kaiwen Zheng +6
Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong r…
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
Min Zhao, Hongzhou Zhu, Bokai Yan +13
Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains…
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
Hongzhou Zhu, Min Zhao, Guande He +3
To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models, facing an archi…
UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers
Min Zhao, Bokai Yan, Xue Yang +5
Recent image diffusion transformers achieve high-fidelity generation, but struggle to generate images beyond these scales, suffering from content repetition and quality degradation…
UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers
Min Zhao, Hongzhou Zhu, Yingze Wang +6
Despite advances, video diffusion transformers still struggle to generalize beyond their training length, a challenge we term video length extrapolation. We identify two failure mo…
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
Min Zhao, Guande He, Yixiao Chen +3
Recent advancements in video generation have enabled models to synthesize high-quality, minute-long videos. However, generating even longer videos with temporal coherence remains a…
Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model
Min Zhao, Hongzhou Zhu, Chendong Xiang +3
Diffusion models have obtained substantial progress in image-to-video generation. However, in this paper, we find that these models tend to generate videos with less motion than ex…
MicroDreamer: Efficient 3D Generation in 20 Seconds by Score-based Iterative Reconstruction
Luxi Chen, Zhengyi Wang, Zihan Zhou +4
Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number o…
CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model
Zhengyi Wang, Yikai Wang, Yifei Chen +6
Feed-forward 3D generative models like the Large Reconstruction Model (LRM) have demonstrated exceptional generation speed. However, the transformer-based methods do not leverage t…
Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training
Ximing Xing, Chuang Wang, Haitao Zhou +4
Exemplar-based sketch-to-photo synthesis allows users to generate photo-realistic images based on sketches. Recently, diffusion-based methods have achieved impressive performance o…
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
Min Zhao, Rongzhen Wang, Fan Bao +2
This paper presents \emph{ControlVideo} for text-driven video editing -- generating a video that aligns with a given text while preserving the structure of the source video. Buildi…
On Evaluating Adversarial Robustness of Large Vision-Language Models
Yunqing Zhao, Tianyu Pang, Chao Du +4
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptabl…
A Closer Look at Parameter-Efficient Tuning in Diffusion Models
Chendong Xiang, Fan Bao, Chongxuan Li +2
Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time ineffi…
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
Zebin You, Yong Zhong, Fan Bao +3
In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called dual pseudo training (DPT), built up…
All are Worth Words: A ViT Backbone for Diffusion Models
Fan Bao, Shen Nie, Kaiwen Xue +4
Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based on a convolutional neural network (CNN) remains dominant in diffusion models. We design a…
EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations
Min Zhao, Fan Bao, Chongxuan Li +1
Score-based diffusion models (SBDMs) have achieved the SOTA FID results in unpaired image-to-image translation (I2I). However, we notice that existing methods totally ignore the tr…
Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation
Qijun Luo, Zhili Liu, Lanqing Hong +7
Semi-supervised domain adaptation (SSDA), which aims to learn models in a partially labeled target domain with the assistance of the fully labeled source domain, attracts increasin…
Countering Noisy Labels By Learning From Auxiliary Clean Labels
Tsung Wei Tsai, Chongxuan Li, Jun Zhu
We consider the learning from noisy labels (NL) problem which emerges in many real-world applications. In addition to the widely-studied synthetic noise in the NL literature, we al…
Max-Margin Deep Generative Models for (Semi-)Supervised Learning
Chongxuan Li, Jun Zhu, Bo Zhang
Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. How…
Towards Better Analysis of Deep Convolutional Neural Networks
Mengchen Liu, Jiaxin Shi, Zhen Li +3
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-qu…