English
Related papers

Related papers: Causal Forcing++: Scalable Few-Step Autoregressive…

200 papers

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Cheng Han , Qifan Wang , Sohail A. Dianat , Majid Rabbani , Raghuveer M. Rao , Yi Fang , Qiang Guan , Lifu Huang , Dongfang Liu

Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Mingyuan Zhou , Zhendong Wang , Huangjie Zheng , Hai Huang

Generative policies based on diffusion and flow matching achieve strong performance in robotic manipulation by modeling multi-modal human demonstrations. However, their reliance on iterative Ordinary Differential Equation (ODE) integration…

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xiangyu Fan , Zesong Qiu , Zhuguanyu Wu , Fanzhou Wang , Zhiqian Lin , Tianxiang Ren , Dahua Lin , Ruihao Gong , Lei Yang

Diffusion models produce high-quality text-to-image results, but their iterative denoising is computationally expensive.Distribution Matching Distillation (DMD) emerges as a promising path to few-step distillation, but suffers from…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haoyu Li , Tingyan Wen , Lin Qi , Zhe Wu , Yihuang Chen , Xing Zhou , Lifei Zhu , Xueqian Wang , Kai Zhang

Streaming video generation (SVG) distills a pretrained bidirectional video diffusion model into an autoregressive model equipped with sliding window attention (SWA). However, SWA inevitably loses distant history during long video…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Ruibin Li , Tao Yang , Fangzhou Ai , Tianhe Wu , Shilei Wen , Bingyue Peng , Lei Zhang

Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Kesen Zhao , Jiaxin Shi , Beier Zhu , Junbao Zhou , Xiaolong Shen , Yuan Zhou , Qianru Sun , Hanwang Zhang

Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Justin Cui , Jie Wu , Ming Li , Tao Yang , Xiaojie Li , Rui Wang , Andrew Bai , Yuanhao Ban , Cho-Jui Hsieh

Diffusion-based stylization methods typically denoise from a specific partial noise state for image-to-image and video-to-video tasks. This multi-step diffusion process is computationally expensive and hinders real-world application. A…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Sijie Xu , Runqi Wang , Wei Zhu , Dejia Song , Nemo Chen , Xu Tang , Yao Hu

Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xunzhi Xiang , Zixuan Duan , Guiyu Zhang , Haiyu Zhang , Zhe Gao , Junta Wu , Shaofeng Zhang , Tengfei Wang , Qi Fan , Chunchao Guo

Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-19 Liang Xu , Longfei Felix Yan , W. Bastiaan Kleijn

Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Zhenyu Zhou , Defang Chen , Can Wang , Chun Chen , Siwei Lyu

Non-Autoregressive generation is a sequence generation paradigm, which removes the dependency between target tokens. It could efficiently reduce the text generation latency with parallel decoding in place of token-by-token sequential…

Computation and Language · Computer Science 2022-05-24 Weizhen Qi , Yeyun Gong , Yelong Shen , Jian Jiao , Yu Yan , Houqiang Li , Ruofei Zhang , Weizhu Chen , Nan Duan

Real-time talking avatar generation requires low latency and minute-level temporal stability. Autoregressive (AR) forcing enables streaming inference but suffers from exposure bias, which causes errors to accumulate and become irreversible…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Liyuan Cui , Wentao Hu , Wenyuan Zhang , Zesong Yang , Fan Shi , Xiaoqiang Liu

Diffusion-based video super-resolution (VSR) methods deliver strong perceptual quality but are often unsuitable for latency-sensitive scenarios due to reliance on future frames and expensive multi-step denoising. We propose Stream-DiffVSR,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Hau-Shiang Shiu , Chin-Yang Lin , Zhixiang Wang , Chi-Wei Hsiao , Po-Fan Yu , Yu-Chih Chen , Yu-Lun Liu

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Nikita Starodubcev , Ilya Drobyshevskiy , Denis Kuznedelev , Artem Babenko , Dmitry Baranchuk

Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks such as image enhancement, restoration, editing, and compositing. However, their widespread adoption…

Computer Vision and Pattern Recognition · Computer Science 2024-02-20 Kangfu Mei , Mauricio Delbracio , Hossein Talebi , Zhengzhong Tu , Vishal M. Patel , Peyman Milanfar

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Chuhan Wang , Hao Chen

Diffusion-based audio-driven talking avatar methods have recently gained attention for their high-fidelity, vivid, and expressive results. However, their slow inference speed limits practical applications. Despite the development of various…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Tianyun Zhong , Chao Liang , Jianwen Jiang , Gaojie Lin , Jiaqi Yang , Zhou Zhao

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 community to develop effective methods to distill…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Weijian Luo , Zemin Huang , Zhengyang Geng , J. Zico Kolter , Guo-jun Qi