English
Related papers

Related papers: Just-in-Time: Training-Free Spatial Acceleration f…

200 papers

Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Fu-Yun Wang , Ling Yang , Zhaoyang Huang , Mengdi Wang , Hongsheng Li

Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Zitao Shuai , Chenwei Wu , Zhengxu Tang , Bowen Song , Liyue Shen

Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent breakthroughs have been driven by mask strategy that significantly…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Rui Zhu , Yingwei Pan , Yehao Li , Ting Yao , Zhenglong Sun , Tao Mei , Chang Wen Chen

The latest advances in artificial intelligence (AI) present many unprecedented opportunities to achieve much improved bandwidth saving in communications. Unlike conventional communication systems focusing on packet transport, rich datasets…

Machine Learning · Computer Science 2023-12-07 Achintha Wijesinghe , Songyang Zhang , Suchinthaka Wanninayaka , Weiwei Wang , Zhi Ding

Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving remarkable progress across various tasks, such as image and…

Machine Learning · Computer Science 2025-02-04 Wanghan Xu , Xiaoyu Yue , Zidong Wang , Yao Teng , Wenlong Zhang , Xihui Liu , Luping Zhou , Wanli Ouyang , Lei Bai

Controllable music generation methods are critical for human-centered AI-based music creation, but are currently limited by speed, quality, and control design trade-offs. Diffusion Inference-Time T-optimization (DITTO), in particular,…

Sound · Computer Science 2024-05-31 Zachary Novack , Julian McAuley , Taylor Berg-Kirkpatrick , Nicholas Bryan

Diffusion models recently developed for generative AI tasks can produce high-quality samples while still maintaining diversity among samples to promote mode coverage, providing a promising path for learning stochastic closure models.…

Machine Learning · Computer Science 2026-02-20 Xinghao Dong , Huchen Yang , Jin-long Wu

Though rectified flow models have achieved remarkable performance in image, video, and 3D generation, their practical deployments are challenged by slow inference speeds. Prior acceleration methods reuse cached features from previous steps,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Junwen Tan , Jinglin Liang , Hongyuan Chen , Shuangping Huang

Fine-grained and efficient controllability on video diffusion transformers has raised increasing desires for the applicability. Recently, In-context Conditioning emerged as a powerful paradigm for unified conditional video generation, which…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Xuanhua He , Quande Liu , Zixuan Ye , Weicai Ye , Qiulin Wang , Xintao Wang , Qifeng Chen , Pengfei Wan , Di Zhang , Kun Gai

Flow matching with $x$-prediction -- regressing the clean data point rather than the ambient velocity -- is known to exploit low-dimensional manifold structure effectively in pixel space \cite{li2025back}. We ask whether a pretrained…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Le Zhang , Ning Mang , Aishwarya Agrawal

Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion},…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Aiyue Chen , Bin Dong , Jingru Li , Jing Lin , Kun Tian , Yiwu Yao , Gongyi Wang

Diffusion models have demonstrated a remarkable ability in Text-to-Image (T2I) generation applications. Despite the advanced generation output, they suffer from heavy computation overhead, especially for large models that contain tens of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Desen Sun , Jason Hon , Jintao Zhang , Sihang Liu

One of the main drawback of diffusion models is the slow inference time for image generation. Among the most successful approaches to addressing this problem are distillation methods. However, these methods require considerable…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Senmao Li , Taihang Hu , Joost van de Weijer , Fahad Shahbaz Khan , Tao Liu , Linxuan Li , Shiqi Yang , Yaxing Wang , Ming-Ming Cheng , Jian Yang

Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Zechuan Zhang , Ji Xie , Yu Lu , Zongxin Yang , Yi Yang

Diffusion models have demonstrated impressive generation capabilities, particularly with recent advancements leveraging transformer architectures to improve both visual and artistic quality. However, Diffusion Transformers (DiTs) continue…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Hui Zhang , Tingwei Gao , Jie Shao , Zuxuan Wu

The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Shufan Li , Konstantinos Kallidromitis , Akash Gokul , Arsh Koneru , Yusuke Kato , Kazuki Kozuka , Aditya Grover

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Junyi Wu , Zhiteng Li , Zheng Hui , Yulun Zhang , Linghe Kong , Xiaokang Yang

In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applications. Furthermore, with hardware advancements, a wide range…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Aiyue Chen , Yaofu Liu , Junjian Huang , Guang Lian , Yiwu Yao , Wangli Lan , Jing Lin , Zhixin Ma , Tingting Zhou

The steep computational cost of diffusion models at inference hinders their use as fast physics emulators. In the context of image and video generation, this computational drawback has been addressed by generating in the latent space of an…

Machine Learning · Computer Science 2025-11-04 François Rozet , Ruben Ohana , Michael McCabe , Gilles Louppe , François Lanusse , Shirley Ho

Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT); however, the autoencoder component has barely evolved.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Boyang Zheng , Nanye Ma , Shengbang Tong , Saining Xie
‹ Prev 1 8 9 10 Next ›