English
Related papers

Related papers: SoftCap: Soft-Budget Control for Diffusion Transfo…

200 papers

Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative sampling process. While feature caching techniques achieve effective acceleration at higher step…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Benlei Cui , Shaoxuan He , Bukun Huang , Zhizeng Ye , Yunyun Sun , Longtao Huang , Hui Xue , Yang Yang , Jingqun Tang , Zhou Zhao , Haiwen Hong

Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for hundreds of function evaluations. Recent progress in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Tong Zhao , Mingkun Lei , Liangyu Yuan , Yanming Yang , Chenxi Song , Yang Wang , Beier Zhu , Chi Zhang

Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. However, these attributions also hinder the practical deployment…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Kai Liu , Shaoqiu Zhang , Linghe Kong , Yulun Zhang

Diffusion Transformers (DiTs) achieve remarkable performance within image generation via the transformer architecture. Conventionally, DiTs are constructed by stacking serial isotropic global modeling transformers, which face significant…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Jiafu Wu , Yabiao Wang , Jian Li , Jinlong Peng , Yun Cao , Chengjie Wang , Jiangning Zhang

We introduce SteeringDiffusion, a bottlenecked activation-level control interface for diffusion models that exposes a smooth, monotonic, and runtime-adjustable control surface over the content--style trade-off. Our method keeps the U-Net…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Fangzheng Wu , Brian Summa

Deploying a deep learning model on mobile/IoT devices is a challenging task. The difficulty lies in the trade-off between computation speed and accuracy. A complex deep learning model with high accuracy runs slowly on resource-limited…

Computer Vision and Pattern Recognition · Computer Science 2018-12-31 Xin Li , Shuai Zhang , Bolan Jiang , Yingyong Qi , Mooi Choo Chuah , Ning Bi

Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Chun-Mei Feng , Kai Yu , Yong Liu , Salman Khan , Wangmeng Zuo

Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their computational demands, particularly the quadratic complexity of attention mechanisms and…

Machine Learning · Computer Science 2026-01-28 Jinming Lou , Wenyang Luo , Yufan Liu , Bing Li , Xinmiao Ding , Weiming Hu , Yuming Li , Chenguang Ma

Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial control. However, existing methods either train separate models…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Yucheng Xie , Fu Feng , Ruixiao Shi , Jing Wang , Yong Rui , Xin Geng

Neural networks commonly execute on hardware accelerators such as NPUs and GPUs for their size and computation overhead. These accelerators are costly and it is hard to scale their resources to handle real-time workload fluctuations. We…

Machine Learning · Computer Science 2025-10-06 Jaemin Kim , Hongjun Um , Sungkyun Kim , Yongjun Park , Jiwon Seo

We study inference-time scaling for diffusion models, where the goal is to adapt a pre-trained model to new target distributions without retraining. Existing guidance-based methods are simple but introduce bias, while particle-based…

Machine Learning · Computer Science 2026-02-24 Yinuo Ren , Wenhao Gao , Lexing Ying , Grant M. Rotskoff , Jiequn Han

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive language generation due to their potential for parallel decoding and global refinement of the entire sequence. To unlock this potential, DLM…

Machine Learning · Computer Science 2026-04-20 Xiang Xia , Wuyang Zhang , Jiazheng Liu , Cheng Yan , Yanyong Zhang

Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Chao Xu , Maohua Li , Qirui Li , Yixuan Xu , Yanke Zhou , Yunhe Li , Cuifeng Shen , Hanlin Tang , Kan Liu , Tao Lan , Lin Qu , Shao-Qun Zhang

Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decoding mitigates this by rechecking earlier tokens, yet we…

Computation and Language · Computer Science 2026-02-09 Yanzheng Xiang , Lan Wei , Yizhen Yao , Qinglin Zhu , Hanqi Yan , Chen Jin , Philip Alexander Teare , Dandan Zhang , Lin Gui , Amrutha Saseendran , Yulan He

Diffusion Transformers (DiTs) have achieved state-of-the-art video generation quality, but they incur immense computational cost because standard inference applies the same number of denoising steps uniformly to every token in the sequence.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Ernie Chu , Vishal M. Patel

Future servers will incorporate many active lowpower modes for different system components, such as cores and memory. Though these modes provide flexibility for power management via Dynamic Voltage and Frequency Scaling (DVFS), they must be…

Performance · Computer Science 2016-03-07 Yanpei Liu , Guilherme Cox , Qingyuan Deng , Stark C. Draper , Ricardo Bianchini

Recent research arXiv:2410.15027 arXiv:2410.23775 has highlighted the inherent in-context generation capabilities of pretrained diffusion transformers (DiTs), enabling them to seamlessly adapt to diverse visual tasks with minimal or no…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Lianghua Huang , Wei Wang , Zhi-Fan Wu , Yupeng Shi , Chen Liang , Tong Shen , Han Zhang , Huanzhang Dou , Yu Liu , Jingren Zhou

A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a…

Machine Learning · Computer Science 2026-04-10 Jinhong Lin , Pan Wang , Zitong Zhan , Lin Zhang , Pedro Morgado

3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models for high-fidelity reconstruction. However, their multi-step…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Wenzhe He , Xiaojun Chen , Ruiqi Wang , Ruihui Li , Huilong Pi , Jiapeng Zhang , Zhuo Tang , Kenli Li

Action diffusion excels at high-fidelity action generation but incurs heavy computational costs owing to its iterative denoising nature. Despite current technologies showing promise in accelerating diffusion transformers by reusing the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Kangye Ji , Yuan Meng , Jianbo Zhou , Ye Li , Chen Tang , Zhi Wang