English
Related papers

Related papers: SeaCache: Spectral-Evolution-Aware Cache for Accel…

200 papers

Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Dong Liu , Yanxuan Yu , Ben Lengerich , Ying Nian Wu

Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transformers (DiTs) pose a significant challenge to their practical deployment. While feature…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Peiliang Cai , Jiacheng Liu , Haowen Xu , Xinyu Wang , Chang Zou , Linfeng Zhang

The rapid advancement of single-cell ATAC sequencing (scATAC-seq) technologies holds great promise for investigating the heterogeneity of epigenetic landscapes at the cellular level. The amplification process in scATAC-seq experiments often…

Genomics · Quantitative Biology 2024-08-28 Lei Huang , Lei Xiong , Na Sun , Zunpeng Liu , Ka-Chun Wong , Manolis Kellis

The rapid progress in generative models has given rise to the critical task of AI-Generated Content Stealth (AIGC-S), which aims to create AI-generated images that can evade both forensic detectors and human inspection. This task is crucial…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Ziyin Zhou , Ke Sun , Zhongxi Chen , Huafeng Kuang , Xiaoshuai Sun , Rongrong Ji

Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or…

Machine Learning · Computer Science 2025-09-22 Haoran Zhao , Tong Bai , Lei Huang , Xiaoyu Liang

Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E$^2$-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching) to accelerate frequency…

Machine Learning · Computer Science 2026-04-28 Dong Liu , Haisheng Wang , Yanxuan Yu

Diffusion models have achieved remarkable generative quality but remain bottlenecked by costly iterative sampling. Recent training-free methods accelerate diffusion process by reusing model outputs. However, these methods ignore denoising…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Jiajian Xie , Hubery Yin , Chen Li , Zhou Zhao , Shengyu Zhang

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 trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address this, we propose SCoRe (Spectral Cutoff Regeneration), a training-free, generation-time…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Yuta Matsuzaki , Seiichi Uchida , Shumpei Takezaki

The feedforward selective fixed-filter method selects the most suitable pre-trained control filter based on the spectral features of the detected reference signal, effectively avoiding slow convergence in conventional adaptive algorithms.…

Signal Processing · Electrical Eng. & Systems 2025-08-04 Hong-Cheng Liang , Man-Wai Mak , Kong Aik Lee

We introduce a model-agnostic forward diffusion process for time-series forecasting that decomposes signals into spectral components, preserving structured temporal patterns such as seasonality more effectively than standard diffusion.…

Machine Learning · Statistics 2026-02-17 Francisco Caldas , Sahil Kumar , Cláudia Soares

Diffusion Transformers (DiTs) have demonstrated remarkable generative capabilities, particularly benefiting from Transformer architectures that enhance visual and artistic fidelity. However, their inherently sequential denoising process…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Hanqi Chen , Xu Zhang , Xiaoliu Guan , Lielin Jiang , Guanzhong Wang , Zeyu Chen , Yi Liu

Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Carlos Esteves , Ameesh Makadia

Feature caching approaches accelerate diffusion transformers (DiTs) by storing the output features of computationally expensive modules at certain timesteps, and exploiting them for subsequent steps to reduce redundant computations. Recent…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Byunggwan Son , Jeimin Jeon , Jeongwoo Choi , Bumsub Ham

In cost-sensitive deployments, RAID arrays may combine SSDs with different performance levels. Such heterogeneity arises when aging SSDs degrade yet remain usable, or when failed drives are replaced with new devices of explicitly better…

Operating Systems · Computer Science 2026-04-03 Jialin Liu , Liang Shi , Dingcui Yu

Despite the potential of diffusion models in speech enhancement, their deployment in Acoustic Echo Cancellation (AEC) has been restricted. In this paper, we propose DI-AEC, pioneering a diffusion-based stochastic regeneration approach…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-10 Yang Liu , Li Wan , Yun Li , Yiteng Huang , Ming Sun , James Luan , Yangyang Shi , Xin Lei

Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Guanjie Chen , Xinyu Zhao , Yucheng Zhou , Xiaoye Qu , Tianlong Chen , Yu Cheng

Marine obstacle detection demands robust segmentation under challenging conditions, such as sun glitter, fog, and rapidly changing wave patterns. These factors degrade image quality, while the scarcity and structural repetition of marine…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Miaohua Zhang , Mohammad Ali Armin , Xuesong Li , Sisi Liang , Lars Petersson , Changming Sun , David Ahmedt-Aristizabal , Zeeshan Hayder

Autoregressive models, often built on Transformer architectures, represent a powerful paradigm for generating ultra-long videos by synthesizing content in sequential chunks. However, this sequential generation process is notoriously slow.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Yuexiao Ma , Xuzhe Zheng , Jing Xu , Xiwei Xu , Feng Ling , Xiawu Zheng , Huafeng Kuang , Huixia Li , Xing Wang , Xuefeng Xiao , Fei Chao , Rongrong Ji

This paper presents a practical approach for detecting non-stationarity in time series prediction. This method is called SAFE and works by monitoring the evolution of the spectral contents of time series through a distance function. This…

Machine Learning · Computer Science 2018-05-18 Arief Koesdwiady , Fakhri Karray