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