Related papers: ERTACache: Error Rectification and Timesteps Adjus…
Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained…
Diffusion models have achieved remarkable performance on a wide range of generative tasks, yet training them from scratch is notoriously resource-intensive, typically requiring millions of training images and many GPU days. Motivated by a…
In this paper, we propose a more refined video segment based Mobile Edge Computing (MEC) enhanced cache update strategy, which takes into account the client's playback status and transmission state, MEC cache capacity and the popularity of…
Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard…
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…
Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition…
Diffusion-based text-to-image generation models trade latency for quality: small models are fast but generate lower-quality images, while large models produce better images but are slow. We present MoDM, a novel caching-based serving system…
In this paper, we proposed an effective and efficient multi-core shared-cache design optimization approach based on reuse-distance analysis of the data traces of target applications. Since data traces are independent of system hardware…
Hiding data using neural networks (i.e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks. However, the potential of data hiding in diffusion models remains…
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses…
The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models…
Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…
Although diffusion models (DMs) have shown promising performances in a number of tasks (e.g., speech synthesis and image generation), they might suffer from error propagation because of their sequential structure. However, this is not…
Video enhancement is a challenging problem, more than that of stills, mainly due to high computational cost, larger data volumes and the difficulty of achieving consistency in the spatio-temporal domain. In practice, these challenges are…
The disaggregated memory (DM) architecture offers high resource elasticity at the cost of data access performance. While caching frequently accessed data in compute nodes (CNs) reduces access overhead, it requires costly centralized…
The cache plays a key role in determining the performance of applications, no matter for sequential or concurrent programs on homogeneous and heterogeneous architecture. Fixing cache misses requires to understand the origin and the type of…
Text-to-video diffusion models deliver impressive results but remain slow because of the sequential denoising of 3D latents. Existing approaches to speed up inference either require expensive model retraining or use heuristic-based step…
Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference, limiting practical applications. Existing acceleration methods for general diffusion models fail to exploit the temporal and…
Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In this paper, we rethink that the redundancy in inversion-based…
A simultaneously transmitting and reflecting surface (STARS) enabled edge caching system is proposed for reducing backhaul traffic and ensuring the quality of service. A novel Caching-at-STARS structure, where a dedicated smart controller…