相关论文: EC-Diff: Fast and High-Quality Edge-Cloud Collabor…

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free guidance (CFG) is the de facto choice in modern systems and achieves this by contrasting…

Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making…

Diffusion models (DMs) have emerged as powerful tools for high-quality content generation, yet their intensive computational requirements for inference pose challenges for resource-constrained edge devices. Cloud-based solutions aid in…

The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…

Image super-resolution is a fundamentally ill-posed problem because multiple valid high-resolution images exist for one low-resolution image. Super-resolution methods based on diffusion probabilistic models can deal with the ill-posed…

Social recommendation has emerged as a powerful approach to enhance personalized recommendations by leveraging the social connections among users, such as following and friend relations observed in online social platforms. The fundamental…

Deploying Vision Transformers on edge devices is challenging due to their high computational complexity, while full offloading to cloud resources presents significant latency overheads. We propose a novel collaborative inference framework,…

This paper studies inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing. To ensure inference accuracy in inference task partitioning, we consider the receptive-field when performing…

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the…

Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect…

While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation…

Autism Spectrum Disorder (ASD) diagnosis systems in school environments increasingly relies on IoT-enabled cameras, yet pure cloud processing raises privacy and latency concerns while pure edge inference suffers from limited accuracy. We…

A novel accelerated mobile edge generation (MEG) framework is proposed for generating high-resolution images on mobile devices. Exploiting a large-scale latent diffusion model (LDM) distributed across edge server (ES) and user equipment…

Efficient video generation models are increasingly vital for multimedia synthetic content generation. Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality…

The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…

With the impressive generative capabilities of diffusion models, personalized content synthesis has emerged as the most highly anticipated. However, the large model sizes and iterative nature of inference make it difficult to deploy…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion…