Related papers: SynerDiff: Synergetic Continuous Batching for Fast…

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question:…

We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection between the quality of generation and the representations…

Video Frame Interpolation (VFI) is a fundamental yet challenging task in computer vision, particularly under conditions involving large motion, occlusion, and lighting variation. Recent advancements in event cameras have opened up new…

The network edge's role in Artificial Intelligence (AI) inference processing is rapidly expanding, driven by a plethora of applications seeking computational advantages. These applications strive for data-driven efficiency, leveraging…

The Mixture of Experts (MoE) models are emerging as the latest paradigm for Large Language Models (LLMs). However, due to memory constraints, MoE models with billions or even trillions of parameters can only be deployed in multi-GPU or even…

Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further…

Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems with near-data processing (NDP) capabilities that offload…

Generative models often treat continuous data and discrete events as separate processes, creating a gap in modeling complex systems where they interact synchronously. To bridge this gap, we introduce JointDiff, a novel diffusion framework…

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,…

The target duration of a synthesized human motion is a critical attribute that requires modeling control over the motion dynamics and style. Speeding up an action performance is not merely fast-forwarding it. However, state-of-the-art…

The ever-growing volume and decentralized nature of data, coupled with the need to harness it and extract knowledge, have led to the extensive use of distributed deep learning (DDL) techniques for training. These techniques rely on local…

Serving deep neural networks in latency critical interactive settings often requires GPU acceleration. However, the small batch sizes typical in online inference results in poor GPU utilization, a potential performance gap which GPU…

Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration…

Diffusion Transformers (DiTs) excel in generative tasks but face practical deployment challenges due to high inference costs. Feature caching, which stores and retrieves redundant computations, offers the potential for acceleration.…

Heterogeneity has grown in popularity both at the core and server level as a way to improve both performance and energy efficiency. However, despite these benefits, scheduling applications in heterogeneous machines remains challenging.…

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 has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

The next generation multibeam satellites open up a new way to design satellite communication channels with the full flexibility in bandwidth, transmit power and beam coverage management. In this paper, we exploit the flexible multibeam…

The exponential growth of wireless devices and stringent reliability requirements of emerging applications demand fundamental improvements in distributed channel access mechanisms for unlicensed bands. Current Wi-Fi systems, which rely on…

We propose XPipe, an efficient asynchronous pipeline model parallelism approach for multi-GPU DNN training. XPipe is designed to use multiple GPUs to concurrently and continuously train different parts of a DNN model. To improve GPU…