Related papers: AdaptiveLoad: Towards Efficient Video Diffusion Tr…

Mixture-of-Experts (MoE) has emerged as a promising approach to scale up deep learning models due to its significant reduction in computational resources. However, the dynamic nature of MoE leads to load imbalance among experts, severely…

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop…

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…

Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory…

In the domain of multimedia and multimodal processing, the efficient handling of diverse data streams such as images, video, and sensor data is paramount. Model compression and multitask learning (MTL) are crucial in this field, offering…

In recent years, there has been a significant surge of interest in unifying image comprehension and generation within Large Language Models (LLMs). This growing interest has prompted us to explore extending this unification to videos. The…

This paper studies deep network architectures to address the problem of video classification. A multi-stream framework is proposed to fully utilize the rich multimodal information in videos. Specifically, we first train three Convolutional…

Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems. This paper studied an optimal divisible load distribution sequencing problem using a machine learning framework. The problem is…

Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we…

To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the…

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…

In light of recent progress in video editing, deep learning models focusing on both spatial and temporal dependencies have emerged as the primary method. However, these models suffer from the quadratic computational complexity of…

Recent advancements in Diffusion Transformer (DiT) models have significantly improved 3D point cloud generation. However, existing methods primarily focus on local feature extraction while overlooking global topological information, such as…

Demand for 2K video synthesis is rising with increasing consumer expectations for ultra-clear visuals. While diffusion transformers (DiTs) have demonstrated remarkable capabilities in high-quality video generation, scaling them to 2K…

Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…

It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an effective approach for improving device utilization. However,…

Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently. While prior work has…

Visual instruction datasets from various distributors are released at different times and often contain a significant number of semantically redundant text-image pairs, depending on their task compositions (i.e., skills) or reference…

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…