Related papers: DeDelayed: Deleting Remote Inference Delay via On-…
Recent years have witnessed the great success of vision transformer (ViT), which has achieved state-of-the-art performance on multiple computer vision benchmarks. However, ViT models suffer from vast amounts of parameters and high…
The quality of the video stream is key to neural network-based video analytics. However, low-quality video is inevitably collected by existing surveillance systems because of poor quality cameras or over-compressed/pruned video streaming…
We present StreamDEQ, a method that aims to infer frame-wise representations on videos with minimal per-frame computation. Conventional deep networks do feature extraction from scratch at each frame in the absence of ad-hoc solutions. We…
We consider the problem of detecting objects, as they come into view, from videos in an online fashion. We provide the first real-time solution that is guaranteed to minimize the delay, i.e., the time between when the object comes in view…
Learning to defer uncertain predictions to costly experts offers a powerful strategy for improving the accuracy and efficiency of machine learning systems. However, standard training procedures for deferral algorithms typically require…
Video diffusion models have recently made great progress in generation quality, but are still limited by the high memory and computational requirements. This is because current video diffusion models often attempt to process…
A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…
Video prediction is a fundamental task for various downstream applications, including robotics and world modeling. Although general video prediction models have achieved remarkable performance in standard scenarios, occlusion is still an…
Modern computationally-intensive applications often operate under time constraints, necessitating acceleration methods and distribution of computational workloads across multiple entities. However, the outcome is either achieved within the…
Making accurate forecasts for a complex system is a challenge in various practical applications. The major difficulty in solving such a problem concerns nonlinear spatiotemporal dynamics with time-varying characteristics. Takens' delay…
Delays endanger safety of autonomous systems operating in a rapidly changing environment, such as nondeterministic surrounding traffic participants in autonomous driving and high-speed racing. Unfortunately, delays are typically not…
Federated learning (FL) is a collaborative machine learning paradigm, which enables deep learning model training over a large volume of decentralized data residing in mobile devices without accessing clients' private data. Driven by the…
Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…
The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution. For time series modeling, most existing works make some unrealistic assumptions such as the input…
The paper presents an efficient real-time scheduling algorithm for intelligent real-time edge services, defined as those that perform machine intelligence tasks, such as voice recognition, LIDAR processing, or machine vision, on behalf of…
Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing…
Unpredictable sensor-to-estimator delays fundamentally distort what matters for wireless remote state estimation: not just freshness, but how delay interacts with sensor informativeness and energy efficiency. In this paper, we present a…
Recently proposed pyramidal models decompose the conventional forward and backward diffusion processes into multiple stages operating at varying resolutions. These models handle inputs with higher noise levels at lower resolutions, while…
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient…
Deep Neural Networks are allowing mobile devices to incorporate a wide range of features into user applications. However, the computational complexity of these models makes it difficult to run them effectively on resource-constrained mobile…