Related papers: P$^2$U: Progressive Precision Update For Efficient…
The recent focus on the efficiency of deep neural networks (DNNs) has led to significant work on model compression approaches, of which weight pruning is one of the most popular. At the same time, there is rapidly-growing computational…
While current high-resolution depth estimation methods achieve strong results, they often suffer from computational inefficiencies due to reliance on heavyweight models and multiple inference steps, increasing inference time. To address…
We propose a new compressive imaging method for reconstructing 2D or 3D objects from their scattered wave-field measurements. Our method relies on a novel, nonlinear measurement model that can account for the multiple scattering phenomenon,…
Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained…
In recent years, diffusion models have demonstrated remarkable success in high-fidelity image synthesis. However, fine-tuning these models for specialized domains, such as medical imaging, remains challenging due to limited domain-specific…
Based on the model's resilience to computational noise, model quantization is important for compressing models and improving computing speed. Existing quantization techniques rely heavily on experience and "fine-tuning" skills. In the…
Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…
The fundamental success of large language models hinges upon the efficacious implementation of large-scale distributed training techniques. Nevertheless, building a vast, high-performance cluster featuring high-speed communication…
Wireless communications for status update are becoming increasingly important, especially for machine-type control applications. Existing work has been mainly focused on Age of Information (AoI) optimizations. In this paper, a status-aware…
Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and…
Diffusion probabilistic models have recently achieved remarkable success in generating high-quality images. However, balancing high perceptual quality and low distortion remains challenging in application of diffusion models in image…
In wireless Internet of things (IoT), the sensors usually have limited bandwidth and power resources. Therefore, in a distributed setup, each sensor should compress and quantize the sensed observations before transmitting them to a fusion…
Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get…
This paper addresses distributed parameter estimation in stochastic dynamic systems with quantized measurements, constrained by quantized communication and Markovian switching directed topologies. To enable accurate recovery of the original…
Approximating model predictive control (MPC) using imitation learning (IL) allows for fast control without solving expensive optimization problems online. However, methods that use neural networks in a simple L2-regression setup fail to…
Phasor measurement units (PMUs) have the advantage of providing direct measurements of power states. However, as the number of PMUs in a power system is limited, the traditional supervisory control and data acquisition (SCADA) system cannot…
LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To…
Text-to-image diffusion models are computationally intensive, often requiring dozens of forward passes through large transformer backbones. For instance, Stable Diffusion XL generates high-quality images with 50 evaluations of a…
This paper presents an IoT cloud-based state estimation system for distribution networks in which the PMUs (Phasor Measurement Units) are virtualized with respect to the physical devices. In the considered system only application level…
The recent progress made in large language models (LLMs) has brought tremendous application prospects to the world. The growing model size demands LLM training on multiple GPUs, while data parallelism is the most popular distributed…