Related papers: Lightweight and Scalable Transfer Learning Framewo…

Heterogeneous device-edge-cloud computing infrastructures have become widely adopted in telecommunication operators and Wide Area Networks (WANs), offering multi-tier computational support for emerging intelligent services. With the rapid…

A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual…

Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference. In the latter, the inference process is unrolled in time and interpreted as a…

The increasing complexity and energy demands of deep learning models have highlighted the limitations of traditional computing architectures, especially for edge devices with constrained resources. Spiking Neural Networks (SNNs) offer a…

Implicit Neural Representations (INRs) are proving to be a powerful paradigm in unifying task modeling across diverse data domains, offering key advantages such as memory efficiency and resolution independence. Conventional deep learning…

Optical metasurfaces, consisting of subwavelength-scale meta-atom arrays, hold great promise to overcome fundamental limitations of conventional optics. Scalable nanomanufacturing of metasurfaces with high uniformity and reproducibility is…

Emerging Large Language Model (LLM) system patterns, such as disaggregated inference, Mixture-of-Experts (MoE) routing, and asynchronous reinforcement fine-tuning, require flexible point-to-point communication beyond simple collectives.…

This paper presents a framework for deep transfer learning, which aims to leverage information from multi-domain upstream data with a large number of samples $n$ to a single-domain downstream task with a considerably smaller number of…

In this paper, we explore a novel knowledge-transfer task, termed as Deep Model Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous models pre-trained from distinct sources and with diverse architectures,…

The accurate identification of wireless devices is critical for enabling automated network access monitoring and authenticated data communication in large-scale networks; e.g., IoT. RF fingerprinting has emerged as a solution for device…

Choice of load signature or feature space is one of the most fundamental design choices for non-intrusive load monitoring or energy disaggregation problem. Electrical power quantities, harmonic load characteristics, canonical transient and…

Various studies among side-channel attacks have tried to extract information through leakages from electronic devices to reach the instruction flow of some appliances. However, previous methods highly depend on the resolution of traced…

The evolution of Large Language Models from the Transformer architecture to models with trillions of parameters has shifted the primary bottleneck from model training to real time inference. Deploying these massive models is a complex…

Fine-tuning the deep convolution neural network(CNN) using a pre-trained model helps transfer knowledge learned from larger datasets to the target task. While the accuracy could be largely improved even when the training dataset is small,…

Energy disaggregation refers to the decomposition of energy use time series data into its constituent loads. This paper decomposes daily use data of a household unit into fixed loads and one or more classes of shiftable loads. The latter is…

Deep learning (DL) has introduced a new paradigm in multiple-input multiple-output (MIMO) detection, balancing performance and complexity. However, the practical deployment of DL-based detectors is hindered by poor generalization,…

In the residential sector, electric water heaters are appliances with a relatively high power consumption and a significant thermal inertia, which is particularly suitable for Demand Response schemes. The success of efficient DR schemes via…

Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often demands complex training recipes and careful data balancing. We…

For learning with noisy labels, the transition matrix, which explicitly models the relation between noisy label distribution and clean label distribution, has been utilized to achieve the statistical consistency of either the classifier or…

In today's connected world, the generation of massive streaming data across diverse domains has become commonplace. In the presence of concept drift, class imbalance, label scarcity, and new class emergence, they jointly degrade…