Related papers: A Tiny Supervised ODL Core with Auto Data Pruning …

Recognizing Activities of Daily Living (ADLs) has a large number of health applications, such as characterize lifestyle for habit improvement, nursing and rehabilitation services. Wearable cameras can daily gather large amounts of image…

Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the…

Detecting out-of-distribution (OOD) samples is an essential requirement for the deployment of machine learning systems in the real world. Until now, research on energy-based OOD detectors has focused on the softmax confidence score from a…

Optical neural networks (ONNs) have demonstrated record-breaking potential in high-performance neuromorphic computing due to their ultra-high execution speed and low energy consumption. However, current learning protocols fail to provide…

Automated and accurate human activity recognition (HAR) using body-worn sensors enables practical and cost efficient remote monitoring of Activity of DailyLiving (ADL), which are shown to provide clinical insights across multiple…

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

DTMM is a library designed for efficient deployment and execution of machine learning models on weak IoT devices such as microcontroller units (MCUs). The motivation for designing DTMM comes from the emerging field of tiny machine learning…

This paper introduces an effective solution for retrofitting construction power tools with low-power IoT to enable accurate activity classification. We address the challenge of distinguishing between when a power tool is being moved and…

Online multiple kernel learning (OMKL) has provided an attractive performance in nonlinear function learning tasks. Leveraging a random feature approximation, the major drawback of OMKL, known as the curse of dimensionality, has been…

To overcome the burden on the memory size and bandwidth due to ever-increasing size of large language models (LLMs), aggressive weight quantization has been recently studied, while lacking research on quantizing activations. In this paper,…

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Token reduction accelerates Multimodal Large Language Models (MLLMs) by reducing excessive tokens, but overlooks structural redundancy differences, where critical and redundant modules process identical token loads. For fine-grained…

In the last few years, research and development on Deep Learning models and techniques for ultra-low-power devices in a word, TinyML has mainly focused on a train-then-deploy assumption, with static models that cannot be adapted to newly…

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…

In recent years, deep neural networks (DNNs) have been found very successful for multi-label classification (MLC) of remote sensing (RS) images. Self-supervised pre-training combined with fine-tuning on a randomly selected small training…

This work aims to enable on-device training of convolutional neural networks (CNNs) by reducing the computation cost at training time. CNN models are usually trained on high-performance computers and only the trained models are deployed to…

Supervised training of optical flow predictors generally yields better accuracy than unsupervised training. However, the improved performance comes at an often high annotation cost. Semi-supervised training trades off accuracy against…

On-device machine learning (ODML) enables intelligent applications on resource-constrained devices. However, power consumption poses a major challenge, forcing a trade-off between model accuracy and power efficiency that often limits model…

Low power deep learning accelerators on the speech processing enable real-time applications on edge devices. However, most of the existing accelerators suffer from high power consumption and focus on image applications only. This paper…

Training deep learning models on in-home IoT sensory data is commonly used to recognise human activities. Recently, federated learning systems that use edge devices as clients to support local human activity recognition have emerged as a…