Related papers: LightSAE: Parameter-Efficient and Heterogeneity-Aw…
Efficiently querying data on embedded sensor and IoT devices is challenging given the very limited memory and CPU resources. With the increasing volumes of collected data, it is critical to process, filter, and manipulate data on the edge…
Wearable sensors provide abundant physiological time series, yet the principles governing their predictive utility remain unclear. We hypothesize that temporal resolution is a fundamental axis of representation learning, with different…
In the era of the Internet of Things (IoT), where smartphones, built-in systems, wireless sensors, and nearly every smart device connect through local networks or the internet, billions of smart things communicate with each other and…
The Internet of Things (IoT) has been introduced as a breakthrough technology that integrates intelligence into everyday objects, enabling high levels of connectivity between them. As the IoT networks grow and expand, they become more…
Time series forecasting is important in many fields that require accurate predictions for decision-making. Patching techniques, commonly used and effective in time series modeling, help capture temporal dependencies by dividing the data…
While end-to-end multi-channel electroencephalography (EEG) learning approaches have shown significant promise, their applicability is often constrained in neurological diagnostics, such as intracranial EEG resources. When provided with a…
Internet of Things (IoT) devices generate heterogeneous data over time; and relying solely on individual data points is inadequate for accurate analysis. Segmentation is a common preprocessing step in many IoT applications, including…
Data is rapidly increasing in volume and velocity and the Internet of Things (IoT) is one important source of this data. The IoT is a collection of connected devices (things) which are constantly recording data from their surroundings using…
The rapid proliferation of the Internet of Things (IoT) has brought remarkable advancements to industries by enabling interconnected systems and intelligent automation. However, this exponential growth has also introduced significant…
Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments often face limited on-chip memory and severe workload imbalance; the prevalent use of offloading further incurs off-chip memory…
In the Industrial Internet of Things (IoT), a large amount of data will be generated every day. Due to privacy and security issues, it is difficult to collect all these data together to train deep learning models, thus the federated…
Recent advances in Earth Observation have focused on large-scale foundation models. However, these models are computationally expensive, limiting their accessibility and reuse for downstream tasks. In this work, we investigate compact…
Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable…
Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has…
Low-power and cost-effective IoT sensing nodes enable scalable monitoring of different environments. Some of these environments impose rough and extreme operating conditions, requiring continuous adaptation and reconfiguration of physical…
Currently, it is a hot research topic to realize accurate, efficient, and real-time identification of massive spectral data with the help of deep learning and IoT technology. Deep neural networks played a key role in spectral analysis.…
Sparse autoencoders (SAEs) are a promising approach to interpreting the internal representations of transformer language models. However, SAEs are usually trained separately on each transformer layer, making it difficult to use them to…
Accurate prediction of lithium-ion battery lifespan is vital for ensuring operational reliability and reducing maintenance costs in applications like electric vehicles and smart grids. This study presents a hybrid learning framework for…
The omnipresence of IoT devices in Industry 4.0 is expected to foster higher reliability, safety, and efficiency. However, interconnecting a large number of wireless devices without jeopardizing the system performance proves challenging. To…
Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the…