Related papers: TinyD\'ej\`aVu: Smaller RAM and Faster Inference w…
The deployment of Quantized Neural Networks (QNNs) on resource-constrained edge devices, such as microcontrollers (MCUs), introduces fundamental challenges in balancing model performance, computational complexity, and memory constraints.…
Implicit neural video representations encode entire video sequences within the parameters of a neural network and enable constant time frame reconstruction. Recent work on Neural Representations for Videos (NeRV) has demonstrated…
Image segmentation is one of the major computer vision tasks, which is applicable in a variety of domains, such as autonomous navigation of an unmanned aerial vehicle. However, image segmentation cannot easily materialize on tiny embedded…
Among hardware accelerators for deep-learning inference, data flow implementations offer low latency and high throughput capabilities. In these architectures, each neuron is mapped to a dedicated hardware unit, making them well-suited for…
The growing number of low-power smart devices in the Internet of Things is coupled with the concept of "Edge Computing", that is moving some of the intelligence, especially machine learning, towards the edge of the network. Enabling machine…
IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persistent storage, which is orders of magnitude fewer…
Autonomous navigation typically relies on power-intensive processors, limiting accessibility in low-cost robotics. Although microcontrollers offer a resource-efficient alternative, they impose strict constraints on model complexity. We…
Quantized CNN inference on ultra-low-power MCUs incurs unnecessary computations in neurons that produce saturated output values. These values are too extreme and are eventually clamped to the boundaries allowed by the neuron. Often times,…
State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets.…
Memory optimization for deep neural network (DNN) inference gains high relevance with the emergence of TinyML, which refers to the deployment of DNN inference tasks on tiny, low-power microcontrollers. Applications such as audio keyword…
Current and future applications demand ultra-low latency and consistent throughput, yet frequently traverse 5G cellular networks, so cope with volatile packet dynamics, as 5G base station schedulers dynamically react to user workloads and…
Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…
Sliding window convolutional networks (ConvNets) have become a popular approach to computer vision problems such as image segmentation, and object detection and localization. Here we consider the problem of inference, the application of a…
Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…
Tiny machine learning (TinyML) is a rapidly growing field aiming to democratize machine learning (ML) for resource-constrained microcontrollers (MCUs). Given the pervasiveness of these tiny devices, it is inherent to ask whether TinyML…
Energy-harvesting technology provides a promising platform for future IoT applications. However, since communication is very expensive in these devices, applications will require inference "beyond the edge" to avoid wasting precious energy…
This paper describes a memory-efficient transformer model designed to drive a reduction in memory usage and execution time by substantial orders of magnitude without impairing the model's performance near that of the original model.…
On-device learning enables edge devices to continually adapt the AI models to new data, which requires a small memory footprint to fit the tight memory constraint of edge devices. Existing work solves this problem by reducing the number of…
On-device learning allows AI models to adapt to user data, thereby enhancing service quality on edge platforms. However, training AI on resource-limited devices poses significant challenges due to the demanding computing workload and the…
Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…