118 citations · 485 across the 63 of their papers we have counts for
63 papers
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports
Beatrice Alessandra Motetti, Emilien Guandalino, Daniele Jahier Pagliari +4
In the current artificial intelligence-driven innovation era, the pace of knowledge growth is accelerating, and is hard to keep up with. While generative models are increasingly us…
MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor
Beatrice Alessandra Motetti, Tanguy Dugas du Villard, Matteo Risso +7
Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems. In this letter, we describe a smart multi-pix…
A Hardware-oriented Approach for Efficient Bayesian Inference Computation and Deployment
Nikola Pižurica, Matteo Risso, Nikola Milović +4
Bayesian inference provides a principled foundation for reasoning under uncertainty, but its computational cost hinders deployment on resource-constrained edge devices. In this pap…
Before Parc Fermé: RL-Time Pruning for Efficient Embodied LLMs in Autonomous Driving
Luca Benfenati, Ali Azimi, Matteo Risso +3
Embodied Large Language Models (LLMs) are increasingly used as reasoning modules in robotic control pipelines to improve human-robot interaction, but their memory and generation la…
End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables
Francesco Carlucci, Giovanni Pollo, Xiaying Wang +6
Photoplethysmography (PPG)-based blood pressure (BP) estimation is a challenging task, particularly on resource-constrained wearable devices. However, fully on-board processing is…
Late Breaking Results: CHESSY: Coupled Hybrid Emulation with SystemC-FPGA Synchronization
Lorenzo Ruotolo, Giovanni Pollo, Mohamed Amine Hamdi +7
The growing complexity of cyber-physical systems (CPSs) calls for early prototyping tools that combine accuracy, speed, and usability. Virtual Platforms (VPs) provide fast function…
MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs
Enrico Russo, Mohamed Amine Hamdi, Alessandro Ottaviano +6
Deploying DNNs on System-on-Chips (SoC) with multiple heterogeneous acceleration engines is challenging, and the majority of deployment frameworks cannot fully exploit heterogeneit…
BlankSkip: Early-exit Object Detection onboard Nano-drones
Carlo Marra, Beatrice Alessandra Motetti, Alessio Burrello +3
Deploying tiny computer vision Deep Neural Networks (DNNs) on-board nano-sized drones is key for achieving autonomy, but is complicated by the extremely tight constraints of their…
TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge
Run Wang, Victor J. B. Jung, Philip Wiese +3
On-device tuning of deep neural networks enables long-term adaptation at the edge while preserving data privacy. However, the high computational and memory demands of backpropagati…
Improving Continual Learning for Gaussian Splatting based Environments Reconstruction on Commercial Off-the-Shelf Edge Devices
Ivan Zaino, Matteo Risso, Daniele Jahier Pagliari +3
Novel view synthesis (NVS) is increasingly relevant for edge robotics, where compact and incrementally updatable 3D scene models are needed for SLAM, navigation, and inspection und…
SilentWear: an Ultra-Low Power Wearable System for EMG-based Silent Speech Recognition
Giusy Spacone, Sebastian Frey, Giovanni Pollo +5
Detecting speech from biosignals is gaining increasing attention due to the potential to develop human-computer interfaces that are noise-robust, privacy-preserving, and scalable f…
OnDA: On-device Channel Pruning for Efficient Personalized Keyword Spotting
Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari
Always-on keyword spotting (KWS) demands on-device adaptation to cope with user- and environment-specific distribution shifts under tight latency and energy budgets. This paper pro…
Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold
Luca Benfenati, Matteo Risso, Andrea Vannozzi +5
Key-value (KV) caching enables fast autoregressive decoding but at long contexts becomes a dominant bottleneck in High Bandwidth Memory (HBM) capacity and bandwidth. A common mitig…
Integrating SystemC TLM into FMI 3.0 Co-Simulations with an Open-Source Approach
Andrei Mihai Albu, Giovanni Pollo, Alessio Burrello +6
The growing complexity of cyber-physical systems, particularly in automotive applications, has increased the demand for efficient modeling and cross-domain co-simulation techniques…
Automatic integration of SystemC in the FMI standard for Software-defined Vehicle design
Giovanni Pollo, Andrei Mihai Albu, Alessio Burrello +6
The recent advancements of the automotive sector demand robust co-simulation methodologies that enable early validation and seamless integration across hardware and software domain…
MEbots: Integrating a RISC-V Virtual Platform with a Robotic Simulator for Energy-aware Design
Giovanni Pollo, Mohamed Amine Hamdi, Matteo Risso +9
Virtual Platforms (VPs) enable early software validation of autonomous systems' electronics, reducing costs and time-to-market. While many VPs support both functional and non-funct…
Fused-Tiled Layers: Minimizing Data Movement on RISC-V SoCs with Software-Managed Caches
Victor J. B. Jung, Alessio Burrello, Francesco Conti +1
The success of DNNs and their high computational requirements pushed for large codesign efforts aiming at DNN acceleration. Since DNNs can be represented as static computational gr…
V-Seek: Accelerating LLM Reasoning on Open-hardware Server-class RISC-V Platforms
Javier J. Poveda Rodrigo, Mohamed Amine Ahmdi, Alessio Burrello +2
The recent exponential growth of Large Language Models (LLMs) has relied on GPU-based systems. However, CPUs are emerging as a flexible and lower-cost alternative, especially when…
Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers
Francesco Daghero, Daniele Jahier Pagliari, Francesco Conti +3
The acceleration of pruned Deep Neural Networks (DNNs) on edge devices such as Microcontrollers (MCUs) is a challenging task, given the tight area- and power-constraints of these d…
Coupling Neural Networks and Physics Equations For Li-Ion Battery State-of-Charge Prediction
Giovanni Pollo, Alessio Burrello, Enrico Macii +3
Estimating the evolution of the battery's State of Charge (SoC) in response to its usage is critical for implementing effective power management policies and for ultimately improvi…
MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices
Mohamed Amine Hamdi, Francesco Daghero, Giuseppe Maria Sarda +6
Streamlining the deployment of Deep Neural Networks (DNNs) on heterogeneous edge platforms, coupling within the same micro-controller unit (MCU) instruction processors and hardware…
Building Damage Assessment in Conflict Zones: A Deep Learning Approach Using Geospatial Sub-Meter Resolution Data
Matteo Risso, Alessia Goffi, Beatrice Alessandra Motetti +6
Very High Resolution (VHR) geospatial image analysis is crucial for humanitarian assistance in both natural and anthropogenic crises, as it allows to rapidly identify the most crit…
Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables
Alessio Burrello, Francesco Carlucci, Giovanni Pollo +5
PPG-based Blood Pressure (BP) estimation is a challenging biosignal processing task for low-power devices such as wearables. State-of-the-art Deep Neural Networks (DNNs) trained fo…
Optimizing DNN Inference on Multi-Accelerator SoCs at Training-time
Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari
The demand for executing Deep Neural Networks (DNNs) with low latency and minimal power consumption at the edge has led to the development of advanced heterogeneous Systems-on-Chip…