Alert button
Picture for Stylianos I. Venieris

Stylianos I. Venieris

Alert button

LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms

Nov 19, 2023
Young D. Kwon, Jagmohan Chauhan, Hong Jia, Stylianos I. Venieris, Cecilia Mascolo

Viaarxiv icon

Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads

Oct 17, 2023
Hongxiang Fan, Stylianos I. Venieris, Alexandros Kouris, Nicholas D. Lane

Figure 1 for Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads
Figure 2 for Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads
Figure 3 for Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads
Figure 4 for Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads
Viaarxiv icon

Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation

Jul 25, 2023
Stylianos I. Venieris, Javier Fernandez-Marques, Nicholas D. Lane

Figure 1 for Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation
Figure 2 for Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation
Figure 3 for Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation
Figure 4 for Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation
Viaarxiv icon

TinyTrain: Deep Neural Network Training at the Extreme Edge

Jul 19, 2023
Young D. Kwon, Rui Li, Stylianos I. Venieris, Jagmohan Chauhan, Nicholas D. Lane, Cecilia Mascolo

Figure 1 for TinyTrain: Deep Neural Network Training at the Extreme Edge
Figure 2 for TinyTrain: Deep Neural Network Training at the Extreme Edge
Figure 3 for TinyTrain: Deep Neural Network Training at the Extreme Edge
Figure 4 for TinyTrain: Deep Neural Network Training at the Extreme Edge
Viaarxiv icon

MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge

Jun 22, 2023
Sokratis Nikolaidis, Stylianos I. Venieris, Iakovos S. Venieris

Figure 1 for MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge
Figure 2 for MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge
Figure 3 for MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge
Figure 4 for MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge
Viaarxiv icon

Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices

Jun 20, 2023
Ioannis Panopoulos, Sokratis Nikolaidis, Stylianos I. Venieris, Iakovos S. Venieris

Figure 1 for Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices
Figure 2 for Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices
Figure 3 for Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices
Figure 4 for Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices
Viaarxiv icon

NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution

Dec 15, 2022
Stylianos I. Venieris, Mario Almeida, Royson Lee, Nicholas D. Lane

Figure 1 for NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution
Figure 2 for NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution
Figure 3 for NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution
Figure 4 for NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution
Viaarxiv icon

Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation

Dec 15, 2022
Royson Lee, Rui Li, Stylianos I. Venieris, Timothy Hospedales, Ferenc Huszár, Nicholas D. Lane

Figure 1 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Figure 2 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Figure 3 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Figure 4 for Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Viaarxiv icon

The Future of Consumer Edge-AI Computing

Oct 19, 2022
Stefanos Laskaridis, Stylianos I. Venieris, Alexandros Kouris, Rui Li, Nicholas D. Lane

Figure 1 for The Future of Consumer Edge-AI Computing
Figure 2 for The Future of Consumer Edge-AI Computing
Figure 3 for The Future of Consumer Edge-AI Computing
Viaarxiv icon

Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs

Sep 27, 2022
Alexandros Kouris, Stylianos I. Venieris, Stefanos Laskaridis, Nicholas D. Lane

Figure 1 for Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs
Figure 2 for Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs
Figure 3 for Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs
Figure 4 for Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs
Viaarxiv icon