Stefanos Laskaridis
Stefanos Laskaridis
ML Researcher @ Brave
Verificeret mail på brave.com - Startside
Citeret af
Citeret af
SPINN: synergistic progressive inference of neural networks over device and cloud
S Laskaridis, SI Venieris, M Almeida, I Leontiadis, ND Lane
Proceedings of the 26th annual international conference on mobile computing …, 2020
Fjord: Fair and accurate federated learning under heterogeneous targets with ordered dropout
S Horvath, S Laskaridis, M Almeida, I Leontiadis, S Venieris, N Lane
Advances in Neural Information Processing Systems 34, 12876-12889, 2021
Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
S Laskaridis, A Kouris, ND Lane
Proceedings of the 5th International Workshop on Embedded and Mobile Deep …, 2021
EmBench: Quantifying performance variations of deep neural networks across modern commodity devices
M Almeida, S Laskaridis, I Leontiadis, SI Venieris, ND Lane
The 3rd international workshop on deep learning for mobile systems and …, 2019
HAPI: Hardware-aware progressive inference
S Laskaridis, SI Venieris, H Kim, ND Lane
Proceedings of the 39th International Conference on Computer-Aided Design, 1-9, 2020
Smart at what cost? characterising mobile deep neural networks in the wild
M Almeida, S Laskaridis, A Mehrotra, L Dudziak, I Leontiadis, ND Lane
Proceedings of the 21st ACM Internet Measurement Conference, 658-672, 2021
Multi-exit semantic segmentation networks
A Kouris, SI Venieris, S Laskaridis, N Lane
European Conference on Computer Vision, 330-349, 2022
Dyno: Dynamic onloading of deep neural networks from cloud to device
M Almeida, S Laskaridis, SI Venieris, I Leontiadis, ND Lane
ACM Transactions on Embedded Computing Systems 21 (6), 1-24, 2022
Shrinkml: End-to-end asr model compression using reinforcement learning
Ł Dudziak, MS Abdelfattah, R Vipperla, S Laskaridis, ND Lane
INTERSPEECH 2019, 2019
It's always personal: Using early exits for efficient on-device CNN personalisation
I Leontiadis, S Laskaridis, SI Venieris, ND Lane
Proceedings of the 22nd International Workshop on Mobile Computing Systems …, 2021
Fedoras: Federated architecture search under system heterogeneity
L Dudziak, S Laskaridis, J Fernandez-Marques
arXiv preprint arXiv:2206.11239, 2022
Federated learning for inference at anytime and anywhere
Z Liu, D Li, J Fernandez-Marques, S Laskaridis, Y Gao, Ł Dudziak, SZ Li, ...
arXiv preprint arXiv:2212.04084, 2022
The future of consumer edge-ai computing
S Laskaridis, SI Venieris, A Kouris, R Li, ND Lane
arXiv preprint arXiv:2210.10514, 2022
Fluid batching: Exit-aware preemptive serving of early-exit neural networks on edge npus
A Kouris, SI Venieris, S Laskaridis, ND Lane
International Conference on Computer-Aided Design (ICCAD'23), 2022
MELTing point: Mobile Evaluation of Language Transformers
S Laskaridis, K Katevas, L Minto, H Haddadi
arXiv preprint arXiv:2403.12844, 2024
Federated mobile sensing for activity recognition
S Laskaridis, D Spathis, M Almeida
Proceedings of the 27th Annual International Conference on Mobile Computing …, 2021
Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
S Horváth, S Laskaridis, S Rajput, H Wang
arXiv preprint arXiv:2308.14929, 2023
Method and apparatus for image segmentation
A Kouris, SI Venieris, S Laskaridis, I Leontiadis
US Patent App. 17/888,138, 2023
Cross-device Federated Architecture Search
S Laskaridis, J Fernandez-Marques, Ł Dudziak
Workshop on Federated Learning: Recent Advances and New Challenges (in …, 2022
Adaptable mobile vision systems through multi-exit neural networks
A Kouris, SI Venieris, S Laskaridis, ND Lane
Proceedings of the 20th Annual International Conference on Mobile Systems …, 2022
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–20