Łukasz Dudziak
Łukasz Dudziak
Samsung AI Center Cambridge
Verificeret mail på samsung.com
Citeret af
Citeret af
Dynamic channel pruning: Feature boosting and suppression
X Gao, Y Zhao, Ł Dudziak, R Mullins, C Xu
7th International Conference on Learning Representations (ICLR'19), 2019
Zero-Cost Proxies for Lightweight NAS
MS Abdelfattah, A Mehrotra, Ł Dudziak, ND Lane
9th International Conference on Learning Representations (ICLR'21), 2021
BRP-NAS: Prediction-based NAS using GCNs
Ł Dudziak, T Chau, M Abdelfattah, R Lee, H Kim, N Lane
34th Conference on Neural Information Processing Systems (NeurIPS'20), 2020
Edgevits: Competing light-weight cnns on mobile devices with vision transformers
J Pan, A Bulat, F Tan, X Zhu, L Dudziak, H Li, G Tzimiropoulos, B Martinez
17th European Conference on Computer Vision (ECCV'22), 2022
μnas: Constrained neural architecture search for microcontrollers
E Liberis, Ł Dudziak, ND Lane
Proceedings of the 1st Workshop on Machine Learning and Systems, 70-79, 2021
Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator
MS Abdelfattah, Ł Dudziak, T Chau, R Lee, H Kim, ND Lane
57th Design Automation Conference (DAC'20), 2020
Mobisr: Efficient on-device super-resolution through heterogeneous mobile processors
R Lee, SI Venieris, L Dudziak, S Bhattacharya, ND Lane
The 25th Annual International Conference on Mobile Computing and Networking …, 2019
NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition
A Mehrotra, AG Ramos, S Bhattacharya, Ł Dudziak, R Vipperla, T Chau, ...
9th International Conference on Learning Representations (ICLR'21), 2021
Journey Towards Tiny Perceptual Super-Resolution
R Lee, Ł Dudziak, M Abdelfattah, SI Venieris, H Kim, H Wen, ND Lane
16th European Conference on Computer Vision (ECCV'20), 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
ACM Internet Measurement Conference (IMC'21), 2021
ShrinkML: End-to-end ASR model compression using reinforcement learning
Ł Dudziak, MS Abdelfattah, R Vipperla, S Laskaridis, ND Lane
Proc. Interspeech 2019, 2235-2239, 2019
Zero-Cost Operation Scoring in Differentiable Architecture Search
L Xiang, Ł Dudziak, MS Abdelfattah, TCP Chau, ND Lane, H Wen
37th AAAI Conference on Artificial Intelligence (AAAI'23), 2023
BLOX: Macro Neural Architecture Search Benchmark and Algorithms
TCP Chau, Ł Dudziak, H Wen, ND Lane, MS Abdelfattah
36th Conference on Neural Information Processing Systems, D&B Track (NeurIPS'22), 2022
Codesign-NAS: Automatic FPGA/CNN codesign using neural architecture search
MS Abdelfattah, L Dudziak, T Chau, R Lee, H Kim, ND Lane
Proceedings of the 2020 ACM/SIGDA International Symposium on Field …, 2020
Iterative Compression of End-to-End ASR Model using AutoML
A Mehrotra, Ł Dudziak, J Yeo, Y Lee, R Vipperla, MS Abdelfattah, ...
Proc. Interspeech 2020, 3361-3365, 2020
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
Fedoras: Federated architecture search under system heterogeneity
L Dudziak, S Laskaridis, J Fernandez-Marques
arXiv preprint arXiv:2206.11239, 2022
Electronic device and method for controlling the electronic device thereof
MS Abdelfattah, L Dudziak, CP Chau, H Kim, LEE Royson, ...
US Patent App. 17/015,724, 2021
Method and apparatus for analyzing neural network performance
CP Chau, MS Abdelfattah, L Dudziak, LEE Royson, H Kim, NDA Lane
US Patent App. 17/514,840, 2022
Fast Inference Through The Reuse Of Attention Maps In Diffusion Models
R Hunter, Ł Dudziak, MS Abdelfattah, A Mehrotra, S Bhattacharya, H Wen
arXiv preprint arXiv:2401.01008, 2023
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–20