Lukasz Dudziak

45 papers A* 12A 4Journal 23Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Fine-Tuning GPT-5 for GPU Kernel Generation. CoRR Ali Tehrani, Yahya Emara, Essam Wissam, Wojciech Paluch, Waleed Atallah, Lukasz Dudziak, Mohamed S. Abdelfattah
2025	J	`jnl`	Fast Sampling Through The Reuse Of Attention Maps In Diffusion Models. Int. J. Comput. Vis. Rosco Hunter, Lukasz Dudziak, Mohamed S. Abdelfattah, Abhinav Mehrotra, Sourav Bhattacharya, Hongkai Wen
2024	J	`jnl`	Fast Inference Through The Reuse Of Attention Maps In Diffusion Models. CoRR Rosco Hunter, Lukasz Dudziak, Mohamed S. Abdelfattah, Abhinav Mehrotra, Sourav Bhattacharya, Hongkai Wen
2024	A*	`conf`	Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA. DAC Zehuan Zhang, Hongxiang Fan, Hao Mark Chen, Lukasz Dudziak, Wayne Luk
2024	J	`jnl`	Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA. CoRR Zehuan Zhang, Hongxiang Fan, Hao Mark Chen, Lukasz Dudziak, Wayne Luk
2024	—	`conf`	MobileQuant: Mobile-friendly Quantization for On-device Language Models. EMNLP (Findings) Fuwen Tan, Royson Lee, Lukasz Dudziak, Shell Xu Hu, Sourav Bhattacharya, Timothy M. Hospedales, Georgios Tzimiropoulos, Brais Martínez
2024	J	`jnl`	MobileQuant: Mobile-friendly Quantization for On-device Language Models. CoRR Fuwen Tan, Royson Lee, Lukasz Dudziak, Shell Xu Hu, Sourav Bhattacharya, Timothy M. Hospedales, Georgios Tzimiropoulos, Brais Martínez
2024	A*	`conf`	Neural Fine-Tuning Search for Few-Shot Learning. ICLR Panagiotis Eustratiadis, Lukasz Dudziak, Da Li, Timothy M. Hospedales
2024	A*	`conf`	Recurrent Early Exits for Federated Learning with Heterogeneous Clients. ICML Royson Lee, Javier Fernández-Marqués, Shell Xu Hu, Da Li, Stefanos Laskaridis, Lukasz Dudziak, Timothy M. Hospedales, Ferenc Huszár, Nicholas Donald Lane
2024	J	`jnl`	Recurrent Early Exits for Federated Learning with Heterogeneous Clients. CoRR Royson Lee, Javier Fernández-Marqués, Shell Xu Hu, Da Li, Stefanos Laskaridis, Lukasz Dudziak, Timothy M. Hospedales, Ferenc Huszár, Nicholas D. Lane
2024	A*	`conf`	Towards Neural Architecture Search through Hierarchical Generative Modeling. ICML Lichuan Xiang, Lukasz Dudziak, Mohamed S. Abdelfattah, Abhinav Mehrotra, Nicholas Donald Lane, Hongkai Wen
2023	—	`conf`	Exploiting Network Compressibility and Topology in Zero-Cost NAS. AutoML Lichuan Xiang, Rosco Hunter, Minghao Xu, Lukasz Dudziak, Hongkai Wen
2023	J	`jnl`	How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor. CoRR Hrushikesh Loya, Lukasz Dudziak, Abhinav Mehrotra, Royson Lee, Javier Fernández-Marqués, Nicholas D. Lane, Hongkai Wen
2023	J	`jnl`	Neural Fine-Tuning Search for Few-Shot Learning. CoRR Panagiotis Eustratiadis, Lukasz Dudziak, Da Li, Timothy M. Hospedales
2023	A*	`conf`	Zero-Cost Operation Scoring in Differentiable Architecture Search. AAAI Lichuan Xiang, Lukasz Dudziak, Mohamed S. Abdelfattah, Thomas C. P. Chau, Nicholas D. Lane, Hongkai Wen
2022	A*	`conf`	BLOX: Macro Neural Architecture Search Benchmark and Algorithms. NeurIPS Thomas Chau, Lukasz Dudziak, Hongkai Wen, Nicholas D. Lane, Mohamed S. Abdelfattah
2022	J	`jnl`	BLOX: Macro Neural Architecture Search Benchmark and Algorithms. CoRR Thomas Chun-Pong Chau, Lukasz Dudziak, Hongkai Wen, Nicholas Donald Lane, Mohamed S. Abdelfattah
2022	—	`conf`	EdgeViTs: Competing Light-Weight CNNs on Mobile Devices with Vision Transformers. ECCV (11) Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, Brais Martínez
2022	J	`jnl`	EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers. CoRR Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, Brais Martínez
2022	J	`jnl`	Federated Learning for Inference at Anytime and Anywhere. CoRR Zicheng Liu, Da Li, Javier Fernández-Marqués, Stefanos Laskaridis, Yan Gao, Lukasz Dudziak, Stan Z. Li, Shell Xu Hu, Timothy M. Hospedales
2022	J	`jnl`	FedorAS: Federated Architecture Search under system heterogeneity. CoRR Lukasz Dudziak, Stefanos Laskaridis, Javier Fernández-Marqués
2021	A*	`conf`	NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition. ICLR Abhinav Mehrotra, Alberto Gil C. P. Ramos, Sourav Bhattacharya, Lukasz Dudziak, Ravichander Vipperla, Thomas Chau, Mohamed S. Abdelfattah, Samin Ishtiaq, Nicholas Donald Lane
2021	J	`jnl`	Smart at what cost? Characterising Mobile Deep Neural Networks in the wild. CoRR Mário Almeida, Stefanos Laskaridis, Abhinav Mehrotra, Lukasz Dudziak, Ilias Leontiadis, Nicholas D. Lane
2021	A	`conf`	Smart at what cost?: characterising mobile deep neural networks in the wild. Internet Measurement Conference Mário Almeida, Stefanos Laskaridis, Abhinav Mehrotra, Lukasz Dudziak, Ilias Leontiadis, Nicholas D. Lane
2021	J	`jnl`	Zero-Cost Proxies Meet Differentiable Architecture Search. CoRR Lichuan Xiang, Lukasz Dudziak, Mohamed S. Abdelfattah, Thomas Chau, Nicholas D. Lane, Hongkai Wen
2021	A*	`conf`	Zero-Cost Proxies for Lightweight NAS. ICLR Mohamed S. Abdelfattah, Abhinav Mehrotra, Lukasz Dudziak, Nicholas Donald Lane
2021	J	`jnl`	Zero-Cost Proxies for Lightweight NAS. CoRR Mohamed S. Abdelfattah, Abhinav Mehrotra, Lukasz Dudziak, Nicholas D. Lane
2021	—	`conf`	μNAS: Constrained Neural Architecture Search for Microcontrollers. EuroMLSys@EuroSys Edgar Liberis, Lukasz Dudziak, Nicholas D. Lane
2020	A*	`conf`	BRP-NAS: Prediction-based NAS using GCNs. NeurIPS Lukasz Dudziak, Thomas Chau, Mohamed S. Abdelfattah, Royson Lee, Hyeji Kim, Nicholas D. Lane
2020	J	`jnl`	BRP-NAS: Prediction-based NAS using GCNs. CoRR Thomas Chau, Lukasz Dudziak, Mohamed S. Abdelfattah, Royson Lee, Hyeji Kim, Nicholas D. Lane
2020	A*	`conf`	Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator. DAC Mohamed S. Abdelfattah, Lukasz Dudziak, Thomas Chau, Royson Lee, Hyeji Kim, Nicholas D. Lane
2020	J	`jnl`	Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator. CoRR Mohamed S. Abdelfattah, Lukasz Dudziak, Thomas Chau, Royson Lee, Hyeji Kim, Nicholas D. Lane
2020	A	`conf`	Codesign-NAS: Automatic FPGA/CNN Codesign Using Neural Architecture Search. FPGA Mohamed S. Abdelfattah, Lukasz Dudziak, Thomas Chau, Royson Lee, Hyeji Kim, Nicholas D. Lane
2020	A	`conf`	Iterative Compression of End-to-End ASR Model Using AutoML. INTERSPEECH Abhinav Mehrotra, Lukasz Dudziak, Jinsu Yeo, Young-Yoon Lee, Ravichander Vipperla, Mohamed S. Abdelfattah, Sourav Bhattacharya, Samin Ishtiaq, Alberto Gil C. P. Ramos, SangJeong Lee, Daehyun Kim, Nicholas D. Lane
2020	J	`jnl`	Iterative Compression of End-to-End ASR Model using AutoML. CoRR Abhinav Mehrotra, Lukasz Dudziak, Jinsu Yeo, Young-Yoon Lee, Ravichander Vipperla, Mohamed S. Abdelfattah, Sourav Bhattacharya, Samin Ishtiaq, Alberto Gil C. P. Ramos, SangJeong Lee, Daehyun Kim, Nicholas D. Lane
2020	—	`conf`	Journey Towards Tiny Perceptual Super-Resolution. ECCV (26) Royson Lee, Lukasz Dudziak, Mohamed S. Abdelfattah, Stylianos I. Venieris, Hyeji Kim, Hongkai Wen, Nicholas D. Lane
2020	J	`jnl`	Journey Towards Tiny Perceptual Super-Resolution. CoRR Royson Lee, Lukasz Dudziak, Mohamed S. Abdelfattah, Stylianos I. Venieris, Hyeji Kim, Hongkai Wen, Nicholas D. Lane
2020	J	`jnl`	μNAS: Constrained Neural Architecture Search for Microcontrollers. CoRR Edgar Liberis, Lukasz Dudziak, Nicholas D. Lane
2019	—	`conf`	Dynamic Channel Pruning: Feature Boosting and Suppression. ICLR (Poster) Xitong Gao, Yiren Zhao, Lukasz Dudziak, Robert Mullins, Cheng-Zhong Xu
2019	A*	`conf`	MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors. MobiCom Royson Lee, Stylianos I. Venieris, Lukasz Dudziak, Sourav Bhattacharya, Nicholas D. Lane
2019	J	`jnl`	MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors. CoRR Royson Lee, Stylianos I. Venieris, Lukasz Dudziak, Sourav Bhattacharya, Nicholas D. Lane
2019	A*	`conf`	Poster: MobiSR - Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors. MobiCom Royson Lee, Stylianos I. Venieris, Lukasz Dudziak, Sourav Bhattacharya, Nicholas D. Lane
2019	A	`conf`	ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning. INTERSPEECH Lukasz Dudziak, Mohamed S. Abdelfattah, Ravichander Vipperla, Stefanos Laskaridis, Nicholas D. Lane
2019	J	`jnl`	ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning. CoRR Lukasz Dudziak, Mohamed S. Abdelfattah, Ravichander Vipperla, Stefanos Laskaridis, Nicholas D. Lane
2018	J	`jnl`	Dynamic Channel Pruning: Feature Boosting and Suppression. CoRR Xitong Gao, Yiren Zhao, Lukasz Dudziak, Robert Mullins, Cheng-Zhong Xu