204 citations · 491 across the 17 of their papers we have counts for
20 papers
Fine-Tuning GPT-5 for GPU Kernel Generation
Ali Tehrani, Yahya Emara, Essam Wissam +4
Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized opti…
MobileQuant: Mobile-friendly Quantization for On-device Language Models
Fuwen Tan, Royson Lee, Łukasz Dudziak +5
Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. However, deploying LLMs on edge devices poses sev…
Recurrent Early Exits for Federated Learning with Heterogeneous Clients
Royson Lee, Javier Fernandez-Marques, Shell Xu Hu +6
Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clien…
How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor
Hrushikesh Loya, Łukasz Dudziak, Abhinav Mehrotra +4
Neural architecture search has proven to be a powerful approach to designing and refining neural networks, often boosting their performance and efficiency over manually-designed va…
Neural Fine-Tuning Search for Few-Shot Learning
Panagiotis Eustratiadis, Łukasz Dudziak, Da Li +1
In few-shot recognition, a classifier that has been trained on one set of classes is required to rapidly adapt and generalize to a disjoint, novel set of classes. To that end, rece…
Federated Learning for Inference at Anytime and Anywhere
Zicheng Liu, Da Li, Javier Fernandez-Marques +6
Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication…
BLOX: Macro Neural Architecture Search Benchmark and Algorithms
Thomas Chun Pong Chau, Łukasz Dudziak, Hongkai Wen +2
Neural architecture search (NAS) has been successfully used to design numerous high-performance neural networks. However, NAS is typically compute-intensive, so most existing appro…
FedorAS: Federated Architecture Search under system heterogeneity
Lukasz Dudziak, Stefanos Laskaridis, Javier Fernandez-Marques
Federated learning (FL) has recently gained considerable attention due to its ability to learn on decentralised data while preserving client privacy. However, it also poses additio…
EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
Junting Pan, Adrian Bulat, Fuwen Tan +5
Self-attention based models such as vision transformers (ViTs) have emerged as a very competitive architecture alternative to convolutional neural networks (CNNs) in computer visio…
Smart at what cost? Characterising Mobile Deep Neural Networks in the wild
Mario Almeida, Stefanos Laskaridis, Abhinav Mehrotra +3
With smartphones' omnipresence in people's pockets, Machine Learning (ML) on mobile is gaining traction as devices become more powerful. With applications ranging from visual filte…
Zero-Cost Operation Scoring in Differentiable Architecture Search
Lichuan Xiang, Łukasz Dudziak, Mohamed S. Abdelfattah +3
We formalize and analyze a fundamental component of differentiable neural architecture search (NAS): local "operation scoring" at each operation choice. We view existing operation…
Zero-Cost Proxies for Lightweight NAS
Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak +1
Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models n…
NAS: Constrained Neural Architecture Search for Microcontrollers
Edgar Liberis, Łukasz Dudziak, Nicholas D. Lane
IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persist…
Iterative Compression of End-to-End ASR Model using AutoML
Abhinav Mehrotra, Łukasz Dudziak, Jinsu Yeo +9
Increasing demand for on-device Automatic Speech Recognition (ASR) systems has resulted in renewed interests in developing automatic model compression techniques. Past research hav…
Journey Towards Tiny Perceptual Super-Resolution
Royson Lee, Łukasz Dudziak, Mohamed Abdelfattah +4
Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks.…
BRP-NAS: Prediction-based NAS using GCNs
Łukasz Dudziak, Thomas Chau, Mohamed S. Abdelfattah +3
Neural architecture search (NAS) enables researchers to automatically explore broad design spaces in order to improve efficiency of neural networks. This efficiency is especially i…
Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator
Mohamed S. Abdelfattah, Łukasz Dudziak, Thomas Chau +3
Neural architecture search (NAS) has been very successful at outperforming human-designed convolutional neural networks (CNN) in accuracy, and when hardware information is present,…
MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
Royson Lee, Stylianos I. Venieris, Łukasz Dudziak +2
In recent years, convolutional networks have demonstrated unprecedented performance in the image restoration task of super-resolution (SR). SR entails the upscaling of a single low…
ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning
Łukasz Dudziak, Mohamed S. Abdelfattah, Ravichander Vipperla +2
End-to-end automatic speech recognition (ASR) models are increasingly large and complex to achieve the best possible accuracy. In this paper, we build an AutoML system that uses re…
Dynamic Channel Pruning: Feature Boosting and Suppression
Xitong Gao, Yiren Zhao, Łukasz Dudziak +2
Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we reduce this cost by exploitin…