PW
Paul Whatmough
cs.LGcs.ARcs.CVcs.AIstat.MLcs.CLcs.DCcs.ROeess.IVcs.CC
On Valency
published · living versionsW_r72x54u6·v1 · currentpublished
A Unified Hessian-Guided Framework for Post-Training Quantization
with Mads Toftrup, Marco Federici, Boris van Breugel, Markus Nagel
1 version
W_jwjz8qee·v1published
Preprints & journals
49 papers in the corpus · 2014–2026The Key to Going Linear: Analysis-Driven Transformer Linearization2607.07706v1 · Anna Kuzina, Paul N. Whatmough, Babak Ehteshami Bejnordi2026 · 0 citationsarXiv
Efficient Reasoning on the Edge2603.16867v2 · Yelysei Bondarenko, Thomas Hehn, Rob Hesselink et al.2026 · 0 citationsarXiv
Leech Lattice Vector Quantization for Efficient LLM Compression2603.11021v2 · Tycho F. A. van der Ouderaa, Mart van Baalen, Paul Whatmough et al.2026 · 0 citationsarXiv
Dissecting Quantization Error: A Concentration-Alignment Perspective2603.04359v2 · Marco Federici, Boris van Breugel, Paul Whatmough et al.2026 · 0 citationsarXiv
PipeFlow: Pipelined Processing and Motion-Aware Frame Selection for Long-Form Video Editing2512.24026v1 · Mustafa Munir, Md Mostafijur Rahman, Kartikeya Bhardwaj et al.2025 · 0 citationsarXiv
ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction2511.18701v1 · Mustafa Munir, Harsh Goel, Xiwen Wei et al.2025 · 0 citationsarXiv
STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization2510.26771v1 · Marco Federici, Riccardo Del Chiaro, Boris van Breugel et al.2025 · 0 citationsarXiv
KaVa: Latent Reasoning via Compressed KV-Cache Distillation2510.02312v2 · Anna Kuzina, Maciej Pioro, Paul N. Whatmough et al.2025 · 0 citationsarXiv
Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs2510.01185v1 · Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar et al.2025 · 0 citationsarXiv
HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations2506.09932v2 · Marco Federici, Riccardo Del Chiaro, Boris van Breugel et al.2025 · 0 citationsarXiv
FPTQuant: Function-Preserving Transforms for LLM Quantization2506.04985v2 · Boris van Breugel, Yelysei Bondarenko, Paul Whatmough et al.2025 · 0 citationsarXiv
Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking2412.01380v2 · Marco Federici, Davide Belli, Mart van Baalen et al.2024 · 0 citationsarXiv
Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference2412.00099v2 · Andrii Skliar, Ties van Rozendaal, Romain Lepert et al.2024 · 1 citationarXiv
Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters2407.16712v1 · Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi et al.2024 · 0 citationsarXiv
Sparse High Rank Adapters2406.13175v2 · Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi et al.2024 · 3 citationsarXiv
Characterizing Soft-Error Resiliency in Arm's Ethos-U55 Embedded Machine Learning Accelerator2404.09317v1 · Abhishek Tyagi, Reiley Jeyapaul, Chuteng Zhu et al.2024 · 4 citationsarXiv
GPTVQ: The Blessing of Dimensionality for LLM Quantization2402.15319v2 · Mart van Baalen, Andrey Kuzmin, Ivan Koryakovskiy et al.2024 · 2 citationsarXiv
PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices2301.10999v1 · Yuji Chai, Devashree Tripathy, Chuteng Zhou et al.2023 · 1 citationarXiv
Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators2212.02649v2 · Abhishek Tyagi, Yiming Gan, Shaoshan Liu et al.2022 · 6 citationsarXiv
Restructurable Activation Networks2208.08562v2 · Kartikeya Bhardwaj, James Ward, Caleb Tung et al.2022 · 4 citationsarXiv
UDC: Unified DNAS for Compressible TinyML Models2201.05842v4 · Igor Fedorov, Ramon Matas, Hokchhay Tann et al.2022 · 7 citationsarXiv
Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge2112.14340v1 · Kartikeya Bhardwaj, Dibakar Gope, James Ward et al.2021 · 3 citationsarXiv
AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator2111.06503v1 · Chuteng Zhou, Fernando Garcia Redondo, Julian Buchel et al.2021 · 10 citationsarXiv
Federated Learning Based on Dynamic Regularization2111.04263v2 · Durmus Alp Emre Acar, Yue Zhao, Ramon Matas Navarro et al.2021 · 391 citationsarXiv
S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration2107.07983v2 · Zhi-Gang Liu, Paul N. Whatmough, Yuhao Zhu et al.2021 · 109 citationsarXiv
Fast and Accurate: Video Enhancement using Sparse Depth2103.08764v2 · Yu Feng, Patrick Hansen, Paul N. Whatmough et al.2021 · 9 citationsarXiv
Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices2102.07071v1 · Urmish Thakker, Paul N. Whatmough, Zhigang Liu et al.2021 · 1 citationarXiv
AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs2102.02988v3 · Srivatsan Krishnan, Zishen Wan, Kshitij Bhardwaj et al.2021 · 2 citationsarXiv
Information contraction in noisy binary neural networks and its implications2101.11750v2 · Chuteng Zhou, Quntao Zhuang, Matthew Mattina et al.2021 · 3 citationsarXiv
EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference2011.14203v5 · Thierry Tambe, Coleman Hooper, Lillian Pentecost et al.2020 · 125 citationsarXiv
MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers2010.11267v6 · Colby Banbury, Chuteng Zhou, Igor Fedorov et al.2020 · 186 citationsarXiv
Sparse Systolic Tensor Array for Efficient CNN Hardware Acceleration2009.02381v2 · Zhi-Gang Liu, Paul N. Whatmough, Matthew Mattina2020 · 11 citationsarXiv
Mesorasi: Architecture Support for Point Cloud Analytics via Delayed-Aggregation2008.06967v1 · Yu Feng, Boyuan Tian, Tiancheng Xu et al.2020 · 75 citationsProceedings of the 53nd (2020) Annual IEEE/ACM International Symposium on Microarchitecture
TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids2005.11138v1 · Igor Fedorov, Marko Stamenovic, Carl Jensen et al.2020 · 116 citationsarXiv
Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference2005.08098v1 · Zhi-Gang Liu, Paul N. Whatmough, Matthew Mattina2020 · 105 citationsarXiv
Searching for Winograd-aware Quantized Networks2002.10711v1 · Javier Fernandez-Marques, Paul N. Whatmough, Andrew Mundy et al.2020 · 24 citationsProceedings of Machine Learning and Systems (2020), 14-29
Compressing Language Models using Doped Kronecker Products2001.08896v5 · Urmish Thakker, Paul N. Whatmough, Zhi-Gang Liu et al.2020 · 7 citationsPresented at On-device Intelligence Workshop at Third Conference on Machine Learning and Systems (MLSys) 2020
Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation2001.04974v1 · Chuteng Zhou, Prad Kadambi, Matthew Mattina et al.2020 · 26 citationsarXiv
CHIPKIT: An agile, reusable open-source framework for rapid test chip development2001.04504v2 · Paul Whatmough, Marco Donato, Glenn Ko et al.2020 · 20 citationsarXiv
SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads1912.04481v2 · Sam Likun Xi, Yuan Yao, Kshitij Bhardwaj et al.2019 · 12 citationsarXiv
ISP4ML: Understanding the Role of Image Signal Processing in Efficient Deep Learning Vision Systems1911.07954v4 · Patrick Hansen, Alexey Vilkin, Yury Khrustalev et al.2019 · 3 citationsarXiv
ASV: Accelerated Stereo Vision System1911.07919v1 · Yu Feng, Paul Whatmough, Yuhao Zhu2019 · 0 citationsIn Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO '52). ACM, New York, NY, USA, 643-656 (2019)
SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers1905.12107v1 · Igor Fedorov, Ryan P. Adams, Matthew Mattina et al.2019 · 125 citationsarXiv
FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning1902.11128v1 · Paul N. Whatmough, Chuteng Zhou, Patrick Hansen et al.2019 · 49 citationsarXiv
Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning1812.01672v2 · Paul Whatmough, Chuteng Zhou, Patrick Hansen et al.2018 · 0 citationsarXiv
SCALE-Sim: Systolic CNN Accelerator Simulator1811.02883v2 · Ananda Samajdar, Yuhao Zhu, Paul Whatmough et al.2018 · 213 citationsarXiv
Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision1803.11232v1 · Yuhao Zhu, Anand Samajdar, Matthew Mattina et al.2018 · 81 citationsarXiv
Mobile Machine Learning Hardware at ARM: A Systems-on-Chip (SoC) Perspective1801.06274v2 · Yuhao Zhu, Matthew Mattina, Paul Whatmough2018 · 17 citationsarXiv
Precision-Energy-Throughput Scaling Of Generic Matrix Multiplication and Convolution Kernels Via Linear Projections1411.2860v1 · Mohammad Ashraful Anam, Paul N. Whatmough, Yiannis Andreopoulos2014 · 3 citationsIEEE Transactions on Circuits and Systems for Video Technology, vol. 24, no. 11, pp. 1860-1873, Nov. 2014
Career total: 127 works. 49 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.