Paul Whatmough
6 papers · 2019–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Academic Marathon (5) π Cross-Pollinator (6)
πΊοΈ
Taxonomy Completionist
(14)
π£
Hot Topic Early Bird
Conferences
NIPS (3)
ICLR (2)
ICML (1)
Top co-authors
Keywords
model compression
(3)
neural architecture search
(2)
knowledge distillation
(1)
efficient computing
(1)
model pruning
(1)
convolutional neural network
(1)
personalized model
(1)
low-rank adaptation
(1)
sparse training
(1)
weight quantization
(1)
inference latency
(1)
parameter-efficient finetuning
(1)
sparse adapter
(1)
concept loss
(1)
model sparsity
(1)
memory constraint
(1)
model debiasing
(1)
low rank adaptation
(1)
gradient correction
(1)
parameter efficient finetuning
(1)
Papers
Sparse High Rank Adapters
NIPS 2024
Efficient Edge Inference by Selective Query
ICLR 2023
UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units
NIPS 2022
Federated Learning Based on Dynamic Regularization
ICLR 2021
Debiasing Model Updates for Improving Personalized Federated Training
ICML 2021
SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
NIPS 2019