Arash Ardakani
6 papers · 2019–2024 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
model compression
(4)
long short-term memory
(3)
recurrent neural network
(2)
transformer model
(2)
stochastic computing
(2)
language modeling
(1)
neural network optimization
(1)
efficient computing
(1)
character-level language modeling
(1)
training dynamics
(1)
layer freezing
(1)
weight quantization
(1)
neural network binarization
(1)
model binarization
(1)
gpu memory
(1)
neural network initialization
(1)
gated recurrent unit
(1)
binary neural network
(1)
finite state machine
(1)
binary quantization
(1)
Papers
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics
NAACL 2024
Efficient Two-Stage Progressive Quantization of BERT
EMNLP 2022
Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT
EMNLP 2022
Training Linear Finite-State Machines
NeurIPS 2020
Learning Recurrent Binary/Ternary Weights
ICLR 2019
The Synthesis of XNOR Recurrent Neural Networks with Stochastic Logic
NeurIPS 2019