Naigang Wang
11 papers · 2018–2024 · 6 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16)
🧬
Topic Evolution
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Top co-authors
Research topics
Keywords
model compression
(4)
model quantization
(3)
efficient computing
(2)
knowledge distillation
(2)
neural network optimization
(2)
gradient computation
(1)
deep learning training
(1)
speech recognition
(1)
energy efficiency
(1)
latency constraint
(1)
neural network training
(1)
distributed training
(1)
deep neural network
(1)
communication efficiency
(1)
long short-term memory
(1)
proximal gradient descent
(1)
neural architecture search
(1)
gradient compression
(1)
post-training quantization
(1)
neural network quantization
(1)
Papers
A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
ICML 2024
Improved Techniques for Quantizing Deep Networks With Adaptive Bit-Widths
WACV 2024
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
NeurIPS 2024
Deep Compression of Pre-trained Transformer Models
NeurIPS 2022
4-Bit Quantization of LSTM-Based Speech Recognition Models
Interspeech 2021
Hardware-Aware Neural Architecture Search: Survey and Taxonomy
IJCAI 2021
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
NeurIPS 2020
Ultra-Low Precision 4-bit Training of Deep Neural Networks
NeurIPS 2020
Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks
ICLR 2019
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks
NeurIPS 2019
Training Deep Neural Networks with 8-bit Floating Point Numbers
NeurIPS 2018