Decebal Constantin Mocanu
15 papers · 2016–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🐝 Cross-Pollinator (10) 🏃 Academic Marathon (9) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🌈 Renaissance Researcher (7)
🌍
Conference Polyglot
(6)
🏃
Academic Marathon
(9)
🌈
Renaissance Researcher
(7)
🤝
Dynamic Duo
(13)
🏆
Keyword Champion
(5)
💎
Century Club
(15)
❓
The Questioner
(2)
⚡
Prolific Year
(5)
🔥
Unstoppable
(5)
Conferences
NIPS (5)
ICLR (4)
ICML (2)
IJCAI (2)
AISTATS (1)
INTERSPEECH (1)
Top co-authors
Keywords
dynamic sparse training
(5)
sparse neural network
(3)
neural network pruning
(3)
feature selection
(2)
sample efficiency
(1)
attention mechanism
(1)
automatic speech recognition
(1)
medical image segmentation
(1)
efficient computing
(1)
time series classification
(1)
continuous control
(1)
receptive field
(1)
convolutional neural network
(1)
recurrent neural network
(1)
feature fusion
(1)
sparse autoencoder
(1)
sparse training
(1)
data pruning
(1)
training datum
(1)
3d convolution
(1)
Papers
Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
ICLR 2025
Dynamic Data Pruning for Automatic Speech Recognition
INTERSPEECH 2024
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
NIPS 2024
Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks
AISTATS 2024
Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training
NIPS 2023
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
ICLR 2023
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity
ICLR 2022
Where to Pay Attention in Sparse Training for Feature Selection?
NIPS 2022
Dynamic Sparse Network for Time Series Classification: Learning What to “See”
NIPS 2022
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
ICLR 2022
Dynamic Sparse Training for Deep Reinforcement Learning
IJCAI 2022
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
ICML 2021
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
NIPS 2021
Selfish Sparse RNN Training
ICML 2021
On the Synergy of Network Science and Artificial Intelligence
IJCAI 2016