Utku Evci
12 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (7) πΊοΈ Taxonomy Completionist (16) π£ Hot Topic Early Bird
π
Conference Polyglot
(3)
π
Academic Marathon
(5)
π₯
Mega-Team
(42)
π
Century Club
(12)
π₯
Unstoppable
(6)
Conferences
ICLR (6)
ICML (5)
AAAI (1)
Top co-authors
Keywords
parameter efficiency
(3)
sparse neural network
(3)
lottery ticket hypothesis
(2)
deep reinforcement learning
(2)
neural network pruning
(2)
gradient flow
(1)
neural network expressivity
(1)
dynamic sparse training
(1)
dormant neuron
(1)
sparse training
(1)
model scaling
(1)
inference efficiency
(1)
linear probing
(1)
intermediate representation
(1)
dynamic topology
(1)
network sparsity
(1)
feature reuse
(1)
lottery ticket
(1)
network expressivity
(1)
neural network
(1)
Papers
The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
ICLR 2025
Dynamic Sparse Training with Structured Sparsity
ICLR 2024
Scaling Laws for Sparsely-Connected Foundation Models
ICLR 2024
The Dormant Neuron Phenomenon in Deep Reinforcement Learning
ICML 2023
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
ICML 2022
The State of Sparse Training in Deep Reinforcement Learning
ICML 2022
Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win
AAAI 2022
GradMax: Growing Neural Networks using Gradient Information
ICLR 2022
Practical Real Time Recurrent Learning with a Sparse Approximation
ICLR 2021
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
ICLR 2020
Rigging the Lottery: Making All Tickets Winners
ICML 2020