Utku Evci
12 papers · 2020–2025 · 3 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 ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (20)
👥
Mega-Team · Squad
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(12)
Deep Learning
(8)
Application Areas
(7)
Optimization & Theory · Machine Learning
(7)
Artificial Intelligence
(6)
Core AI
(4)
Techniques
(4)
Architectures
(3)
Reinforcement Learning
(2)
Learning Paradigms
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Methods
(2)
Optimization & Theory · Deep Learning
(2)
Keywords
parameter efficiency
(5)
neural network pruning
(5)
sparse neural network
(3)
vision transformer
(2)
scaling law
(2)
deep reinforcement learning
(2)
transfer learning
(2)
model compression
(2)
lottery ticket hypothesis
(2)
dynamic sparse training
(2)
model scaling
(2)
structured sparsity
(1)
singular value decomposition
(1)
hidden state
(1)
sparse approximation
(1)
few-shot learning
(1)
neural architecture
(1)
real-time recurrent learning
(1)
out-of-distribution generalization
(1)
neural network expressivity
(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
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
The Dormant Neuron Phenomenon in Deep Reinforcement Learning
ICML 2023
Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win
AAAI 2022
GradMax: Growing Neural Networks using Gradient Information
ICLR 2022
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
ICML 2022
The State of Sparse Training in Deep Reinforcement Learning
ICML 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