Hanseul Cho
8 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π§
Keyword Pioneer
π
Conference Polyglot
(3)
π
Cross-Pollinator
(6)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
Conferences
NIPS (4)
ICLR (3)
ICML (1)
Top co-authors
Keywords
transformer architecture
(1)
sample efficiency
(1)
neural network training
(1)
principal component analysis
(1)
loss landscape
(1)
streaming algorithm
(1)
noisy power method
(1)
weight initialization
(1)
plasticity loss
(1)
positional encoding
(1)
noise memorization
(1)
stationary datum
(1)
length generalization
(1)
gradient propagation
(1)
neural network plasticity
(1)
fair representation
(1)
fair pca
(1)
arithmetic task
(1)
position coupling
(1)
input plasticity
(1)
Papers
Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
ICLR 2025
Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
ICLR 2025
Fundamental Benefit of Alternating Updates in Minimax Optimization
ICML 2024
DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
NIPS 2024
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
NIPS 2024
SGDA with shuffling: faster convergence for nonconvex-PΕ minimax optimization
ICLR 2023
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
NIPS 2023
Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint
NIPS 2023