Makoto Kawano
5 papers · 2021–2026 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Deep Learning
(5)
Machine Learning
(4)
Architectures
(4)
Core Methods
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Natural Language Processing
(1)
Application Areas
(1)
Core AI · Computer Vision
(1)
Core AI · Artificial Intelligence
(1)
Learning Types
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
data augmentation
(1)
spectral analysis
(1)
generalization bound
(1)
deep neural network
(1)
language model
(1)
lie group
(1)
zero-shot generalization
(1)
downstream performance
(1)
group equivariance
(1)
group invariance
(1)
transformer training
(1)
equivariant representation
(1)
invariant representation
(1)
permutation invariance
(1)
dynamic mode decomposition
(1)
koopman operator
(1)
text augmentation
(1)
training instability
(1)
group symmetry
(1)
conditional neural process
(1)
Papers
Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability
UAI 2026
Invariant and Equivariant Reynolds Networks
JMLR 2024
On the Impact of Data Augmentation on Downstream Performance in Natural Language Processing
ACL 2022
Group Equivariant Conditional Neural Processes
ICLR 2021
Improved generalization bounds of group invariant / equivariant deep networks via quotient feature spaces
UAI 2021