kangil kim
7 papers · 2017–2025 · 5 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (19) π£ Hot Topic Early Bird
π
Keyword Champion
Top co-authors
Research topics
Machine Learning
(6)
Deep Learning
(5)
Core Methods
(4)
Learning Types Β· Machine Learning
(4)
Natural Language Processing
(3)
Architectures
(2)
Learning Types Β· Deep Learning
(2)
Techniques
(2)
Understanding
(2)
Artificial Intelligence
(1)
Mathematics & Optimization
(1)
Applications
(1)
Core AI
(1)
Mathematics
(1)
Models
(1)
Keywords
unsupervised learning
(3)
neural network
(2)
grammar induction
(2)
metric learning
(1)
vision transformer
(1)
few-shot learning
(1)
neural machine translation
(1)
syntactic parsing
(1)
model architecture
(1)
feature embedding
(1)
unsupervised parsing
(1)
semantic consistency
(1)
visual classification
(1)
inner product
(1)
angular similarity
(1)
hierarchical structure
(1)
knowledge graph embedding
(1)
entity embedding
(1)
inductive bia
(1)
neural collapse
(1)
Papers
Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction
EMNLP 2025
RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge Graph
ACL 2025
Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
ICLR 2024
Label-Focused Inductive Bias over Latent Object Features in Visual Classification
ICLR 2024
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
ACL 2024
Spherization Layer: Representation Using Only Angles
NeurIPS 2022
Concept Equalization to Guide Correct Training of Neural Machine Translation
IJCNLP 2017