Yongyi Yang
8 papers · 2021–2025 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(8)
Deep Learning
(6)
Optimization & Theory · Machine Learning
(6)
Architectures
(5)
Core Methods
(4)
Artificial Intelligence
(1)
Mathematics & Optimization
(1)
Core AI
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Models
(1)
Optimization
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
node classification
(3)
representation learning
(3)
graph neural network
(2)
energy minimization
(2)
neural network optimization
(2)
energy function
(2)
unsupervised clustering
(1)
attention mechanism
(1)
in-context learning
(1)
concept representation
(1)
loss landscape
(1)
compositional generalization
(1)
model interpretability
(1)
message passing
(1)
concept learning
(1)
graph topology
(1)
neural representation
(1)
bilevel optimization
(1)
proximal gradient descent
(1)
diffusion model
(1)
Papers
ICLR: In-Context Learning of Representations
ICLR 2025
Implicit vs Unfolded Graph Neural Networks
JMLR 2025
Swing-by Dynamics in Concept Learning and Compositional Generalization
ICLR 2025
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
ICML 2023
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
NeurIPS 2023
Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks
NeurIPS 2022
Transformers from an Optimization Perspective
NeurIPS 2022
Graph Neural Networks Inspired by Classical Iterative Algorithms
ICML 2021