Yaoyu Zhang
9 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)
🐣
Hot Topic Early Bird
🏆
Keyword Champion
(2)
Venues
Top co-authors
Research topics
Machine Learning
(9)
Deep Learning
(7)
Architectures
(7)
Optimization & Theory · Machine Learning
(7)
Optimization & Theory · Deep Learning
(3)
Artificial Intelligence
(1)
Computer Vision
(1)
Mathematics & Optimization
(1)
Analysis
(1)
Application Areas
(1)
Core AI
(1)
Core Methods
(1)
Optimization
(1)
Processing
(1)
Keywords
training dynamics
(2)
transformer model
(2)
deep neural network
(2)
neural network optimization
(2)
phase diagram
(2)
sample complexity
(1)
chain-of-thought reasoning
(1)
matrix factorization
(1)
matrix completion
(1)
efficient computing
(1)
optimization theory
(1)
network optimization
(1)
visual tracking
(1)
nuclear norm
(1)
symbolic reasoning
(1)
gradient flow
(1)
loss landscape
(1)
weight initialization
(1)
implicit regularization
(1)
spiking neural network
(1)
Papers
Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
JMLR 2025
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
EMNLP 2025
VISTREAM: Improving Computation Efficiency of Visual Streaming Perception via Law-of-Charge-Conservation Inspired Spiking Neural Network
CVPR 2025
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
NeurIPS 2024
Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
NeurIPS 2024
Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width
NeurIPS 2022
Towards Understanding the Condensation of Neural Networks at Initial Training
NeurIPS 2022
Embedding Principle of Loss Landscape of Deep Neural Networks
NeurIPS 2021
Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit
JMLR 2021