Yihang Gao
6 papers · 2022–2025 · 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)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Deep Learning
(4)
Optimization & Theory · Machine Learning
(4)
Architectures
(3)
Optimization & Theory · Deep Learning
(3)
Artificial Intelligence
(1)
Computer Science
(1)
Mathematics & Optimization
(1)
Application Areas
(1)
Applications
(1)
Core AI
(1)
Core Methods
(1)
Mathematics
(1)
Optimization
(1)
Techniques
(1)
Keywords
attention mechanism
(3)
length extrapolation
(2)
transformer architecture
(2)
neural network optimization
(1)
global optimization
(1)
gradient descent
(1)
feature map
(1)
physics-informed neural network
(1)
partial differential equation
(1)
hessian eigenvalue
(1)
gradient vanishing
(1)
positional encoding
(1)
position encoding
(1)
inference speed
(1)
matrix-vector multiplication
(1)
softmax function
(1)
cubic regularization
(1)
plug-and-play framework
(1)
kv cache reduction
(1)
gram matrice
(1)
Papers
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation
ACL 2025
Self-Adjust Softmax
EMNLP 2025
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
ICML 2025
DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
NeurIPS 2024
Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
ICML 2023
Approximate Secular Equations for the Cubic Regularization Subproblem
NeurIPS 2022