Shikai Qiu
10 papers · 2023–2025 · 2 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 ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (25) 💎 Century Club · Bronze ❓ The Questioner
🗃️
Keyword Collector
(61)
Venues
Top co-authors
Research topics
Machine Learning
(10)
Artificial Intelligence
(5)
Deep Learning
(5)
Application Areas
(4)
Core AI
(4)
Core Methods
(4)
Optimization & Theory
(4)
Architectures
(3)
Natural Language Processing
(2)
Generation
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Techniques
(2)
Bayesian & Probabilistic
(1)
Learning Paradigms
(1)
Keywords
bayesian inference
(2)
neural network
(2)
structured matrice
(2)
domain generalization
(1)
uncertainty quantification
(1)
neural network optimization
(1)
covariate shift
(1)
out-of-distribution generalization
(1)
scaling law
(1)
time series forecasting
(1)
maximum a posteriori
(1)
classifier
(1)
learning rate decay
(1)
learning rate
(1)
empirical baye
(1)
multimodal distribution
(1)
language model
(1)
foundation model
(1)
efficient computing
(1)
regularization
(1)
Papers
Customizing the Inductive Biases of Softmax Attention using Structured Matrices
ICML 2025
Position: Supervised Classifiers Answer the Wrong Questions for OOD Detection
ICML 2025
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
ICML 2025
Compute Better Spent: Replacing Dense Layers with Structured Matrices
ICML 2024
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
NeurIPS 2024
Transferring Knowledge From Large Foundation Models to Small Downstream Models
ICML 2024
Function-Space Regularization in Neural Networks: A Probabilistic Perspective
ICML 2023
Large Language Models Are Zero-Shot Time Series Forecasters
NeurIPS 2023
Should We Learn Most Likely Functions or Parameters?
NeurIPS 2023
Simple and Fast Group Robustness by Automatic Feature Reweighting
ICML 2023