Linwei Tao
7 papers · 2023–2025 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
Top co-authors
Research topics
Machine Learning
(7)
Deep Learning
(6)
Optimization & Theory · Machine Learning
(6)
Learning Types
(3)
Optimization & Theory · Deep Learning
(3)
Artificial Intelligence
(2)
Application Areas
(2)
Architectures
(2)
Core AI
(2)
Core Methods
(2)
Models
(2)
Techniques
(2)
Computer Vision
(1)
Generation
(1)
Keywords
model calibration
(4)
diffusion model
(2)
focal loss
(2)
confidence score
(2)
deep neural network
(2)
uncertainty estimation
(2)
data attribution
(1)
regularization method
(1)
prediction accuracy
(1)
brier score
(1)
post-hoc calibration
(1)
training data influence
(1)
logit manipulation
(1)
neural network
(1)
feature clipping
(1)
gradient weighting
(1)
uncertainty
(1)
calibrated reannotation
(1)
calibration-aware data augmentation
(1)
uncertainty quantification
(1)
Papers
Beyond One-Hot Labels: Semantic Mixing for Model Calibration
ICML 2025
Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
ICLR 2025
Feature Clipping for Uncertainty Calibration
AAAI 2025
Uncertainty Weighted Gradients for Model Calibration
CVPR 2025
A Benchmark Study on Calibration
ICLR 2024
Calibrating a Deep Neural Network with Its Predecessors
IJCAI 2023
Dual Focal Loss for Calibration
ICML 2023