Qinghua Tao
6 papers · 2022–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
๐
Conference Polyglot
(3)
๐
Interdisciplinary Bridge
๐งญ
Keyword Pioneer
๐ฃ
Hot Topic Early Bird
๐
Cross-Pollinator
(15)
Conferences
NIPS (3)
ICML (2)
ICLR (1)
Top co-authors
Keywords
principal component analysis
(1)
model robustness
(1)
model architecture
(1)
low-rank approximation
(1)
kernel pca
(1)
singular value decomposition
(1)
reconstruction error
(1)
non-linear mapping
(1)
adversarial attack
(1)
adversarial defense
(1)
out-of-distribution detection
(1)
kernel machine
(1)
query attack
(1)
asymmetric kernel
(1)
kernel singular value decomposition
(1)
primal representation
(1)
logits modification
(1)
Papers
Kernel PCA for Out-of-Distribution Detection
NIPS 2024
Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes
ICML 2024
Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nystrรถm method
ICML 2024
Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation
NIPS 2023
Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions
ICLR 2023
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks
NIPS 2022