Chia-Yi Hsu
6 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Cross-Pollinator (12) π Interdisciplinary Bridge π Conference Polyglot (4) π§ Keyword Pioneer π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(28)
β
The Questioner
Conferences
NIPS (3)
AAAI (1)
EMNLP (1)
ICLR (1)
Top co-authors
Keywords
adversarial robustness
(2)
model compression
(2)
representation learning
(1)
contrastive learning
(1)
knowledge editing
(1)
data augmentation
(1)
instruction following
(1)
model merging
(1)
responsible ai
(1)
safety alignment
(1)
mutual information
(1)
weight perturbation
(1)
layer-wise analysis
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
model fine-tuning
(1)
generalization gap
(1)
adversarial example
(1)
vertical federated learning
(1)
task vector
(1)
Papers
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
EMNLP 2025
Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
NIPS 2024
Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
ICLR 2024
Adversarial Examples Can Be Effective Data Augmentation for Unsupervised Machine Learning
AAAI 2022
CAFE: Catastrophic Data Leakage in Vertical Federated Learning
NIPS 2021
Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations
NIPS 2021