Chia-Mu Yu
15 papers · 2021–2026 · 8 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (43) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§
Keyword Pioneer
π§¬
Topic Evolution
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β
The Questioner
(2)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(78)
Top co-authors
Research topics
Machine Learning
(12)
Deep Learning
(10)
Artificial Intelligence
(9)
Application Areas
(9)
Core AI
(7)
Learning Types Β· Machine Learning
(5)
Models
(5)
Learning Types Β· Deep Learning
(4)
Optimization & Theory Β· Machine Learning
(3)
Techniques
(3)
Computer Vision
(2)
Security & Privacy
(2)
Differential Privacy
(2)
Generation
(2)
Optimization & Theory Β· Deep Learning
(2)
Keywords
parameter-efficient fine-tuning
(3)
differential privacy
(3)
low-rank adaptation
(3)
image generation
(2)
image synthesis
(2)
model compression
(2)
privacy-utility trade-off
(2)
safety alignment
(2)
model merging
(2)
adversarial robustness
(2)
representation learning
(1)
data poisoning
(1)
transfer learning
(1)
backdoor defense
(1)
langevin dynamics
(1)
semi-supervised learning
(1)
data augmentation
(1)
knowledge editing
(1)
adversarial learning
(1)
personalized generation
(1)
Papers
Defending Unauthorized Model Merging via Dual-Stage Weight Protection
CVPR 2026
Defending Against Repetitive Backdoor Attacks on Semi-Supervised Learning through Lens of Rate-Distortion-Perception Trade-Off
WACV 2025
Differentially Private Fine-Tuning of Diffusion Models
ICCV 2025
DiffuseKronA: A Parameter Efficient Fine-Tuning Method for Personalized Diffusion Models
WACV 2025
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
EMNLP 2025
The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?
ACML 2025
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
ICLR 2024
Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
ICLR 2024
Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
NeurIPS 2024
Exploring the Benefits of Visual Prompting in Differential Privacy
ICCV 2023
Adversarial Examples Can Be Effective Data Augmentation for Unsupervised Machine Learning
AAAI 2022
DPGEN: Differentially Private Generative Energy-Guided Network for Natural Image Synthesis
CVPR 2022
CAFE: Catastrophic Data Leakage in Vertical Federated Learning
NeurIPS 2021
Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations
NeurIPS 2021
Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation With Manipulable Semantics
CVPR 2021