Ziyi Dong
4 papers · 2022–2025 · 4 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
❓
The Questioner
(2)
Top co-authors
Research topics
Deep Learning
(3)
Machine Learning
(3)
Models
(3)
Computer Vision
(2)
Generation
(2)
Application Areas
(1)
Architectures
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
model compression
(1)
knowledge distillation
(1)
adversarial training
(1)
efficient computing
(1)
stochastic process
(1)
gaussian noise
(1)
generative model
(1)
diffusion model
(1)
convolutional neural network
(1)
adversarial defense
(1)
denoising diffusion
(1)
image quality
(1)
convolutional architecture
(1)
diffusion purification
(1)
pyramid convolution
(1)
self-attention distillation
(1)
text to image
(1)
detector accuracy
(1)
contrast
(1)
saturation
(1)
Papers
Are High-Quality AI-Generated Images More Difficult for Models to Detect?
ICML 2025
Can We Achieve Efficient Diffusion Without Self-Attention? Distilling Self-Attention into Convolutions
ICCV 2025
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
ICLR 2025
Adversarially-Aware Robust Object Detector
ECCV 2022