Picture for Yingqian Cui

Yingqian Cui

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models

Add code
Jun 21, 2024
Viaarxiv icon

Copyright Protection in Generative AI: A Technical Perspective

Add code
Feb 04, 2024
Figure 1 for Copyright Protection in Generative AI: A Technical Perspective
Figure 2 for Copyright Protection in Generative AI: A Technical Perspective
Figure 3 for Copyright Protection in Generative AI: A Technical Perspective
Figure 4 for Copyright Protection in Generative AI: A Technical Perspective
Viaarxiv icon

Superiority of Multi-Head Attention in In-Context Linear Regression

Add code
Jan 30, 2024
Viaarxiv icon

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models

Add code
Oct 03, 2023
Figure 1 for FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
Figure 2 for FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
Figure 3 for FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
Figure 4 for FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
Viaarxiv icon

On the Generalization of Training-based ChatGPT Detection Methods

Add code
Oct 03, 2023
Figure 1 for On the Generalization of Training-based ChatGPT Detection Methods
Figure 2 for On the Generalization of Training-based ChatGPT Detection Methods
Figure 3 for On the Generalization of Training-based ChatGPT Detection Methods
Figure 4 for On the Generalization of Training-based ChatGPT Detection Methods
Viaarxiv icon