Bin Xiao

12

Papers

22

Total Citations

Papers (12)

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

Using My Artistic Style? You Must Obtain My Authorization

Transferable 3D Adversarial Shape Completion using Diffusion Models

Focus Stacking with High Fidelity and Superior Visual Effects

Breaking Grid Constraints: Dynamic Graph Reconstruction Network for Multi-organ Segmentation

CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training

Power of Diversity: Enhancing Data-Free Black-Box Attack with Domain-Augmented Learning

Improving Transferable Targeted Attacks with Feature Tuning Mixup

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network

Who Controls the Authorization? Invertible Networks for Copyright Protection in Text-to-Image Synthesis

PLA: Prompt Learning Attack against Text-to-Image Generative Models