Picture for Qian Wang

Qian Wang

Henry

Automatic Left Ventricular Cavity Segmentation via Deep Spatial Sequential Network in 4D Computed Tomography Studies

Add code
Dec 17, 2024
Viaarxiv icon

Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL

Add code
Dec 17, 2024
Viaarxiv icon

OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation

Add code
Dec 12, 2024
Viaarxiv icon

An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers

Add code
Dec 09, 2024
Viaarxiv icon

Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer

Add code
Dec 06, 2024
Figure 1 for Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
Figure 2 for Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
Figure 3 for Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
Figure 4 for Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
Viaarxiv icon

Hidden Data Privacy Breaches in Federated Learning

Add code
Nov 27, 2024
Viaarxiv icon

StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart

Add code
Nov 21, 2024
Viaarxiv icon

Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement

Add code
Nov 15, 2024
Viaarxiv icon

ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization

Add code
Nov 06, 2024
Figure 1 for ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
Figure 2 for ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
Figure 3 for ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
Figure 4 for ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
Viaarxiv icon

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Add code
Nov 05, 2024
Figure 1 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Figure 2 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Figure 3 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Figure 4 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Viaarxiv icon