Picture for Kai Zhu

Kai Zhu

ViViD: Video Virtual Try-on using Diffusion Models

Add code
May 20, 2024
Viaarxiv icon

InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

Add code
Apr 17, 2024
Viaarxiv icon

Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation

Add code
Mar 22, 2024
Figure 1 for Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation
Figure 2 for Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation
Figure 3 for Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation
Figure 4 for Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation
Viaarxiv icon

Intention-driven Ego-to-Exo Video Generation

Add code
Mar 17, 2024
Figure 1 for Intention-driven Ego-to-Exo Video Generation
Figure 2 for Intention-driven Ego-to-Exo Video Generation
Figure 3 for Intention-driven Ego-to-Exo Video Generation
Figure 4 for Intention-driven Ego-to-Exo Video Generation
Viaarxiv icon

CCM: Adding Conditional Controls to Text-to-Image Consistency Models

Add code
Dec 12, 2023
Viaarxiv icon

Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detection

Add code
Dec 04, 2023
Viaarxiv icon

Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation

Add code
Sep 22, 2023
Figure 1 for Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
Figure 2 for Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
Figure 3 for Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
Figure 4 for Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
Viaarxiv icon

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models

Add code
Aug 06, 2023
Figure 1 for Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
Figure 2 for Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
Figure 3 for Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
Figure 4 for Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models
Viaarxiv icon

Eliminating Lipschitz Singularities in Diffusion Models

Add code
Jun 20, 2023
Figure 1 for Eliminating Lipschitz Singularities in Diffusion Models
Figure 2 for Eliminating Lipschitz Singularities in Diffusion Models
Figure 3 for Eliminating Lipschitz Singularities in Diffusion Models
Figure 4 for Eliminating Lipschitz Singularities in Diffusion Models
Viaarxiv icon

Cones 2: Customizable Image Synthesis with Multiple Subjects

Add code
May 30, 2023
Figure 1 for Cones 2: Customizable Image Synthesis with Multiple Subjects
Figure 2 for Cones 2: Customizable Image Synthesis with Multiple Subjects
Figure 3 for Cones 2: Customizable Image Synthesis with Multiple Subjects
Figure 4 for Cones 2: Customizable Image Synthesis with Multiple Subjects
Viaarxiv icon