Picture for Zeke Xie

Zeke Xie

MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Portrait Few-Step Synthesis

Add code
Mar 17, 2025
Viaarxiv icon

CoRe^2: Collect, Reflect and Refine to Generate Better and Faster

Add code
Mar 12, 2025
Viaarxiv icon

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice

Add code
Mar 07, 2025
Viaarxiv icon

Learning from Ambiguous Data with Hard Labels

Add code
Jan 08, 2025
Viaarxiv icon

A Simple and Efficient Baseline for Zero-Shot Generative Classification

Add code
Dec 17, 2024
Figure 1 for A Simple and Efficient Baseline for Zero-Shot Generative Classification
Figure 2 for A Simple and Efficient Baseline for Zero-Shot Generative Classification
Figure 3 for A Simple and Efficient Baseline for Zero-Shot Generative Classification
Figure 4 for A Simple and Efficient Baseline for Zero-Shot Generative Classification
Viaarxiv icon

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

Add code
Dec 17, 2024
Viaarxiv icon

Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer

Add code
Nov 16, 2024
Viaarxiv icon

Golden Noise for Diffusion Models: A Learning Framework

Add code
Nov 14, 2024
Figure 1 for Golden Noise for Diffusion Models: A Learning Framework
Figure 2 for Golden Noise for Diffusion Models: A Learning Framework
Figure 3 for Golden Noise for Diffusion Models: A Learning Framework
Figure 4 for Golden Noise for Diffusion Models: A Learning Framework
Viaarxiv icon

Pre-trained Molecular Language Models with Random Functional Group Masking

Add code
Nov 03, 2024
Figure 1 for Pre-trained Molecular Language Models with Random Functional Group Masking
Figure 2 for Pre-trained Molecular Language Models with Random Functional Group Masking
Figure 3 for Pre-trained Molecular Language Models with Random Functional Group Masking
Figure 4 for Pre-trained Molecular Language Models with Random Functional Group Masking
Viaarxiv icon

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis

Add code
Oct 05, 2024
Figure 1 for IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
Figure 2 for IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
Figure 3 for IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
Figure 4 for IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
Viaarxiv icon