Picture for Zhiyuan Ma

Zhiyuan Ma

CMAL: A Novel Cross-Modal Associative Learning Framework for Vision-Language Pre-Training

Add code
Oct 16, 2024
Viaarxiv icon

DH-VTON: Deep Text-Driven Virtual Try-On via Hybrid Attention Learning

Add code
Oct 16, 2024
Viaarxiv icon

Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices

Add code
Oct 15, 2024
Viaarxiv icon

Mirror-Consistency: Harnessing Inconsistency in Majority Voting

Add code
Oct 07, 2024
Viaarxiv icon

Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking

Add code
Jul 19, 2024
Viaarxiv icon

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

Add code
Jul 13, 2024
Viaarxiv icon

ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation

Add code
Jul 02, 2024
Viaarxiv icon

Neural Residual Diffusion Models for Deep Scalable Vision Generation

Add code
Jun 19, 2024
Viaarxiv icon

One-Step Effective Diffusion Network for Real-World Image Super-Resolution

Add code
Jun 12, 2024
Viaarxiv icon

UltraMedical: Building Specialized Generalists in Biomedicine

Add code
Jun 06, 2024
Viaarxiv icon