Chongyang Ma
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
arXiv 2025
MAGREF: Masked Guidance for Any-Reference Video Generation
arXiv 2025
IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting
arXiv 2025
DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
arXiv 2024
InterFusion: Text-Driven Generation of 3D Human-Object Interaction
arXiv 2024
CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion
arXiv 2024
MotionCrafter: One-Shot Motion Customization of Diffusion Models
arXiv 2023
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
arXiv 2023
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
arXiv 2023
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
augmentation-aware-self-supervision-for-data
Inversion-Based Style Transfer with Diffusion Models
CVPR 2023 1
Affiliations
Frequent co-authors
10from 11 papers