Xin Ma

Xin Ma

PhD Student

Biography

Welcome πŸ‘‹ I am currently a Ph.D candidate at Monash University, supervised by Prof. Tien-Tsin Wong, Prof. Fang-Yuan Li, and Prof. Cunjian Chen. Previously, I received the M.S degree from University of Chinese Academy of Sciences, where I studied at CRIPAC under the leadership of Prof. Tieniu Tan and was supervised by Prof. Ran He. My research interests include video and image generation, model compression, face recognition, large-scale generative models and so on.

Recent News

Top Post
Top Post
πŸ’žοΈ Always pursuse research collaborations. Feel free to contact me if you are interested
πŸŽ‰ I was recognized as the outstanding reviewer for CVPR 2025
⬆️ one paper OmniPainter was released on arXiv
πŸŽ‰ one paper Latte was accpeted by Transactions on Machine Learning Research (TMLR)
πŸŽ‰ one paper Cinemo was accpeted by IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
πŸŽ‰ one paper LaVie was accpeted by International Journal of Computer Vision (IJCV)
πŸŽ‰ one paper LEO was accpeted by International Journal of Computer Vision (IJCV)
See all posts

Selected Publications

Here is a selection of research papers that I have worked on over the years.

Quickly discover all papers by filtering publications.
Consistent and Controllable Image Animation with Motion Diffusion Models
Published in Computer Vision and Pattern Recognition (CVPR), 2025, CCF-A, Stars
PDF Cite Code Project
Consistent and Controllable Image Animation with Motion Diffusion Models
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
Published in International Conference on Learning Representations (ICLR), 2024, Stars
PDF Cite Code Project
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
Latte: Latent Diffusion Transformer for Video Generation
Published in Transactions on Machine Learning Research (TMLR), 2025, Stars
PDF Cite Code Project
Latte: Latent Diffusion Transformer for Video Generation
LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models
Published in International Journal of Computer Vision (IJCV), 2024, JCR Q1 & CCF-A, Stars
PDF Cite Code Project
LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

Contact



Β©Xin Ma 马鑫 · Last update on June 2025 · Powered by Hugo Blox