Jingfeng Yao (姚劲枫)

Jingfeng Yao

I'm a third-year Ph.D. student at Huazhong University of Science and Technology (HUST), supervised by Prof. Xinggang Wang, and expected to graduate in 2027. My previous research includes image matting and representation learning. Currently, my research interests focus on generative models.

  • Xiaobing AI (2022.01-2022.12): Algorithm Intern, conducted research on image matting
  • MiniMax (2024.03-present): Algorithm Intern, contributing to Hailuo-01 & Hailuo-02 video generative models

Email GitHub Google Scholar

Awards

Publications

Paper thumbnail
Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices
Ya Zou*, Jingfeng Yao*, Siyuan Yu, Shuai Zhang, Wenyu Liu, Xinggang Wang (* denotes equal contribution)
arXiv preprint, 2025
arXiv code
Paper thumbnail
Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
Jingfeng Yao, Bin Yang, Xinggang Wang
CVPR 2025 Oral (CCF-A)
Rank 1st in ImageNet 256×256 Generation with FID=1.35 (During 2025.01-02)
Accepted with final rating: 5/5/5.
arXiv code
Paper thumbnail
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
Jingfeng Yao, Cheng Wang, Wenyu Liu, Xinggang Wang
NeurIPS 2024 (CCF-A)
Analytical theory that observes diffusion training process with Probability Density Function of SNR.
arXiv code
Paper thumbnail
EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning
Jingfeng Yao, Xinggang Wang, Yuehao Song, Huangxuan Zhao, Jun Ma, Yajie Chen, Wenyu Liu, Bo Wang
arXiv preprint, 2024
arXiv code
Paper thumbnail
LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels
Ziwei Cui*, Jingfeng Yao*, Lunbin Zeng, Juan Yang, Wenyu Liu, Xinggang Wang (* denotes equal contribution)
arXiv preprint, 2024
arXiv code
Paper thumbnail
Matte Anything! Interactive Natural Image Matting with Segment Anything Models
Jingfeng Yao, Xinggang Wang, Lang Ye, Wenyu Liu
Image and Vision Computing (CCF-C), 2024
arXiv code
Paper thumbnail
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang
Information Fusion (IF in 2023=18.6), 2023
Integrated into Hugging Face Hugging Face Transformers with over 1,000,000 monthly downloads
arXiv code

Fun Facts

Volunteer teaching

I spent one year as a volunteer teacher in Lincang, Yunnan Province, representing Huazhong University of Science and Technology. I taught history at Linxiang No.1 Middle School.

News Coverage