š About Me
Hi,
š± Iām Xiaoxiao Ma, 2nd-year graduate student in USTC
š My research interest includes:
- Image resotration, image enhancement
- Generative models, text-to-image generation
š« And Iā m currently looking for collaborations, internship or Ph.D. position, feel free to contact me via email
š„ News
- 2024.09: Ā Delighted to announce that MPI was accepted by NeurIPS 2024!
- 2024.09: Ā I was invited to give a talk at ByteDance as the author of STAR! See slides here
- 2024.06: Ā STAR was released on Arxiv.
š Publications
Arxiv 2024
STAR: Scale-wise Text-to-image generation via Auto-Regressive representations
Xiaoxiao Ma, Mohan Zhou, Tao Liang, Yalong Bai, Tiejun Zhao, Huaian Chen, Yi Jin
- STAR is a novel scale-wise text-to-image model that is effective and efficient in performance
- Notably, STAR shows efficiency by requiring 2.95s to generate 512Ć512 images (compared to 6.48s for PixArt-Ī±)
NeurIPS 2024
Masked Pre-trained Model Enables Universal Zero-shot Denoiser
Xiaoxiao Ma, Zhixiang Wei, Yi Jin, Pengyang Ling, Tianle Liu, Ben Wang, Junkang Dai, Huaian Chen, Enhong Chen
- MPI is a zero-shot denoising pipeline designed for many types of noise degradations
- Only around 10s takes for a MPI to denoise on single noisy image
CVPR 2024
Zhixiang Wei, Lin Chen, Yi Jin*, Xiaoxiao Ma, Tianle Liu, Pengyang Ling, Ben Wang, Huaian Chen, Jinjin Zheng
- Rein is a PEFT framework based on vision foundation models for domain generalized semantic segmentation (DGSS) with merely 1% trainable parameters
š Academic Service (Reviewer)
- IEEE TPAMI
š Honors and Awards
- 2022~2024 The First Prize Scholarship of USTC for three continusous years
- 2024 National Scholarship for Undergraduate Students
š Educations
- 2022.09 - now, University of Science and Technology of China, Anhui, Master candidate in Computer Vision
- 2018.09 - 2022.06, China Agricultural University, Beijing. B. Eng in Computer Science