Jinpeng Yu

Work Email: yujinpeng (at) xiaohongshu.com
School Email: yujp1 (at) alumni.shanghaitech.edu.cn
Research Interests
  • Controllable Image Generation
  • Multimodal Understanding and Generation
  • Multimodal AI Agent
  • 3D Understanding and Reconstruction
Biography

Jinpeng Yu (于劲鹏) is currently a researcher on AIGC team at Xiaohongshu, where he focuses on controllable and conditional image generation, as well as multimodal understanding and generation. He received his Bachelor's degree with honors from the Harbin Institute of Technology (HIT) in June 2021, and obtained his Master's degree in SIST from ShanghaiTech University in 2024, under the supervision of Prof. Shenghua Gao (高盛华, HKU).

I am eager to discuss and collaborate with people from diverse backgrounds. Let's explore new opportunities and do something fancy together!

Selected Publications (Full List)
[motion]
Pseudo-plane Regularized Signed Distance Field for Neural Indoor Scene Reconstruction
Jinpeng Yu, Jing Li, Ruoyu Wang and Shenghua Gao.
International Journal of Computer Vision (IJCV), 2024
[Paper]
[motion]
GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Jinpeng Yu, Binbin Huang, Yuxuan Zhang, Huaxia Li, Xu Tang, and Shenghua Gao.
ACM International Conference on Multimedia (ACM MM), 2024
[Paper] [Poster] [Code]
[motion]
SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation
Yuxuan Zhang, Jiaming Liu, Yiren Song, Rui Wang, Jinpeng Yu*, Hao Tang, Huaxia Li, Xu Tang, Yao Hu, Han Pan and Zhongliang Jing. (* means co-author)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[Project Page] [Code]
[motion]
Fast Personalized Text to Image Synthesis with Attention Injection
Yuxuan Zhang, Yiren Song, Jinpeng Yu*, Han Pan and Zhongliang Jing. (* means co-corresponding author)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
[Paper] Oral
[motion]
P2SDF for Neural Indoor Scene Reconstruction
Jing Li, Jinpeng Yu*, Ruoyu Wang, Zhengxin Li, Zhengyu Zhang, Lina Cao, and Shenghua Gao. (* means co-first author)
arXiv preprint (arXiv), 2023
[Paper]
Talks
  • [08/2024] Hosted by Xiaohongshu. A Review of Recent AIGC Customized Image Generation Techniques
    • Experiences
  • [07/2024 - present] AIGC Researcher at Xiaohongshu AIGC Team (Full-time Employee)
  • [05/2023 - 06/2024] AIGC Research Intern at Xiaohongshu AIGC Team.
  • [Autumn 2022] Teaching Assistant of SI200: Academic Paper Writing, Prof: Song Liu, ShanghaiTech
  • [Autumn 2021] Teaching Assistant of CS272: Computer Vision II, Prof: Shenghua Gao, ShanghaiTech
    • Activities
  • Conference Reviewer of: CVPR (2024, 2025), ICCV (2025), ECCV (2024), ACM MM (2024), ICME (2024)
  • Journal Reviewer of: IJCV
    • Selected Honors
  • Academic Excellence Scholarship, ShanghaiTech (2022, 2023, 2024)
  • Outstanding Graduate, HIT (2021)
  • National Scholarship, Ministry of Education, People's Republic of China (2020)
  • Outstanding Student, HIT (2019, 2020)
  • Merit Student, HIT (2019, 2020)
    • Passions (Discovering, Recording, and Creating Beauty)
  • Traveling Around, Photography (Nikon Z6 and my powerful iPhone), Hiking (Mount Siguniang, 4,668m), Taekwondo (8th Kup)
  • Language Enthusiast, Sports Enthusiast (Skiing, Swimming, Badminton, Table Tennis)