Jinpeng Yu
- Controllable Image Generation
- Multimodal Understanding and Generation
- Multimodal AI Agent
- 3D Understanding and Reconstruction
I am eager to discuss and collaborate with people from diverse backgrounds.
Let's explore new opportunities and do something fancy together!
Jinpeng Yu (于劲鹏) is currently the Creation Agent Algorithm Lead at Qwen App, Alibaba Group, where he works on multimodal AI agents and generative AI for content creation. He previously worked on the AIGC team at Xiaohongshu, focusing 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).
* indicates equal contribution.
![[motion]](images/PPlaneSDF_architecture.png)
Pseudo-plane regularization for high-fidelity SDF-based reconstruction of texture-less indoor scenes.
![[motion]](images/GeoFormer_teaser.png)
![[Poster]](https://github.com/Jinpeng-Yu/GeoFormer/blob/master/posters/GeoFormer_Poster_LaTex/GeoFormer_poster_landscape.png){kind=link}
![[motion]](https://ssr-encoder.github.io/SSR-Encoder_files/teaser_v3.png)
Encodes selective subject representation from reference images for subject-driven image generation.
![[motion]](images/Fast_Personlized_T2I.png)
![[motion]](images/P2SDF_teaser.png)
Signed distance field with planar priors for neural indoor scene reconstruction.