尹相臣 (Xiangchen Yin)
[中文]

University of Science and Technology of China（USTC）

Research Interests: Computer Vision, Multi-modal Generative Model, Image/Video Generation


yinxiangchen@mail.ustc.edu.cn

Hefei, China

Resume

Education

University of Science and Technology of China（USTC）
2025.05 - Now
Artificial Intelligence   Ph.D. Candidate
University of Science and Technology of China（USTC）
2023.09 - 2025.05
Computer Technology   M.S. (Postgraduate Recommendation)
Qufu Normal University（QFNU）
2019.09 - 2023.06
Internet of Things Engineering   Bachelor

Industry Experiences

Li Xiang Auto, Space AI
2024.06 - 2024.10
Research Intern (School-Company Cooperation Project)
Research Topic: Diffusion for Video Generation.
Tencent YouTu Lab
2023.10 - 2024.06
Computer Vision Research Intern
Research Topic: Visual Text Generation and Edit via Text-to-Image Diffusion Model.
Tsinghua University, State Key Laboratory of Automotive Safety and Energy
2022.03 – 2023.03
Research Intern
Research Topic: Multimodal Lane Perception Models in Nighttime Scenes.

Publications

Note: * indicates the joint first author / student first autor.
DeCo-VAE: Learning Compact Latents for Video Reconstruction via Decoupled Representation
Xiangchen Yin, Jiahui Yuan, Zhangchi Hu, Wenzhang Sun, Jie Chen, Xiaozhen Qiao, Hao Li, Xiaoyan Sun
Arxiv'25
[Arxiv]
GRPose: Learning Graph Relations for Human Image Generation with Pose Priors
Xiangchen Yin, Donglin Di, Lei Fan, Hao Li, Wei Chen, Xiaofei Gou, Yang Song, Xiao Sun, Xun Yang
AAAI'25 AAAI Conference on Artificial Intelligence (AAAI), 2025.
CCF A Conference
[Paper] [Arxiv] [Project Page] [GitHub ]
Structure-Guided Diffusion Transformer for Low-Light Image Enhancement
Xiangchen Yin, Zhenda Yu, Longtao Jiang, Xin Gao, Xiao Sun, Zhi Liu, Xun Yang
TMM'25 IEEE Transactions on Multimedia (TMM).
CCF B & THU A Journal, IF=9.7
[Paper] [Arxiv]
Adaptive Entropy Multi-modal Fusion for Nighttime Lane Segmentation
Xinyu Zhang, Xiangchen Yin*, Xin Gao, Tianheng Qiu, Li Wang, Jun Li
TIV'24 IEEE Transactions on Intelligent Vehicles (TIV).
Student first autor, IF=14.3
[Paper]
DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision
Xiangchen Yin*, Zhenda Yu*, Xin Gao, Xiao Sun
ICASSP'25 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025.
CCF B Conference
[Paper] [Arxiv]
PE-YOLO: Pyramid Enhancement Network for Dark Object Detection
Xiangchen Yin, Zhenda Yu, Zetao Fei, Wenjun Lv, Xin Gao
ICANN'23 International Conference on Artificial Neural Networks (ICANN), 2023.
CCF C Conference
[Paper] [GitHub ] [Media Report]

Awards & Honors

2022 第十五届中国大学生计算机设计大赛全国总决赛三等奖
2021 第十二届蓝桥杯全国软件信息技术人才大赛全国总决赛二等奖（全国 2.5%）