Yuxiao Luo

Yuxiao Luo

Auto-generated profile, based on publicly available information

Yuxiao Luo

Chinese Academy of Sciences

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 January 2025 in Pattern Recognition
Verified
Journal Article
Closed access
YLYuxiao Luo
Yuxiao Luo
SZSongming Zhang
Songming Zhang
ZLZiyu Lyu
Ziyu Lyu
YHYuhan Hu
Yuhan Hu

14 June 2025 in Computers, Environment and Urban Systems
Verified
Journal Article
Closed access
YLYuxiao Luo
Yuxiao Luo
Ling YinLing Yin
Ling Yin
KZKemin Zhu
Kemin Zhu
KLKang Liu
Kang Liu

8 July 2025 in Neural Networks
Verified
Journal Article
Closed access
SZSongming Zhang
Songming Zhang
YLYuxiao Luo
Yuxiao Luo
ZLZiyu Lyu
Ziyu Lyu
Xiaofeng ChenXiaofeng Chen
Xiaofeng Chen

1 October 2025 in Information Fusion
Verified
Journal Article
Closed access
YLYuxiao Luo
Yuxiao Luo
SZSongming Zhang
Songming Zhang
KLKang Liu
Kang Liu
Yang XuYang Xu
Yang Xu
Ling YinLing Yin
Ling Yin

3 November 2025
Verified
Conference Paper
Open access
GLGuangyue Li
Guangyue Li
YLYuxiao Luo
Yuxiao Luo
SLShen LIANG
Shen LIANG
JWJinghan Wang
Jinghan Wang
XGXiaogang Guo
Xiaogang Guo
Yang XuYang Xu
Yang Xu

8 December 2025 in arXiv
Verified
Preprint
Open access
PDF file
YLYuxiao Luo
Yuxiao Luo
SZSongming Zhang
Songming Zhang
SRSijie Ruan
Sijie Ruan
SCSiran Chen
Siran Chen
KLKang Liu
Kang Liu
Ling YinLing Yin
Ling Yin
Modeling human mobility is vital for extensive applications such as transportation planning and epidemic modeling. With the rise of the Artificial Intelligence Generated Content (AIGC) paradigm, recent works explore synthetic trajectory generation using autoregressive and diffusion models. While these methods show promise for generating single-day trajectories, they remain limited by inefficiencies in long-term generation (e.g., weekly trajectories) and a lack of explicit spatiotemporal multi-scale modeling. This study proposes Multi-Scale Spatio-Temporal AutoRegression (M-STAR), a new framework that generates long-term trajectories through a coarse-to-fine spatiotemporal prediction process. M-STAR combines a Multi-scale Spatiotemporal Tokenizer that encodes hierarchical mobility patterns with a Transformer-based decoder for next-scale autoregressive prediction. Experiments on two real-world datasets show that M-STAR outperforms existing methods in fidelity and significantly improves generation speed. The data and codes are available at https://github.com/YuxiaoLuo0013/M-STAR.