Yuxiang Xu 许宇翔

My name is Yuxiang Xu. I am currently pursuing a Ph.D. at the Institute of Mechanics, Chinese Academy of Sciences. My research spans AI for Physics and Embodied AI. My current work focuses on latent world models, world action models, and vision-language models. My long-term vision is to build embodied agents that can understand the physical world, predict how it evolves, and translate multimodal perception into reliable action in complex real-world environments.

Portrait of Yuxiang Xu

Recent News

  • 2026/06 “Estimating orbital parameters of direct imaging exoplanet using neural networks” published in Physical Review Research.
  • 2026/05 “Accelerating stochastic gravitational wave backgrounds parameter estimation in pulsar timing arrays with flow matching” published in Physics Letters B.
  • 2026/04 The Taiji detection-pipeline study published in Science China Physics, Mechanics & Astronomy.
  • 2026/04 New preprint: FluxMC, a rapid and high-fidelity inference framework for space-based gravitational-wave observations.
  • 2026/01 Machine-learning-enhanced MCMC framework for EMRI parameter estimation published in Research.
  • 2025/08 “Unlocking New Paths for Efficient Analysis of Gravitational Waves...” published in Chinese Physics Letters.
  • 2025/07 Joined vivo AI Lab as an Assistant AI Algorithm Engineer Intern.
  • 2025/05 Joined AutoLab, Westlake University as a visiting student intern.
  • 2025/05 Launched the Taiji Data Challenge. Read the original preprint.

Publications

Publication details are synchronized with my Google Scholar profile and listed by year.

2026

Estimating orbital parameters of direct imaging exoplanet using neural networks

Bo Liang, Chang Liu, Hanlin Song, Tianyu Zhao, Yuxiang Xu, Zihao Xiao, Manjia Liang, Minghui Du, Wei-Liang Qian, Li-e Qiang, Mingming Sun, Peng Xu, Ziren Luo.

Physical Review Research 8(2), 023341, 2026.

[DOI] [Scholar]

Accelerating stochastic gravitational wave backgrounds parameter estimation in pulsar timing arrays with flow matching

Bo Liang, Chang Liu, Tianyu Zhao, Minghui Du, Manjia Liang, Ruijun Shi, Hong Guo, Yuxiang Xu, Li-e Qiang, Peng Xu, Wei-Liang Qian, Ziren Luo.

Physics Letters B, 140551, 2026.

[DOI] [Scholar]

Towards realistic detection pipelines of Taiji: New challenges in data analysis and high-fidelity simulations of space-based gravitational wave antenna

Minghui Du, Pengcheng Wang, Ziren Luo, Wen-Biao Han, Xin Zhang, Xian Chen, Zhoujian Cao, Yonghe Zhang, He Wang, Xiaodong Peng, Li-E Qiang, Ke An, Yidi Fan, Jiafeng Zhang, Liang-Gui Zhu, Ping Shen, Qianyun Yun, Xiao-Bo Zou, Ye Jiang, Tianyu Zhao, Yong Yuan, Xiaotong Wei, Yuxiang Xu, Bo Liang, Peng Xu, Yueliang Wu.

Science China Physics, Mechanics & Astronomy 69(4), 249501, 2026.

[DOI] [arXiv] [Scholar]

FluxMC: Rapid and High-Fidelity Inference for Space-Based Gravitational-Wave Observations

Bo Liang, Chang Liu, Hanlin Song, Tianyu Zhao, Minghui Du, He Wang, Haohao Gu, Sensen He, Yuxiang Xu, Wei-Liang Qian, Li-e Qiang, Peng Xu, Ziren Luo, Mingming Sun.

arXiv:2604.04957, 2026.

[arXiv] [Scholar]

Toward Efficient and Accurate EMRI Parameter Estimation: A Machine Learning-Enhanced MCMC Framework

Bo Liang, Chang Liu, Hanlin Song, Zhenwei Lyu, Minghui Du, Peng Xu, Ziren Luo, Sensen He, Haohao Gu, Tianyu Zhao, Manjia Liang, Yuxiang Xu, Li-e Qiang, Mingming Sun, Wei-Liang Qian.

Research 9, 1055, 2026.

[DOI] [Scholar]

2025

Unlocking New Paths for Efficient Analysis of Gravitational Waves from Extreme-Mass-Ratio Inspirals with Machine Learning

Bo Liang, Hong Guo, Tianyu Zhao, He Wang, Herik Evangelinelis, Yuxiang Xu, Chang Liu, Manjia Liang, Xiaotong Wei, Yong Yuan, Minghui Du, Peng Xu, Weiliang Qian, Ziren Luo.

Chinese Physics Letters 42(8), 081101, 2025.

[DOI] [arXiv] [Scholar]

Gravitational wave signal denoising and merger time prediction with a deep neural network

Yuxiang Xu, He Wang, Minghui Du, Bo Liang, Peng Xu.

Physical Review D 111(6), 063037, 2025.

[DOI] [arXiv] [Scholar]

2024

Rapid parameter estimation for merging massive black hole binaries using continuous normalizing flows

Bo Liang, Minghui Du, He Wang, Yuxiang Xu, Chang Liu, Xiaotong Wei, Peng Xu, Li-e Qiang, Ziren Luo.

Machine Learning: Science and Technology 5(4), 045040, 2024.

[DOI] [Scholar]

Gravitational wave signal extraction against non-stationary instrumental noises with deep neural network

Yuxiang Xu, Minghui Du, Peng Xu, Bo Liang, He Wang.

Physics Letters B 858, 139016, 2024.

[DOI] [arXiv] [Scholar]

Rapid parameter estimation for extreme mass ratio inspirals using machine learning

Bo Liang, Hong Guo, Tianyu Zhao, Herik Evangelinelis, Yuxiang Xu, Manjia Liang, Xiaotong Wei, Yong Yuan, Peng Xu, Minghui Du, Wei-Liang Qian, Ziren Luo.

arXiv:2409.07957, 2024.

[arXiv] [Scholar]

Rapid parameter estimation for merging massive black hole binaries using ODE-based generative models

Bo Liang, Minghui Du, He Wang, Yuxiang Xu, Chang Liu, Xiaotong Wei, Peng Xu, Li-e Qiang, Ziren Luo.

arXiv:2407.07125, 2024.

[arXiv] [Scholar]

Contact