Xianliang Li

李賢亮

PhD student · The Institute of Statistical Mathematics

The Graduate University for Advanced Studies, SOKENDAI

li.xianliang (at) ism.ac.jp

About

Bio

I am currently a PhD student at The Institute of Statistical Mathematics and The Graduate University for Advanced Studies, SOKENDAI, advised by Prof. Han Bao, as well as a visiting student at The Chinese University of Hong Kong, advised by Prof. Weiyang Liu.

Previously, I received my M.Eng. in Computer Technology at Shenzhen Institutes of Advanced Technology and University of Chinese Academy of Sciences, where I worked on signal processing and localization advised by Prof. Sheng Xu. Before that, I received my B.Sc. in Physics at Sun Yat-sen University.

Research interest. I am interested in the theoretical understanding of optimizers and deep neural network training. I also work on developing new optimizers and training paradigms. My recent research highlight is the Momentum Filtering, which provides a filtering perspective on the behavior of momentum-based optimizers.

Research

Publications

^* equal contribution · ^† corresponding author

Momentum Filtering

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering

Xianliang Li^*, Zihan Zhang^*, Weiyang Liu, Han Bao^†

Preprint, 2026

Project arXiv Code
On the Performance Analysis of Momentum Method: A Frequency Domain Perspective

Xianliang Li^*, Jun Luo^*, Zhiwei Zheng^*, Hanxiao Wang, Li Luo, Lingkun Wen, Linlong Wu, Sheng Xu^†

ICLR — International Conference on Learning Representations, 2025

OpenReview arXiv Code

Localization and Signal Processing

Time-of-Arrival Simultaneous Sensor and Target Localization With Dynamic Optimal Sensor Placements

Xianliang Li, Sheng Xu^†, K. C. Ho

IEEE Transactions on Aerospace and Electronic Systems, 2025

This work also involves Momentum Filtering.

IEEEXplore
Optimal Sensor Placement Using Decentralized TDOA Sensor Network in Source Localization

Kang Tang, Sheng Xu^†, Xianliang Li, K. C. Ho, He Kong, Kutluyil Dogancay

IEEE Transactions on Aerospace and Electronic Systems, 2026

IEEEXplore
3D AOA Target Tracking Using Multiple Distributed UAVs with Unknown Self-Localizations and Dynamic Anchors

Rongrong Xu, Sheng Xu^†, Xianyong Mu, Xianliang Li, Dashuai Wang, Tiantian Xu

IEEE International Conference on Real-time Computing and Robotics, 2025

IEEEXplore
AOA Sensor Placement for Anchor-Assisted Target Localization in GNSS-Denied Environment: Formulation, Bounds and Optimization

Sheng Xu, Linlong Wu, Xianliang Li, Xinyu Wu, Tiantian Xu^†

IEEE Transactions on Mobile Computing, 2025

IEEEXplore
Systematical Sensor Path Optimization Solutions for AOA Target Localization Accuracy Improvement With Theoretical Analysis

Sheng Xu, Bing Zhu, Xianliang Li, Xinyu Wu, Tiantian Xu^†

IEEE Transactions on Vehicular Technology, 2025

IEEEXplore
3D Source Tracking Using a Position-Unknown AOA Sensor with Measurement Drift and UAV Moving Direction Optimization

Rongrong Xu, Sheng Xu^†, Kaimin Cao, Xianliang Li, Jialiang Wang, Wujing Cao

IEEE International Conference on Real-time Computing and Robotics, 2025

IEEEXplore

Service

Reviewing

Reviewer for NeurIPS 2026, ICLR 2026, DSP 2026.