Xin Li (李鑫)
Accelerate Engineering with LLM Automation
I am building LLM systems that automate wireless-communication design and embodied-AI workflows. My vision is to turn complex engineering problems into self-optimising, reproducible pipelines.
I am currently pursuing my Ph.D. at Nanyang Technological University (NTU), Singapore, under the supervision of Prof. Yuen Chau, IEEE Fellow. Previously, I obtained my M.Eng degrees from Peking University in 2021 and B.Eng from Northeastern University in 2018.
💡 Always looking for collaborators on LLM-powered engineering automation. Feel free to drop me a line!
Latest News
Education
Ph.D. in Electrical and Electronic Engineering
Nanyang Technological University
Supervisor: Prof. Yuen Chau, IEEE Fellow
Jan. 2025 - Present
M.Eng. in Electronics and Communication Engineering
Peking University
Supervisor: Prof. Jinlong Lin
Sept. 2018 - Jul. 2021
B.Eng. in Measurement and Control Technology and Instruments
Northeastern University
Sept. 2014 - Jun. 2018
Professional Experience
Research Assistant
Nanyang Technological University (NTU)
Supervisor: Prof. Yuen Chau
- Leveraged Large Language Models (LLMs) to solve complex mathematical engineering challenges in wireless communications.
- Designed and implemented advanced robotic perception systems, integrating deep learning techniques for robust dense scene reconstruction.
Apr. 2024 - Jan. 2025
SLAM Algorithm Engineer
Gausium Robotics (alias "Gaussian Robotics")
- Led a team in engineering a high-performance hierarchical visual localization system for large-scale environments using compact neural networks.
- Directed the integration of real-time map update modules and spearheaded the development of a novel indoor localization system that combines learning-based methods with traditional signal processing.
Mar. 2022 - Feb. 2024
Research Assistant
Singapore University of Technology and Design (SUTD)
Supervisor: Prof. Yuen Chau
- Developed a coplanar direct visual-inertial odometry system that overcomes 2D feature matching inaccuracies, outperforming conventional planar-constrained methods.
Aug. 2021 - Feb. 2022
Research Intern
Microsoft Research Asia (MSRA)
Supervisors: Dr. Yang Liu & Dr. Yizhong Zhang
- Engineered a multi-sensor reconstruction system that integrates mobile camera and IMU data to generate high-fidelity vectorized maps of large-scale supermarkets, enhancing indoor localization and navigation.
Sep. 2020 - Mar. 2021
Research Intern
MEGVII
Supervisor: Dr. Yijia He
- Researched geometric feature extraction in visual SLAM systems and developed a robust, tightly-coupled monocular Visual-Inertial Odometry (VIO) system that leverages heterogeneous features to generate semi-dense 3D scene meshes in real time.
Feb. 2019 - Mar. 2020
Research Interests
-
Large Language Models
Multi-agent orchestration, tool-use & reasoning.
-
Wireless Engineering
LLMassisted modelling & optimisation for 6G.
-
Embodied AI & SLAM
Neural-field SLAM & language-conditioned control.
-
LLM-powered Engineering Automation
Auto-design loops & scientific discovery agents.
Selected Publications
Citation Metrics
Onboard Terrain Classification via Stacked Intelligent Metasurface-Diffractive Deep Neural Networks from SAR Level-0 Raw Data
Mengbing Liu, Xin Li, Jiancheng An, Chau Yuen
ICLR ML4RS Workshop, 2025
@article{liu2025onboard,
title={Onboard Terrain Classification via Stacked Intelligent Metasurface-Diffractive Deep Neural Networks from SAR Level-0 Raw Data},
author={Liu, Mengbing and Li, Xin and An, Jiancheng and Yuen, Chau},
journal={ICLR ML4RS Workshop},
year={2025}
}
TransPathNet: A Novel Two-Stage Framework for Indoor Radio Map Prediction
Xin Li, Ran Liu, Saihua Xu, Sirajudeen Gulam Razul, Chau Yuen
ICASSP, 2025
@inproceedings{li2025transpathnet,
title={TransPathNet: A Novel Two-Stage Framework for Indoor Radio Map Prediction},
author={Li, Xin and Liu, Ran and Xu, Saihua and Razul, Sirajudeen Gulam and Yuen, Chau},
booktitle={Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
year={2025},
month={April}
}
Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry
Xin Li*, Yanyan Li*, Evin Pinar Örnek, Jinlong Lin, Federico Tombari (*equal contribution)
IEEE RA-L, 2020
@article{li2020co,
title={Co-planar parametrization for stereo-SLAM and visual-inertial odometry},
author={Li, Xin and Li, Yanyan and Örnek, Evin Pinar and Lin, Jinlong and Tombari, Federico},
journal={IEEE Robotics and Automation Letters},
volume={5},
number={4},
pages={6972--6979},
year={2020},
publisher={IEEE}
}
Leveraging Planar Regularities for Point Line Visual-Inertial Odometry
Xin Li*, Yijia He*, Jinlong Lin, Xiao Liu (*equal contribution)
IROS, 2020
@inproceedings{li2020leveraging,
title={Leveraging Planar Regularities for Point Line Visual-Inertial Odometry},
author={Li, Xin and He, Yijia and Lin, Jinlong and Liu, Xiao},
booktitle={2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year={2020},
pages={10792--10798},
organization={IEEE}
}