Summary

Hello, I’m He Wang (王赫). Since 2024, I have been working as a Research Associate at the ICTP-AP, University of Chinese Academy of Sciences (UCAS), exploring the fascinating world of gravitational wave physics. My academic voyage took root at Beijing Normal University, where I was honored with a Ph.D. in 2020.

Embarking on the academic path is both challenging and fulfilling. I am firmly set on this path, ready to forge ahead with steadfast determination, undeterred by any obstacles or setbacks that might come my way. The joy I find in disseminating the knowledge I have gathered so far is immeasurable, particularly in the realms of Gravitational-Wave (GW) data analysis and Machine Learning (ML) technology.

Through my blog, I hope to foster a vibrant space of learning and curiosity, offering insights in both Chinese and English. I am in the process of cultivating a rich repository of knowledge, with the hope that, in time, I will carve out a viewpoint that is distinctly my own.

Guided by the profound words of S. Chandrasekhar, who noted, “I have the urge to present my point of view ab initio, in a coherent account with order, form, and structure,” I am navigating the intricate corridors of the academic world. My aim is to remain resilient, sharing my journey and insights, unfazed by potential hurdles or hindrances.

I envision this platform as a living testament to my commitment and evolution in the academic domain, showcasing a relentless pursuit of knowledge, undaunted by any challenges that lie ahead.

My scientific work has followed a certain pattern motivated, principally, by a quest after perspectives.
我的科学研究工作遵循了某种模式,它的动因主要是寻找观点

How to comment

With use of the hypothes.is extension (right-sided), you can highlight, annote any comments and discuss these notes inline at any pages.

Please Feel Free to Let Me Know and Share it There.

Experience

 
 
 
 
 
University of Chinese Academy of Sciences (UCAS)
Research Associate
July 2024 – Present Beijing

Engaged in advanced research on AI-based data analysis methodologies tailored for both ground-based and space-based gravitational wave detection.

Specific projects include:

  • Developing AI-driven software packages for enhanced data processing in ground-based gravitational wave detection.
  • Formulating global fitting algorithms for parameter estimation in space-based gravitational wave detection, utilizing AI techniques.
  • Leveraging large language models (LLMs) to optimize algorithms for gravitational wave data analysis, enhancing computational efficiency and analytical accuracy.
 
 
 
 
 

Focused on the integration of AI and machine learning technologies for noise reduction and signal detection in gravitational wave research.

Key contributions include:

  • Utilizing pre-trained models from natural language processing to expedite signal detection and enhance noise suppression in ground-based gravitational wave detection.
  • Developing fast parameter estimation algorithms based on normalizing flow models for space-based gravitational wave projects.
 
 
 
 
 
Peng Cheng Lab (PCL)
Visiting Scholar
December 2021 – July 2022 ShenZhen
Developed a transformer-based language model leveraging the Bidirectional Encoder Representations from Transformers (BERT) architecture, enhanced with distributed computing capabilities using the Ray framework.
 
 
 
 
 

Researched and developed methodologies for the rapid detection and inference of gravitational wave signals using deep learning approaches, focusing on:

  • Employing normalizing flow models for efficient and accurate gravitational wave signal inference.

Teaching

Gravitational Wave Data Exploration: A Practical Training in Programming and Analysis
《引力波数据探索:编程与分析实战训练营》
Machine learning and GW data analysis
《深度学习之 PyTorch 实战》
《Python 数据可视化与实战》
《大数据预处理》
《Python 程序设计》
《Python 数据挖掘工具》

Recent Publication

(2024). Rapid Parameter Estimation for Merging Massive Black Hole Binaries Using Continuous Normalizing Flows. arXiv:2407.07125 [gr-qc].

DOI

(2024). The Detection, Extraction and Parameter Estimation of Extreme-Mass-Ratio Inspirals with Deep Learning. arXiv.2311.18640.

PDF DOI

(2024). Search for exotic gravitational wave signals beyond general relativity using deep learning. arXiv:2410.20129 [gr-qc].

PDF DOI

Github Contribution

iphysresearch's Github chart

Herb’s github stats

License

本站点内容系本作者原创,如有任何知识产权、版权问题或理论错误,还请指正。 转载请注明原作者及出处,谢谢配合。

The content on this site is original work by the author. If you identify any intellectual property, copyright issues, or theoretical errors, please feel free to point them out. For reprints, please acknowledge the original author and source. Thank you for your cooperation.