My name is Jinxiang Xie (pronounced “JIN-shee-ahng SHEE-eh”). I am a graduate student at Nanjing University. I earned my Bachelor’s degree in Information and Computing Science from Beijing Jiaotong University. I was a research intern at Microsoft, where I have the privilege of working with Principal Researcher Justin Ding. Prior to this, I gained valuable research experience at Peking University under the guidance of Prof. Xiaojun Wan.

My research focuses on leveraging Large Language Models to address complex problems.

Feel free to reach out if you’d like to discuss research or explore potential collaboration!

     AI Researcher
    Research focus on LLMs and NLP
Internships at top institutions
Publications at AAAI, ACL

  

Content Creator

Technical blogs with 500K+ views
Active on Xiaohongshu
Articles about Tech & Humanities

     Life Explorer
    Visited 9 countries worldwide
Traveled to 32 provinces in China
Rich experience in social work

  

Publications

Under Review

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics

Jinxiang Xie, Zihao Li, Wei He, Rui Ding, Shi Han, Dongmei Zhang

Under Review

AAAI 2025

DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models

Jinxiang Xie, Yilin Li, Xunjian Yin, Xiaojun Wan

In The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025)

ArXiv Code

Qiyang Chen, Yuezhi Wang, Jinxiang Xie, Guozheng Li, Chi Harold Liu. $M^3$ Trader: Multimodal Macro–Micro Inference with LLM-Guided Reinforcement Learning for Quantitative Trading. Under Review.

Educations

2025.09 - Present: Master of Science at Kuang Yaming Honors School, Nanjing University.
2021.09 - 2025.06: Bachelor of Science in Information and Computing Science, Beijing Jiaotong University.

Internships

2024.08 - 2025.08: Research Intern, Data, Knowledge and Intelligence (DKI) Group, Microsoft.
2023.11 - 2024.08: Research Intern, Wangxuan Institute of Computer Technology, Peking University.
2023.05 - 2023.07: Summer Workshop Student, School of Computer, National University of Singapore.

Blogs

November, 2025

Claude Code Skills and Subagents in Practice

Two production-grade systems: a paywall-crossing paper harvester and a self-iterating AI Scientist, showing how Skills + Subagents scale LLM workflows.

中文版 English

June, 2025

The Limits of My Language Mean the Limits of My World

Drawing on Wittgenstein's philosophy, a recent paper argues that our existing language might be the fundamental bottleneck.

中文版 English

January, 2025

Beyond the Future of AI: The Dreams and Deceptions of Cryptocurrency

My vision of the future: from Bitcoin to an AGI-driven decentralized society. We must design a more sophisticated trust mechanism than blockchain to install “guardrails” for AI.

中文版 English

November, 2024

LexiMind: An Open-Source LLM-Powered Vocabulary Builder

LexiMind is an AI-powered vocabulary builder that integrates LLM-based translation with smart word retention.

Introduction Project

November, 2023

LLMs: Cutting-Edge Technology and Future Applications

My notes from a presentation on LLMs at the Gaoling School of Artificial Intelligence, Renmin University of China.

中文版

August, 2023

Prompt Engineering: How to Better Ask LLMs

Introduce a number of methods for optimizing the output of large language models and reducing the probability of irrelevant or incorrect responses.

中文版