🙋 Zhan Shaoxiong (詹少雄)
📧 zhansx24@mails.tsinghua.edu.cn / jasaxion@gmail.com
📍 Shenzhen, China · Tsinghua SIGS
I am a master's student at the Knowledge Engineering Lab of Tsinghua Shenzhen International Graduate School, advised by Prof. Haitao Zheng. My research focuses on natural language processing (NLP), information retrieval (IR), and large language models (LLMs), with particular interest in dense retrieval, semantic augmentation, and retrieval-augmented generation. I received a B.Eng. degree in Computer Science from Huazhong Agricultural University.
🔥 News
📝 Publications
(AAAI, 2026) · arXiv:2508.05592
(AAAI, 2026)(co-author) · padding
(Information Science, 2025)(co-author) · arXiv:2504.14620
(ECAI 2025) · arXiv:2508.17858
(NLPCC 2025)(co-author) · arXiv:2409.15763
(IEEE Transactions on Knowledge and Data Engineering, TKDE 2025)(co-author) · DOI: 10.1109/TKDE.2025.3543203
🎖 Honors and Awards
💻 Internships
- Focused on post-training optimization of large language models for mathematical reasoning.
- Designed RL-based hard-problem synthesis strategies and built a large-scale “MathSmith” dataset to improve reasoning robustness.
- Converted research into a first-author publication, integrating data synthesis and fine-tuning experiments.
- Developed enterprise-grade Retrieval-Augmented Generation (RAG) pipelines with LangChain and embedding fine-tuning.
- Implemented OCR + multimodal fusion for document understanding and contributed to system design and delivery.
- Built an AST-based PyTorch→MindSpore conversion module, enhancing framework interoperability and automation.
- Strengthened understanding of AI framework architecture and open-source collaboration workflows.
🎨 Miscellaneous
👋I'm a hands-on tech enthusiast who enjoys tinkering with gadgets and experimenting with new ideas💡—even if things break along the way. Outside of work, you'll find me playing badminton🏸, swimming🏊♀️, or dancing💃 (hiphop/kpop). Always happy to connect—feel free to add me on WeChat: Jasaxion_Taurus0405 🤝