# Wuganjing Song

I'm an MPhil student at the Hong Kong University of Science and Technology, advised by Yangqiu Song. Before this I completed my MSc at HKUST and my BSc at Northeastern University in Shenyang. Along the way I interned at Huawei and at Tencent, where I worked on post-training and retrieval-augmented generation for large language models.

## Publications & Projects

- [Multi-turn Training with Basic Human Feedback Helps Little on LLM Reasoning](https://arxiv.org/abs/2510.21339) — Qiang Liu, Wuganjing Song, Zhenzhou Lin, Feifan Chen, Qiaolong Cai, Chen Li, Yongduo Sui, arXiv preprint, 2025
- [System Report for CCL25-Eval Task 12: Surpassing LLMs with a Simple Pipeline for Mandarin Spoken Entity-Relation Extraction](https://aclanthology.org/2025.ccl-2.56/) — Wuganjing Song, China National Conference on Computational Linguistics (CCL25-Eval), 2025
- [Heterogeneous FL via Active-Passive Collaboration](https://link.springer.com/chapter/10.1007/978-981-95-4149-2_19) — Jianzhe Zhao, Wuganjing Song, Li Zhang, Xingwei Wang, Guibing Guo, Zhelin Fan, Database Systems for Advanced Applications (DASFAA), 2025

## Machine-readable

- Full structured content: https://songwgj.me/api/content.json

## Contact

- Email: songwgj [at] outlook [dot] com
- GitHub: https://github.com/Swgj