Dan Qiao

Dan Qiao

M.Phil student at Soochow University.

Dan Qiao(乔丹)

I am currently a Master’s student enrolled at Soochow University, and I am expected to graduate in July 2025. My academic advisors are Associate Professor Juntao Li and Professor Min Zhang. I also obtained my bachelor’s degree from Soochow University. My research focuses on Natural Language Processing, LLMs’ training and compression and pruning.

  • ✉️ Email: danqiao.jordan@gmail.com

  • GitHub license Github: https://github.com/jordddan

🎓 Education

  • 2018.9.1-2022.6.30: Undergraduate student at Soochow University, majoring in Artificial Intelligence, advised by Juntao Li.
  • 2022.9.1-Till Now: M.Phil student at Soochow University, majoring in Artificial Intelligence, advised by Juntao Li.

🔬 Experience

  • 2024.5-Now: Internship in ByteDance E-Commerce (Training ECOM-LLM)
  • 2023.4-2023.10: Internship in Microsoft Research Asia (LLM Evaluation&Agent)
  • 2022.7-2022.10: Internship for AI Engineer in Alibaba group (Taobao E-commerce, Learning with Label Noise)
  • 2021.7-2021.10: Internship in Byte Dance AI-Lab Speech&Autio (Pretrained Model Inference Engine Development)

📃 Publications

equal contribution is marked by “*”.

  • OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning [Paper][Code]
    Dan Qiao, Yi Su, Pinzheng Wang, Jing Ye, WenJing Xie, Yuechi Zhou, Yuyang Ding, Zecheng Tang, Jikai Wang, Yixin Ji, Yue Wang, Pei Guo, Zechen Sun, Zikang Zhang, Juntao Li Pingfu Chao, Wenliang Chen, Guohong Fu, Guodong Zhou, Qiaoming Zhu, Min Zhang (LLM technical report)

  • SelfMix: Robust Learning against Textual Label Noise with Self-Mixup Training [Paper] [Code]
    Dan Qiao, Chenchen Dai, Yuyang Ding, Juntao Li, Qiang Chen, Wenliang Chen, Min Zhang (Soochow University; Alibaba Group)
    Oral COLING 2022

  • Towards Better Hierarchical Text Classification with Data Generation [Paper] [Code]
    Yue Wang *, Dan Qiao *, Juntao Li, Jinxiong Chang, Qishen Zhang, Zhongyi Liu, Guannan Zhang, Min Zhang (Ant Group;Soochow University)
    In Findings of the Association for Computational Linguistics: ACL 2023

  • GameEval: Evaluating LLMs on Conversational Games [Paper][Code]
    Dan Qiao, Chenfei Wu, Yaobo Liang, Juntao Li, Nan Duan (Microsoft Research; Soochow University)
    arXiv:2308.10032

  • OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch [Paper][Code]
    arXiv:2309.10706

🕹️ Project

  • Visual-ChatGPT: AIGC, Talking, Drawing and Editing with Visual Foundation Models.
  • OpenBA: OpenBA: An Open-Sourced 15B Bilingual Asymmetric Seq2Seq Model Pre-trained from Scratch.
  • Pruning-LLMs: The framework to prune LLMs to any size and any config.
  • Megatron-Cookbook: Codebase for pre-training, compressing, extending, and distilling LLMs with Megatron-LM.

🏆 Awards

  • 🥇International Collegiate Programming Contest (ACM-ICPC) 2021 Xi’an Invitational Gold Medal
  • 🥈China Collegiate Programming Contest (CCPC) 2020 Mianyang Station Silver Award
  • 🥈International Collegiate Programming Contest (ACM-ICPC) 2019 Yinchuan Regional Competition Silver Medal