In 2022, I earned my master’s degree from Hebei University of Science and Technology. From 2019 to 2022, I was a Visiting Postgraduate Student in the THUIAR Group at Tsinghua University, conducting research under the supervision of Professor Hua Xu. My research interests encompass large language models, reinforcement learning, multimodal information processing, and information extraction, among others.

You can find my published work and citation information on Google Scholar and Citation Map.

Should you have questions about my work or wish to connect, please feel free to contact me via email.

Email: zhaok7878@gmail.com, zhaokang5@xiaomi.com

🔥 News

• 2024.06: 🎉 SubLLM has been accepted by ECAI2024.
• 2023.06: 📤 UniMC has been posted on arXiv[cs.CL].
• 2023.03: Began participating in the MiLM model series, involving infrastructure construction, pre-training data processing, and foundation model training & evaluation.
• 2022.06: I joined XiaoMi as an algorithm engineer.
• 2022.03: 🎉 GAR-Net has been accepted by Knowledge-Based Systems.
• 2022.03: 🎉 CRL has been accepted by ACL2022.
• 2021.09: 🎉 TEXTOIR has been accepted by ACL2021(demo paper).
• 2021.05: 🎉 RIFRE has been accepted by Knowledge-Based Systems.

📑 Publications

ECAI2024

Subllm: A novel efficient architecture with token sequence subsampling for llm[C]

Quandong Wang, Yuxuan Yuan, Xiaoyu Yang, Ruike Zhang, Kang Zhao, Wei Liu, Jian Luan, Daniel Povey, Bin Wang

Arxiv , GitHub

Unimc: A unified framework for long-term memory conversation via relevance representation learning

Kang Zhao, Wei Liu, Jian Luan, Minglei Gao, Li Qian, Hanlin Teng, Bin Wang

Arxiv

KBS2022

GAR-Net: A graph attention reasoning network for conversation understanding[J]

Hua Xu*, Ziqi Yuan*, Kang Zhao*, Yunfeng Xu, Jiyun Zou, Kai Gao (Equal First author)

GitHub

ACL2022

Consistent representation learning for continual relation extraction[C]

Kang Zhao, Hua Xu, Jiangong Yang, Kai Gao

Arxiv , GitHub

ACL2021

TEXTOIR: An integrated and visualized platform for text open intent recognition[C]

Hanlei Zhang, Xiaoteng Li, Hua Xu, Panpan Zhang, Kang Zhao, Kai Gao

Arxiv , GitHub

KBS2021

Representation iterative fusion based on heterogeneous graph neural network for joint entity and relation extraction[J]

Kang Zhao, Hua Xu, Yue Cheng, Xiaoteng Li, Kai Gao

GitHub , PDF

🧑‍🏫 Conference & Journal Reviewer Services

• Conferences: ACL, EMNLP, AAAI
• Journals: KBS, ESWA

📖 Educations

• 2019.03 - 2022.05, Visting Postgraduate Student, Tsinghua University, Beijing.
• 2019.09 - 2022.06, Master, Hebei University of Science and Technology, Shijiazhuang.
• 2014.09 - 2018.06, Undergraduate, Hebei University of Engineering, Handan.

💻 Work Experience

• 2022.06 - Now, XiaoMi, Beijing.