Myscarlet

Haojie Pan

I am Haojie. Currently, I am deeply fascinated by and actively working on developing gpt-based autonomous AI agents that interact with the real world. I am a senior research scientist at Kuaishou Technology, leading the KwaiKEG team. Before that, I am an senior research engineer at Alibaba Cloud, developing large scale NLP toolkits on PAI . I got my Mphil. degree from HKUST, supervised by Prof. Yangqiu Song. I received my B.E. degree at ZJU in June 2018, supervised by Prof. Deng Cai. I have worked in Tencent Wechat group, Alibaba DAMO Academy NLP Group and Netease NetEase Fuxi AI Lab.

I work on computational world knowledge, natural language processing and text mining. Find more about my passions and evolving journey with AI and NLP in the blog article "Me and NLP, Seven Years" (2022.02, in Chinese).

Contact

myscarletpan@gmail.com

Pages

LinkedIn, Google Scholar, Github, Zhihu

Publications

* means equal contribution

Papers

  • Haojie Pan, Zepeng Zhai, Hao Yuan, Yaojia Lv, Ruiji Fu, Ming Liu, Zhongyuan Wang, Bing Qin. KwaiAgents: Generalized Information-seeking Agent System with Large Language Models. CoRR. abs/2312.04889. 2023. [paper] [code]
  • Jiaxin Deng, Dong Shen, Haojie Pan, Xiangyu Wu, Ximan Liu, Gaofeng Meng, Fan Yang, Tingting Gao, Ruiji Fu, Zhongyuan Wang. A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset. ICMR. 2023. (CCF-B) [paper] (Best Paper Candidate)
  • Haojie Pan, Zepeng Zhai, Yuzhou Zhang, Ruiji Fu, Ming Liu, Yangqiu Song, Zhongyuan Wang and Bing Qin. Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia. CoRR. abs/2211.00732. 2022. [paper] [code]
  • Hongming Zhang*, Xin Liu*, Haojie Pan*, Haowen Ke, Jiefu Ou, Tianqing Fang, and Yangqiu Song. ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities. Artificial Intelligence(AI). 2022. (CCF-A) [paper] [code]
  • Haojie Pan*, Chengyu Wang*, Minghui Qiu, Yichang Zhang, Yaliang Li, Jun Huang. Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains. ACL. 2021. (CCF-A) [paper] [code]
  • Haojie Pan, Cen Chen, Chengyu Wang, Minghui Qiu, Liu Yang, Feng Ji and Jun Huang. Learning to Expand: Reinforced Response Expansion for Information-seeking Conversations. CIKM. 2021. (CCF-B) [paper]
  • Chengyu Wang*, Haojie Pan*, Yuan Liu, Kehan Chen, Minghui Qiu, Wei Zhou, Jun Huang, Haiqing Chen, Wei Lin, Deng Cai. MeLL: Large-scale Extensible User Intent Classification for Dialogue Systems with Meta Lifelong Learning. KDD. 2021. (CCF-A) [paper] [code]
  • Chengyu Wang, Haojie Pan, Minghui Qiu, Jun Huang, Fei Yang, Yin Zhang. Meta Distant Transfer Learning for Pre-trained Language Models. EMNLP. 2021. (CCF-B) [paper]
  • Tianqing Fang, Haojie Pan, Hongming Zhang, Yangqiu Song, Kun Xu, Dong Yu. Do Boat and Ocean Suggest Beach? Dialogue Summarization with External Knowledge. AKBC. 2021. [paper] [code]
  • Wenyi Xiao, Huan Zhao, Haojie Pan, Yangqiu Song, Vincent W. Zheng, Qiang Yang. Social explorative attention based recommendation for content distribution platforms. Data Mining and Knowledge Discovery(DMKD). 2021. (CCF-B) [paper] [code]
  • Minghui Qiu, Peng Li*, Chengyu Wang*, Haojie Pan*, Ang Wang, Xianyan Jia, Le Jiang, Yaliang Li, Jun Huang, Jun Yang, Lin Wang, Deng Cai, Wei Lin. EasyTransfer: A Simple and Scalable Deep Transfer Learning Platform for NLP Applications. CIKM. 2021. (CCF-B) [paper] [code]
  • Haojie Pan, Rongqin Yang, Xin Zhou, Rui Wang, Deng Cai, Xiaozhong Liu. Large Scale Abstractive Multi-Review Summarization (LSARS) via Aspect Alignment. SIGIR. 2020. (CCF-A) [paper] [data]
  • Hongming Zhang*, Xin Liu*, Haojie Pan*, Yangqiu Song, and Cane Wing-Ki Leung. ASER: A Large-scale Eventuality Knowledge Graph. WWW. 2020. (CCF-A) [paper] [code]
  • Xin Liu, Haojie Pan, Mutian He, Yangqiu Song, Xin Jiang, Neural Subgraph Isomorphism Counting. KDD. 2020 (CCF-A) [paper] [code]
  • Zhou Zhao*, Haojie Pan*, Changjie Fan, Yan Liu, Linlin Li, Min Yang and Deng Cai. Abstractive Meeting Summarization via Hierarchical Adaptive Segmental Network Learning. WWW. 2019. (CCF-A) [paper] [code]
  • Wenyi Xiao, Huan Zhao, Haojie Pan, Yangqiu Song, Vincent W. Zheng, Qiang Yang. Beyond Personalization - Social Content Recommendation for Creator Equality and Consumer Satisfaction. KDD. 2019. (CCF-A) [paper] [code]
  • Haojie Pan, Junpei Zhou, Zhou Zhao, Yan Liu, Deng Cai and Min Yang. Dial2desc: end-to-end dialogue description generation. CoRR. abs/1811.00185. 2018. [paper]

Patents

  • Hongming Zhang*, Xin Liu*, Haojie Pan* and Yangqiu Song. Knowledge graph (kg) construction method for eventuality prediction and eventuality prediction method. US Patent App. 17/613,940. 2022