Weisen JIANG

PhD Candidate
waysonkong@gmail.com
Department of Computer Science and Engineering
Hong Kong University of Science and Technology (HKUST)

Research Interest: large language models, meta learning, prompt learning

Education

• South China University of Technology, Bachelor of Engineering. 2008 - 2012.

• University of Chinese Academy of Sciences, Master of Science (advisor: Prof. Hai-Tao Fang). 2012 - 2015.

• Hong Kong University of Science and Technology, pursing PhD (advisors: Prof. James Kwok and Prof. Yu Zhang). 2020 - now.

Work

• Meituan, Engineer. 2015 - 2017.
  (i) Designed algorithms for recommendation systems (ii) Created the hotel anti-cheating system

• Tencent, Senior Engineer (T9). 2017 - 2019.
  (i) Designed algorithms for recommendation systems (ii) Created the data-mining platform

Publications

(♠ equal contribution)

Preprints

1. Forward-Backward Reasoning in Large Language Models for Mathematical Verification
      Weisen Jiang, Han Shi, Longhui Yu, Zhengying Liu, Yu Zhang, Zhenguo Li, James Kwok
      Preprint arXiv:2308.07758, 2024
      arXiv | project

2. Dual-Balancing for Multi-Task Learning
      Baijiong Lin, Weisen Jiang, Feiyang Ye, Yu Zhang, Pengguang Chen, Ying-Cong Chen, Shu Liu, James Kwok
      Preprint arXiv:2308.12029, 2023
      arXiv

3. Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation
      Yulong Zhang, Shuhao Chen, Weisen Jiang, Yu Zhang, Jiangang Lu, James Kwok
      Preprint arXiv:2309.14360, 2023
      arXiv

4. BYOM: Building Your Own Multi-Task Model For Free
      Weisen Jiang^♠, Baijiong Lin^♠, Han Shi, Yu Zhang, Zhenguo Li, James Kwok
      Preprint arXiv:2310.01886, 2024
      arXiv

5. LLaVO: Large Language Models as Visual Cross-Domain Learners
      Shuhao Chen, Yulong Zhang, Weisen Jiang, Jiangang Lu, Yu Zhang
      Preprint arXiv:2401.03253, 2023
      arXiv | project

6. Rendering Graphs for Graph Reasoning in Multimodal Large Language Models
      Yanbin Wei, Shuai Fu, Weisen Jiang, James Kwok, Yu Zhang
      Preprint arXiv:2402.02130, 2024
      arXiv | project

Conferences

1. Identification for Wiener System with Discontinuous Piece-wise Linear Function via Sparse Optimization
       Weisen Jiang, Hai-Tao Fang
      Chinese Control Conference (CCC) 2014
   

2. Identification of Switched Linear Systems via Sparse Optimization
       Weisen Jiang, Hai-Tao Fang
      IFAC Symposium on System Identification 2015
   

3. SEEN: Few-Shot Classification with SElf-ENsemble
       Weisen Jiang, James Kwok, Yu Zhang
      IJCNN 2021, Virtual
   

4. Effective Meta-Regularization by Kernelized Proximal Regularization
       Weisen Jiang, James Kwok, Yu Zhang
      NeurIPS 2021, Virtual
      OpenReview | Code | Poster

5. Subspace Learning for Effective Meta-Learning
       Weisen Jiang, Yu Zhang, James Kwok
      ICML 2022, Baltimore, Maryland, USA
      OpenReview | Code | Poster

6. An Adaptive Policy to Employ Sharpness-Aware Minimization
       Weisen Jiang, Hansi Yang, Yu Zhang, James Kwok
      ICLR 2023, Kigali, Rwanda
      OpenReview |  Code | Poster

7. Effective Structured Prompting by Meta-Learning and Representative Verbalizer
       Weisen Jiang, Yu Zhang, James Kwok
      ICML 2023, Honolulu, Hawaii, USA
      OpenReview |  Code | Poster

8. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
      Longhui Yu^♠, Weisen Jiang^♠, Han Shi, J. Yu, Z. Liu, Yu Zhang, James Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu
      ICLR 2024, Spotlight (acceptance rate 5%)
      OpenReview |  code |  project |  poster

Patents

1. 信息推荐方法、装置、系统及存储介质
      江伟森, 吴德龙, 邱泰生
      腾讯科技有限公司
      发明专利, 授权号: CN110413868B, 2023

2. 一种页面生成方法及装置
      江伟森, 骆顺昌, 吴德龙, 邱泰生
      腾讯科技有限公司
      发明专利, 授权号: CN112307319A, 2021

Awards

• National Scholarship (TOP 2%), twice. Ministry of Education of the People's Republic of China.

• Outstanding Staff with 5 stars (TOP 10%), twice. Tencent.

• Shenzhen 3rd Excellent Science & Technology Academic Paper, 2023

Teaching

• COMP 2012(Object-oriented programming and data structures), Teaching assistant. HKUST.

• COMP 4331(Data mining), Teaching assistant. HKUST.

Software

• W. Jiang (with team). Meituan. Recommendation systems for booking hotels.

• W. Jiang, J. Wang. Meituan. Hotel anti-cheat systems.

• W. Jiang, S. Luo. Tencent. Teppelin platform for data mining.

• W. Jiang (with team). Tencent. Recommendation systems.

Academic Services

• IEEE Transactions on Neural Networks and Learning Systems
• Artificial Intelligence
• International Journal of Data Science and Analytics
• ICML: 2022, 2023, 2024
• NeurIPS: 2022, 2023
• ICLR: 2023, 2024
• CVPR: 2024