4 Engineering Drive 3, Singapore 117583
Email: kaixin.wang@u.nus.edu Homepage: https://policy.fit

National University of Singapore Singapore
Doctoral Candidate in Data Science Aug 2018 - present
Advisors: Jiashi Feng, Bryan Hooi, Xinchao Wang
Nanjing University Nanjing, China
Bachelor in Information Management and Information System Sep 2014 - Jun 2018
Research Works

*Equal contribution
Peer-Reviewed Conference Publications
[6] The Geometry of Robust Value Functions
Kaixin Wang, Navdeep Kumar, Kuangqi Zhou, Bryan Hooi, Jiashi Feng, Shie Mannor
in International Conference on Machine Learning (ICML), 2022.
[5] Understanding and Resolving Performance Degradation in Graph Convolutional Networks
Kuangqi Zhou*, Yanfei Dong*, Kaixin Wang, Wee Sun Lee, Bryan Hooi, Huan Xu, Jiashi Feng
in Conference on Information and Knowledge Management (CIKM), 2021. (oral)
[4] Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
Kaixin Wang*, Kuangqi Zhou*, Qixin Zhang, Jie Shao, Bryan Hooi, Jiashi Feng
in International Conference on Machine Learning (ICML), 2021.
[3] Improving Generalization in Reinforcement Learning with Mixture Regularization
Kaixin Wang, Bingyi Kang, Jie Shao, Jiashi Feng
in Neural Information Processing Systems (NeurIPS), 2020.
[2] Neural Epitome Search for Architecture-Agnostic Network Compression
Daquan Zhou, Xiaojie Jin, Qibin Hou, Kaixin Wang, Jianchao Yang, Jiashi Feng
in International Conference on Learning Representations (ICLR), 2020.
[1] PANet: Few-shot Image Semantic Segmentation with Prototype Alignment
Kaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou, Jiashi Feng
in International Conference on Computer Vision (ICCV), 2019. (oral)
Non-archival / Workshop Papers
[3] Efficient Policy Iteration for Robust Markov Decision Processes via Regularization
Navdeep Kumar, Kfir Levy, Kaixin Wang, Shie Mannor
Technical report, 2022.
[2] Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
Kuangqi Zhou, Kaixin Wang, Jiashi Feng, Jian Tang, Tingyang Xu, Xinchao Wang
Technical report, 2022.
[1] Policy Gradient for Reinforcement Learning with General Utilities
Navdeep Kumar, Kaixin Wang, Kfir Levy, Shie Mannor
in The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022.
Academic Experience

Technion - Israel Institute of Technology Haifa, Israel
Visiting PhD Student (Supervisor: Prof. Shie Mannor) Sep 2021 - Feb 2022
University of Western Australia Perth, Australia
Research Intern (Supervisor: Prof. Mark Reynolds) Jul 2017 - Aug 2017
Zhejiang University Hangzhou, China
Exchange Student Mar 2017 - Jun 2017
Working Experience

Intelligent Creation Research, TikTok Singapore
Intern, mentored by Jiashi Feng Apr 2022 - July 2022
Sea AI Lab Singapore
Intern, mentored by Bingyi Kang Mar 2021 - Jun 2021
ByteDance AI Lab Singapore
Intern, mentored by Jie Shao Apr 2020 - Feb 2021
Horizon Robotics Nanjing, China
Intern, mentored by Guixing Chen Nov 2017 - Mar 2018
Awards & Scholarships

PREMIA Best Student Paper, Silver Award 2021
NGS Scholarship 2018 - 2022

Conference Reviewer
  • ICML: 2021 (top 10%), 2022
  • NeurIPS: 2021
  • ICLR: 2022, 2023
Journal Reviewer
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • IEEE Transactions on Multimedia
  • IEEE Transactions on Image Processing
  • Machine Vision and Applications
  • Transactions on Machine Learning Research
  • ICML: 2020, 2021
  • NeurIPS: 2020
  • ICLR: 2020, 2021
Teaching Assistant
  • NUS EE5934/6934: Deep Learning
  • IDS PhD-Teach-PhD workshop 2019