CV

Education

• B.S. in Computer Science, Beijing Forestry University, Beijing, China, 2014 - 2018
• M.S. in Computer Science, Beijing Institute of Technology, Beijing, China, 2018-2020
• Ph.D in Computer Science, Beijing Institute of Technology, Beijing, China, 2020-

Academic experience

• Winter 2021: Research Assistant
  • Reinforcement Learning
  • Beijing Institute of Technology
  • Duties included: Monitoring and presenting the ongoing research
  • Supervisor: Dr. Xin Li

Work experience

• 2023.04-2024.01: research intern
  • Institute for Intelligent Computing, Alibaba Group, China
  • Duties: RLHF in image generation
  • Technologies: diffusion models, ppo, monte-carlo gradient estimation
• 2017-2018: NLP research intern
  • Lavector (startup), China
  • Duties: Chatbot development
  • Technologies: pytorch, seq2seq modeling, neo4j.

Skills

• Hard Skills
  • SO: Linux, Windows
  • Programming: Python, Lua, Matlab, and C++
  • Database: MySQL and MongoDB
  • Versioning: Git, Github
  • Misc: LaTeX
• Soft Skills
  • Analytical thinking
  • Scientific method
  • Problem solver
  • International collaboration
  • Small team management
• Advanced Skills
  • statistical modeling, experimental research and design, data analysis, game environment modeling

Publications

Enhancing Identity Preservation in Portrait Generation via Reward Optimization

none

Towards Control-Centric Representations in Reinforcement Learning from Images

Liu C, Zang H, Li X, et al. Towards Control-Centric Representations in Reinforcement Learning from Images[J]. arXiv preprint arXiv:2310.16655, 2023

Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning

Hongyu Zang, Xin Li, Leiji Zhang, Yang Liu, Baigui Sun, Riashat Islam, Remi Tachet des Combes, Romain Laroche: Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning. NeurIPS 2023

Principled Offline RL in the Presence of Rich Exogenous Information

Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Rajiv Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford: Principled Offline RL in the Presence of Rich Exogenous Information. ICML 2023: 14390-14421

Representation Learning in Deep RL via Discrete Information Bottleneck

Riashat Islam, Hongyu Zang, Manan Tomar, Aniket Didolkar, Md Mofijul Islam, Samin Yeasar Arnob, Tariq Iqbal, Xin Li, Anirudh Goyal, Nicolas Heess, Alex Lamb: Representation Learning in Deep RL via Discrete Information Bottleneck. AISTATS 2023: 8699-8722

Behavior Prior Representation learning for Offline Reinforcement Learning

Hongyu Zang, Xin Li, Jie Yu, Chen Liu, Riashat Islam, Remi Tachet des Combes, Romain Laroche: Behavior Prior Representation learning for Offline Reinforcement Learning. ICLR 2023

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford: Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information. NeurIPS 2022 Offline RL Workshop.

WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series

Fuhao Yang, Xin Li, Min Wang, Hongyu Zang, Wei Pang, Mingzhong Wang: WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series. AAAI 2023: 10754-10761

Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning

Riashat Islam, Hongyu Zang, Anirudh Goyal, Alex Lamb, Kenji Kawaguchi, Xin Li, Romain Laroche, Yoshua Bengio, Remi Tachet des Combes: Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning. NeurIPS 2022.

CHA: Categorical Hierarchy-based Attention for Next POI Recommendation

Hongyu Zang, Dongcheng Han, Xin Li, Zhifeng Wan, Mingzhong Wang: CHA: Categorical Hierarchy-based Attention for Next POI Recommendation. ACM Trans. Inf. Syst. 40(1): 7:1-7:22 (2022)

SimSR: Simple Distance-Based State Representations for Deep Reinforcement Learning

Hongyu Zang, Xin Li, Mingzhong Wang: SimSR: Simple Distance-Based State Representations for Deep Reinforcement Learning. AAAI 2022: 8997-9005

On improving knowledge graph facilitated simple question answering system

Xin Li, Hongyu Zang, Xiaoyun Yu, Hao Wu, Zijian Zhang, Jiamou Liu, Mingzhong Wang: On improving knowledge graph facilitated simple question answering system. Neural Comput. Appl. 33(16): 10587-10596 (2021)

Universal Value Iteration Networks: When Spatially-Invariant Is Not Universal

Li Zhang, Xin Li, Sen Chen, Hongyu Zang, Jie Huang, Mingzhong Wang: Universal Value Iteration Networks: When Spatially-Invariant Is Not Universal. AAAI 2020: 6778-6785

A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment

Rui Ye, Xin Li, Yujie Fang, Hongyu Zang, Mingzhong Wang: A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment. IJCAI 2019: 4135-4141

Service & Activities

• Reviewer for Conferences: AAAI-22,23,24 NeurIPS-23 ICLR-24 ICML-24

• Reviewer for Journal: IEEE Transactions on Services Computing

• ACM membership