Haipeng Chen

Email: hpchen@seas.harvard.edu; haipengkeepon@gmail.com

I am a CRCS postdoctoral fellow at Harvard University from July 2020, where I work with Professor Milind Tambe and Professor Hima Lakkaraju. Previously I did my first postdoc in the Department of Computer Science, Dartmouth College from July 2018, where I worked with Professor V.S. Subrahmanian. I obtained my PhD from Interdisciplinary Graduate School (IGS), Nanyang Technological University (NTU) in 2018, where I was advised by Professor Bo An. I got my B.S. in Physics from University of Science and Technology of China (USTC) in 2013.

I study AI techniques that help understand the world and benefit the society. In particular, I am interested in reinforcement learning, learning on graph/network-structured data, generative models, and predictive decision making. I work on domains such as public health, cybersecurity, transportation, and online/real-world social networks.



  • I am co-organizing the 3rd Workshop on Artificial Intelligence for Social Good @IJCAI2021, on August 21.
  • May, 2021 - I am co-organizing the Synthetic Data Generation: Quality, Privacy, Bias workshop @ICLR2021, on May 7th.
  • May, 2021 - Two papers accepted by UAI'2021!
  • May, 2021 - Our paper, 'Active Screening for Recurrent Diseases: A Reinforcement Learning Approach' is awarded the best paper nomination by AAMAS'2021!
  • March, 2021 - Our workshop proposal, 'International Workshop on Artificial Intelligence for Social Good (AI4SG)' is accepted by IJCAI'2021!
  • December, 2020 - Our paper, 'Active Screening for Recurrent Diseases: A Reinforcement Learning Approach' is accepted by AAMAS'2021!
  • December, 2020 - Our workshop proposal, 'Synthetic Data Generation: Quality, Privacy, Bias' is accepted by ICLR'2021 workshops!
  • December, 2020 - Invited to serve as Senior PC of IJCAI'2021!
  • December, 2020 - Our paper, 'EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation' is accepted by AAAI'2021!
Load More
  • September, 2020 - Organzing Harvard CRCS workshop on Using AI for Social Good!
  • August, 2020 - Our team AMI (Bo An, Haipeng Chen, Xu He, Rundong Wang, and Youzhi Zhang; alphabetically ordered) made it to the finalist (top 25 out of 1000+ teams) in the KDD'20 reinforcement learning competition track!
  • August, 2020 - Our paper, "Using Word Embeddings to Deter Intellectual Property Theft Through Automated Generation of Fake Documents" is accepted by ACM Transactions on Management Information Systems!
  • July, 2020 - Started postdoc at Harvard University!
  • May, 2020 - Our paper, "Learning Behaviors with Uncertain Human Feedback" got accepted to UAI'20. Congrats Xu on his first paper -- well deserved!
  • March, 2020 - Invited to serve as a reviewer of Neurips'20.
  • Feb, 2020 - Invited talk at CS department, University of Illinois at Chicago.
  • December 16, 2019 - Attending Matariki Cybersecurity Workshop.
  • December 8-14, 2019 - Attending Neurips'19 in Vancouver, Canada!
  • November, 2019 - Our paper, "Disclose or Exploit? A Game Theoretic Approach Towards Strategic Decision Making in Cyber Warfare" has been accepted to IEEE Systems Journal.
  • November, 2019 - Our paper, "PIE: A Data-Driven Payoff Inference Engine for Strategic Security Applications" has been accepted to IEEE Transactions on Computational Social Systems.
  • August, 2019 - Our IJCAI 2019 demo paper, "VEST: A System for Vulnerability Exploit Scoring & Timing" has been awarded IJCAI'19 Demonstration Innovation Award runner-up. Congrats to all co-authors!
  • August, 2019 - Two papers accepted to ICDM 2019, including one regular paper which integrates contextual bandit with TD learning to handle the joint pricing and dispatch problem in ride-hailing platform, a work done when I was an intern at Didi; and a short paper jointly done with George Mason University, which is a follow-up of our KDD paper .
  • August, 2019 - Attending KDD'19 in Anchorage, Alaska!
  • May, 2019 - Attending ISTS VeChain BlockChain Technology Workshop.
  • May, 2019 - Three papers accepted to IJCAI 2019, including two papers on GAN-based tabular data generation with function-preservation and dynamic ETC control with multi-agent deep reinforcement learning accepted as main conference papers, and one demo paper demonstrating a system for vulnerability exploit timing and severity scoring prediction!
  • April, 2019 - Our paper, Using Twitter to Predict when Vulnerabilities will be Exploited, is accepted to KDD 2019 as poster presentation!
  • April, 2019 - Our paper, DCL-AIM: Decentralized Coordination Learning of Autonomous Intersection Management for Connected and Automated Vehicles has been accepted to Transportation Research, Part C, Emerging Methodologies!


C=Conference, J=Journal, D=Demo, W=Workshop, A=Arxiv, P=Patent







Awards & Certifications

Professional Services

Excellent Reading Materials and Courses