About me

I am currently a Senior Researcher at Microsoft Research Singapore Lab. Previously, I was a Research Scientist at Salesforce AI Research where I worked on time series foundation models. I obtained PhD in Computer Science at School of Computing (SoC), National University of Singapore (NUS), advised by Prof. Xiaokui Xiao. During my PhD, I also closely collaborated with Prof. Bryan Hooi, Prof. Kenji Kawaguchi, and Prof. Muhao Chen. My current research focuses are and time series foundation models and time series language models.

Prior to my PhD study, I received my bachelor degree in Computer Science from Sichuan University, China.

Publications

* indicates the equal contribution.

• Moirai 2.0: When Less Is More for Time Series Forecasting.
  Chenghao Liu*, Taha Aksu*, Juncheng Liu*, Xu Liu*, Hanshu Yan, Quang Pham, Silvio Savarese, Doyen Sahoo, Caiming Xiong, Junnan Li.
  Technical Report
  [Model]

• Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
  Xu Liu, Juncheng Liu, Gerald Woo, Taha Aksu, Yuxuan Liang, Roger Zimmermann, Chenghao Liu, Silvio Savarese, Caiming Xiong, Doyen Sahoo.
  International Conference on Machine Learning (ICML) 2025.
  [Model] [Code]

• UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
  Juncheng Liu, Chenghao Liu, Gerald Woo, Yiwei Wang, Bryan Hooi, Caiming Xiong, Doyen Sahoo.
  Transactions on Machine Learning Research (TMLR) 2025.
  [Code]

• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
  Taha Aksu, Gerald Woo, Juncheng Liu, Xu Liu, Chenghao Liu, Silvio Savarese, Caiming Xiong, Doyen Sahoo.
  Time Series in the Age of Large Models Workshop at NeurIPS 2024
  [LeaderBoard] [Code]

• Scalable and Effective Implicit Graph Neural Networks on Large Graphs
  Juncheng Liu, Bryan Hooi, Kenji Kawaguchi, Yiwei Wang, Chaosheng Dong, Xiaokui Xiao.
  International Conference on Learning Representations (ICLR) 2024.
  [Code]

• MGNNI: Multiscale Graph Neural Networks with Implicit Layers
  Juncheng Liu, Bryan Hooi, Kenji Kawaguchi, Xiaokui Xiao.
  Neural Information Processing Systems (NeurIPS) 2022.
  [Code]

• Dangling-Aware Entity Alignment with Mixed High-Order Proximities
  Juncheng Liu, Zequn Sun, Bryan Hooi, Yiwei Wang, Dayiheng Liu, Baosong Yang, Xiaokui Xiao, Muhao Chen.
  Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) Findings 2022.

• LSCALE: Latent Space Clustering-Based Active Learning for Node Classification
  Juncheng Liu, Yiwei Wang, Bryan Hooi, Renchi Yang, Xiaokui Xiao.
  European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) 2022.
  [Code]

• EIGNN: Efficient Infinite-Depth Graph Neural Networks
  Juncheng Liu, Kenji Kawaguchi, Bryan Hooi, Yiwei Wang, Xiaokui Xiao.
  Neural Information Processing Systems (NeurIPS) 2021.
  [Code]

• Node-wise Diffusion for Scalable Graph Learning
  Keke Huang, Jing Tang, Juncheng Liu, Renchi Yang, and Xiaokui Xiao.
  Proceedings of the ACM Web Conference (TheWebConf) 2023.

• Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis
  Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi.
  Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) 2022.

• A Fusion-Denoising Attack on InstaHide with Data Augmentation
  Xinjian Luo, Xiaokui Xiao, Yuncheng Wu, Juncheng Liu, Beng Chin Ooi.
  AAAI Conference on Artificial Intelligence (AAAI) 2022.

• No PANE, No Gain: Scaling Attributed Network Embedding in a Single Server
  Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, Sourav S. Bhowmick, Juncheng Liu.
  SIGMOD Record 2022. (ACM SIGMOD Research Highlight Award)

• Scaling Attributed Network Embedding to Massive Graphs
  Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, Juncheng Liu, Sourav S. Bhowmick.
  Proceedings of the VLDB Endowment 2021. (Best Research Paper Award)

• NodeAug: Semi-Supervised Node Classification with Data Augmentation
  Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, Juncheng Liu, Bryan Hooi.
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2020.

Experiences

• Amazon, Jun. 2023 - Sep. 2023, Applied Scientist Intern at International Machine Learning Group, working with Dr. Chaosheng Dong.
• Alibaba DAMO Academy, Sep. 2021 – Feb. 2022, Research Intern at Machine Intelligence Group, working with Dr. Dayiheng Liu.
• Tencent AI Lab, Jan. 2018 – Jul. 2018, Research Intern at Computer Vision Group, working with Dr. Zequn Jie and Dr. Lin Ma.

Professional Services

• Programme Committee Member or Reviewer: KDD 2023, NeurIPS 2023, ICLR 2024, ICML 2024, TKDE.
• Subreviewer or External Reviewer: WWW 2022.

Selected Awards & Honors

• Dean’s Graduate Research Excellence Award, NUS SoC, 2023
• NeurIPS Scholar Award, 2022
• Research Achievement, NUS SoC, 2022
• 2022 ACM SIGMOD Research Highlight Award
• Best Research Paper Award in VLDB 2021
• National Scholarship, Ministry of Education of the P. R. China, 2016 & 2017