Jilin Hu

School of Data Science and Engineering, East China Normal University
Room 217, Dili Building, 3663 North Zhongshan Road, Shanghai, China
jlhu [at] dase.ecnu.edu.cn
Google Scholar | DBLP | ECNU Profile

Jilin Hu is a Full Professor at the School of Data Science and Engineering, East China Normal University. His research develops data management and machine learning methods for spatio-temporal data, urban mobility, time series, and AI for science.

Before joining ECNU, he was an Associate Professor in the Department of Computer Science at Aalborg University and a Research Associate at the Inception Institute of Artificial Intelligence under the supervision of Prof. Jianbing Shen. He received his Ph.D. from Aalborg University in 2019, supervised by Prof. Christian S. Jensen and Prof. Bin Yang. From Oct. 2017 to Apr. 2018, he visited the University of California, Berkeley, supervised by Prof. Alexandre Bayen.

Research Interests

Spatio-temporal data managementIndexing, querying, learning, and reasoning over spatial and temporal data.
Traffic data analyticsTrajectory modeling, map inference, demand forecasting, and intelligent transportation systems.
Time series and lightweight MLEfficient models for forecasting, compression, representation learning, and deployment.
AI for scienceMachine learning for molecular, material, and scientific data analysis.

Prospective students: I am always looking for highly self-motivated students interested in data management, time series, and AI for science.

News

May 1, 2026	Our paper “SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement” was accepted at ICML 2026. Congratulations to Xiangfei Qiu.
May 1, 2026	Our paper “Less Token, More Signal: MoE Expert Pruning via Critical Token Selection” was accepted at ICML 2026. Congratulations to Zeliang Zong.
May 1, 2026	Our paper “DiSGMM: A Method for Time-varying Microscopic Weight Completion on Road Networks” was accepted at IJCAI 2026. Congratulations to Yan Lin.
May 1, 2026	Our paper “DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning” was accepted at IJCAI 2026. Congratulations to Sean Bin Yang.
May 1, 2026	Our paper “DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables” was accepted at ICML 2026. Congratulations to Xiangfei Qiu.
May 1, 2026	Our paper “Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting” was accepted at ICML 2026. Congratulations to Xiangfei Qiu.
Mar 2, 2026	One paper “One Layer’s Trash is Another Layer’s Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs” is accepted by CVPR 2026, and congrats to Kai Zhang!
Feb 20, 2026	We are organizing a Workshop on Spatio-Temoral Data and Foundation Models at MDM’26, STxFM, which will be held at Athens, Greece on June 29, 2026! Welcome for submissions.

Selected Publications

# Corresponding author

ICLR’26

ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting

Xvyuan Liu, Xiangfei Qiu, Hanyin Cheng, Xingjian Wu, Chenjuan Guo, Bin Yang, and Jilin Hu^#

In ICLR 2026
WWW’26

FSDI: Frequency-Shaped Diffusion For Time-Series Imputation

Wangmeng Shen, Hongfan Gao, Qingsong Zhong, Dingli Xu, and Jilin Hu^#

In The Web Conference 2026
WWW’26

TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generation

Xiangyu Xu, Qingsong Zhong, and Jilin Hu^#

In The Web Conference 2026
ICML’26

DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables

Xiangfei Qiu, Yuhan Zhu, Zhengyu Li, Xingjian Wu, Bin Yang, and Jilin Hu^#

In ICML 2026
ICML’26

SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement

Xiangfei Qiu, Xvyuan Liu, Tianen Shen, Xingjian Wu, Hanyin Cheng, Bin Yang, and Jilin Hu^#

In ICML 2026
ICML’26

Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting

Xiangfei Qiu, Kangjia Yan, Xvyuan Liu, Xingjian Wu, and Jilin Hu^#

In ICML 2026
ICML’26

Less Token, More Signal: MoE Expert Pruning via Critical Token Selection

Zeliang Zong, Kai Zhang, Yarong Wang, Wenming Tan, Ye Ren, and Jilin Hu^#

In ICML 2026
AAAI’26

SculptDrug: A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design

Qingsong Zhong, Haomin Yu, Yan Lin, Wangmeng Shen, Long Zeng, and Jilin Hu^#

In AAAI 2026
AAAI’26

DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion

Chenxu Han, Sean Bin Yang, and Jilin Hu^#

In AAAI 2026
AAAI’26

Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline

Xvyuan Liu, Xiangfei Qiu, Xingjian Wu, Zhengyu Li, Chenjuan Guo, Jilin Hu^# , and Bin Yang

In AAAI 2026
NeuriPS’25

DBLoss: Decomposition-based Loss Function for Time Series Forecasting

Xiangfei Qiu, Xingjian Wu, Hanyin Cheng, Xvyuan Liu, Chenjuan Guo, Jilin Hu^# , and Bin Yang

In NeuriPS 2025
PVLDB’25

TAB: Unified Benchmarking of Time Series Anomaly Detection Methods

Xiangfei Qiu, Zhe Li, Wanghui Qiu, Shiyan Hu, Lekui Zhou, Xingjian Wu, Zhengyu Li, Chenjuan Guo, Aoying Zhou, Zhenli Sheng, Jilin Hu^# , Christian S. Jensen, and Bin Yang

In PVLDB 2025
KDD’25

SSD-TS: Exploring the potential of linear state space models for diffusion models in time series imputation

Hongfan Gao, Wangmeng Shen, Xiangfei Qiu, Ronghui Xu, Bin Yang, and Jilin Hu^#

In KDD 2025
IJCAI’25

ADFormer: Aggregation Differential Transformer for Passenger Demand Forecasting

Haichen Wang, Liu Yang, Xinyuan Zhang, Haomin Yu, Ming Li, and Jilin Hu^#

In IJCAI 2025
KDD’25

DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting

Xiangfei Qiu, Xingjian Wu, Yan Lin, Chenjuan Guo, Jilin Hu^# , and Bin Yang

In KDD 2025
WWW’25

Path-LLM: A Multi-Modal Path Representation Learning by Aligning and Fusing with Large Language Models

Yongfu Wei, Yan Lin, Hongfan Gao, Ronghui Xu, Sean Bin Yang, and Jilin Hu^#

In WWW 2025

PVLDB’24

TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods

Xiangfei Qiu, Jilin Hu^# , Lekui Zhou, Xingjian Wu, Junyang Du, Buang Zhang, Chenjuan Guo, Aoying Zhou, Christian S. Jensen, Zhenli Sheng, and Bin Yang

In PVLDB 2024

arXiv Bib Code

@inproceedings{DBLP:journals/pvldb/QiuHZWDZGZJSY24,
  arxiv = {2403.20150},
  author = {Qiu, Xiangfei and Hu, Jilin and Zhou, Lekui and Wu, Xingjian and Du, Junyang and Zhang, Buang and Guo, Chenjuan and Zhou, Aoying and Jensen, Christian S. and Sheng, Zhenli and Yang, Bin},
  bibtex_show = {true},
  booktitle = {PVLDB},
  code = {https://github.com/decisionintelligence/TFB},
  corr = {true},
  number = {9},
  pages = {2363--2377},
  selected = {true},
  title = {{TFB:} Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods},
  volume = {17},
  year = {2024},
  abbr = {PVLDB'24}
}

SIGMOD’24

Origin-Destination Travel Time Oracle for Map-based Services

Yan Lin, Huaiyu Wan, Jilin Hu^# , Shengnan Guo, Bin Yang, Youfang Lin, and Christian S. Jensen

In SIGMOD 2024

arXiv Bib

@inproceedings{2307.03048,
  arxiv = {2307.03048},
  author = {Lin, Yan and Wan, Huaiyu and Hu, Jilin and Guo, Shengnan and Yang, Bin and Lin, Youfang and Jensen, Christian S.},
  bibtex_show = {true},
  booktitle = {SIGMOD},
  corr = {true},
  selected = {true},
  title = {Origin-Destination Travel Time Oracle for Map-based Services},
  year = {2024},
  abbr = {SIGMOD'24}
}

KDD

LightPath: Lightweight and Scalable Path Representation Learning

Sean Bin Yang, Jilin Hu^# , Chenjuan Guo, Bin Yang, and Christian S. Jensen

In KDD 2023

arXiv Bib Code

@inproceedings{10.1145/3580305.3599415,
  abbr = {KDD},
  arxiv = {2307.10171},
  author = {Yang, Sean Bin and Hu, Jilin and Guo, Chenjuan and Yang, Bin and Jensen, Christian S.},
  bibtex_show = {true},
  booktitle = {KDD},
  code = {https://github.com/Sean-Bin-Yang/LightPath},
  corr = {true},
  pages = {2999--3010},
  selected = {true},
  title = {LightPath: Lightweight and Scalable Path Representation Learning},
  year = {2023}
}

ICDE

Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning - Extended Version

Sean Bin Yang, Chenjuan Guo, Jilin Hu^# , Bin Yang, Jian Tang, and Christian S. Jensen

In ICDE 2022

arXiv Bib Code

@inproceedings{DBLP:journals/corr/abs-2203-16110,
  abbr = {ICDE},
  arxiv = {2203.16110},
  author = {Yang, Sean Bin and Guo, Chenjuan and Hu, Jilin and Yang, Bin and Tang, Jian and Jensen, Christian S.},
  bibtex_show = {true},
  booktitle = {ICDE},
  code = {https://github.com/Sean-Bin-Yang/TPR.git},
  corr = {true},
  selected = {true},
  title = {Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning - Extended Version},
  year = {2022}
}

AAAI

Hyperverlet: A Symplectic Hypersolver for Hamiltonian Systems

Frederik Mathiesen, Bin Yang, and Jilin Hu^#

In AAAI 2022

Bib Code

@inproceedings{aaai22_hamilton,
  abbr = {AAAI},
  author = {Mathiesen, Frederik and Yang, Bin and Hu, Jilin},
  bibtex_show = {true},
  booktitle = {AAAI},
  code = {https://github.com/Zinoex/hyperverlet},
  corr = {true},
  selected = {true},
  title = {Hyperverlet: A Symplectic Hypersolver for Hamiltonian Systems},
  year = {2022}
}

IJCAI

Unsupervised Path Representation Learning with Curriculum Negative Sampling

Sean Bin Yang, Chenjuan Guo, Jilin Hu^# , Jian Tang, and Bin Yang

In IJCAI 2021

arXiv Bib PDF Code

@inproceedings{DBLP:conf/ijcai/YangGHT021,
  abbr = {IJCAI},
  arxiv = {2106.09373},
  author = {Yang, Sean Bin and Guo, Chenjuan and Hu, Jilin and Tang, Jian and Yang, Bin},
  bibtex_show = {true},
  booktitle = {IJCAI},
  code = {https://github.com/Sean-Bin-Yang/Path-InfoMax.git},
  corr = {true},
  pages = {3286--3292},
  pdf = {IJCAI21.pdf},
  selected = {true},
  title = {Unsupervised Path Representation Learning with Curriculum Negative Sampling},
  year = {2021}
}

ICDE

Stochastic Origin-Destination Matrix Forecasting Using Dual-Stage Graph Convolutional, Recurrent Neural Networks

Jilin Hu , Bin Yang, Chenjuan Guo, Christian S. Jensen, and Hui Xiong

In ICDE 2020

Bib PDF Code

@inproceedings{DBLP:conf/icde/Hu0GJX20,
  abbr = {ICDE},
  author = {Hu, Jilin and Yang, Bin and Guo, Chenjuan and Jensen, Christian S. and Xiong, Hui},
  bibtex_show = {true},
  booktitle = {ICDE},
  code = {https://github.com/hujilin1229/od-pred},
  pages = {1417--1428},
  pdf = {ICDE2020},
  publisher = {{IEEE}},
  selected = {true},
  title = {Stochastic Origin-Destination Matrix Forecasting Using Dual-Stage Graph Convolutional, Recurrent Neural Networks},
  year = {2020}
}

ICDE

Stochastic Weight Completion for Road Networks Using Graph Convolutional Networks

Jilin Hu , Chenjuan Guo, Bin Yang, and Christian S. Jensen

In ICDE 2019

Bib PDF Code

@inproceedings{DBLP:conf/icde/HuG0J19,
  abbr = {ICDE},
  author = {Hu, Jilin and Guo, Chenjuan and Yang, Bin and Jensen, Christian S.},
  bibtex_show = {true},
  booktitle = {ICDE},
  code = {https://github.com/hujilin1229/GraphCompletion},
  pages = {1274--1285},
  pdf = {ICDE2019.pdf},
  selected = {true},
  title = {Stochastic Weight Completion for Road Networks Using Graph Convolutional Networks},
  year = {2019}
}

KBS

SparseLight: Dynamic gradient-optimized softmax for efficient transformer acceleration

Kai Zhang, Chaoxiang Lan, Yazhang Xu, Zheyang Li, Wenming Tan, Ye Ren, and Jilin Hu^#

Knowledge-Based Systems 2026

ISs

Residual memory inference network for regression tracking with weighted gradient harmonized loss

Huanlong Zhang, Jiapeng Zhang, Guohao Nie, Jilin Hu^# , and W.J. (Chris) Zhang

Information Sciences 2022

Bib

@article{ZHANG2022105,
  author = {Zhang, Huanlong and Zhang, Jiapeng and Nie, Guohao and Hu, Jilin and Zhang, W.J. (Chris)},
  title = {Residual memory inference network for regression tracking with weighted gradient harmonized loss},
  journal = {Information Sciences},
  volume = {597},
  pages = {105-124},
  year = {2022},
  bibtex_show = {true},
  abbr = {ISs},
  corr = {true},
  selected = {true}
}

GeoInformatica

Enabling time-dependent uncertain eco-weights for road networks

Jilin Hu , Bin Yang, Christian S. Jensen, and Yu Ma

GeoInformatica 2017

Bib PDF

@article{DBLP:journals/geoinformatica/HuYJM17,
  author = {Hu, Jilin and Yang, Bin and Jensen, Christian S. and Ma, Yu},
  title = {Enabling time-dependent uncertain eco-weights for road networks},
  journal = {GeoInformatica},
  volume = {21},
  number = {1},
  pages = {57--88},
  year = {2017},
  pdf = {GeoInfo.pdf},
  bibtex_show = {true},
  abbr = {GeoInformatica},
  selected = {true}
}

VLDBJ

Risk-aware path selection with time-varying, uncertain travel costs: a time series approach

Jilin Hu , Bin Yang, Chenjuan Guo, and Christian S. Jensen

VLDB J. 2018

Bib PDF

@article{DBLP:journals/vldb/HuYGJ18,
  author = {Hu, Jilin and Yang, Bin and Guo, Chenjuan and Jensen, Christian S.},
  title = {Risk-aware path selection with time-varying, uncertain travel costs: a time series approach},
  journal = {{VLDB} J.},
  volume = {27},
  number = {2},
  pages = {179--200},
  year = {2018},
  bibtex_show = {true},
  abbr = {VLDBJ},
  selected = {true},
  pdf = {https://link.springer.com/article/10.1007/s00778-018-0494-9}
}

TNNLS

Few-Shot Object Detection With Self-Supervising and Cooperative Classifier

Di Qi, Jilin Hu^# , and Jianbing Shen

IEEE TNNLS 2024

Bib

@article{qi2022fsod,
  author = {Qi, Di and Hu, Jilin and Shen, Jianbing},
  title = {Few-Shot Object Detection With Self-Supervising and Cooperative Classifier},
  journal = {IEEE TNNLS},
  volume = {35},
  number = {4},
  pages = {5435--5446},
  year = {2024},
  bibtex_show = {true},
  abbr = {TNNLS},
  selected = {true},
  corr = {true}
}