Yong Liu | Tsinghua University

About Me

I am currently a PhD student (from fall, 2021) at the School of Software of Tsinghua University and a member of the THUML, advised by Prof. MingSheng Long.

My research interests cover Deep Learning and Time Series Analysis. I am currently working on time series foundation models and MLSys for time series. In addition to pure research, I also dedicate myself to promoting research on valuable real-world applications. My research aims to contribute to the advancement of intelligent systems capable of handling massive and complicated temporal data across domains, including finance, healthcare, industry, and environment.

For more information, please take a look at my Google Scholar and GitHub.

News

[Jun. 2025] An open-source time series foundation model (Sundial) is released here, which can generate multiple probable predictions.
[Jun. 2025] A generative foundation model for time series (Sundial) was accepted as ICML 2025 Oral!
[Mar. 2025] An open-source large time-series model (Timer) is released here, which can make zero-shot predictions.
[Jan. 2025] An multivariate attention for time series (Timer-XL) was accepted in ICLR 2025.
[Jan. 2025] iTransformer for Ant Group Green Computing are awarded as Outstanding Projects of CCF Fund.
[Sep. 2024] Two papers (AutoTimes and TimeXer) were accepted in NeurIPS 2024.
[Jun. 2024] A large model for time series (Timer) was accepted in ICML 2024. Code is available.
[Jan. 2024] A deep model for multivariate forecasting (iTransformer) was accepted as ICLR 2024 Spotlight!
[Dec. 2023] Native AI analytical engine (AINode) in database (Apache IoTDB) is released!
[Oct. 2023] A deep model for non-stationary forecasting inspired by Koopman theory (Koopa) was accepted as NeurIPS 2023.
[Apr. 2023] TimesNet for general time series analysis was accepted as ICLR 2023.
[Oct. 2022] Non-stationary Transformers was accepted as NeurIPS 2022.

Publications & Preprints

ICML

Sundial: A Family of Highly Capable Time Series Foundation Models

Yong Liu*, Guo Qin*, Zhiyuan Shi, Zhi Chen, Caiyin Yang, Xiangdong Huang, Jianmin Wang, Mingsheng Long#

International Conference on Machine Learning, 2025.

arXiv Code Oral Paper

ICLR

Timer-XL: Long-Context Transformers for Unified Time Series Forecasting

Yong Liu*, Guo Qin*, Xiangdong Huang, Jianmin Wang, Mingsheng Long#

International Conference on Learning Representations, 2025.

arXiv Code Poster Slides Accepted

ICLR

iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

Yong Liu*, Tengge Hu*, Haoran Zhang*, Haixu Wu, Shiyu Wang, Lintao Ma, Mingsheng Long#

International Conference on Learning Representations, 2024.

arXiv Code Poster Slides Spotlight Paper, PaperDigest Most Influential Paper

NeurIPS

Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting

Yong Liu*, Haiwu Wu*, Jianmin Wang, Mingsheng Long#

Conference on Neural Information Processing Systems, 2022.

arXiv Code Poster Slides Accepted

ICML

Timer: Generative Pre-trained Transformers Are Large Time Series Models

Yong Liu*, Haoran Zhang*, Chenyu Li*, Xiangdong Huang, Jianmin Wang, Mingsheng Long#

International Conference on Machine Learning, 2024.

arXiv Code Poster Slides Dataset Accepted

NeurIPS

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

Yong Liu*, Chenyu Li*, Jianmin Wang, Mingsheng Long#

Conference on Neural Information Processing Systems, 2023.

arXiv Code Poster Slides Accepted

ICLR

TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

Haiwu Wu*, Tengge Hu*, Yong Liu*, Hang Zhou, Jianmin Wang, Mingsheng Long#

International Conference on Learning Representations, 2023.

arXiv Code Slides Accepted, PaperDigest Most Influential Paper

NeurIPS

AutoTimes: Autoregressive Time Series Forecasters via Large Language Models

Yong Liu*, Guo Qin*, Xiangdong Huang, Jianmin Wang, Mingsheng Long#

Conference on Neural Information Processing Systems, 2024.

arXiv Code Poster Slides Accepted

NeurIPS

TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables

Yuxuan Wang*, Haixu Wu*, Jiaxiang Dong, Guo Qin, Haoran Zhang, Yong Liu, Yunzhong Qiu, Jianmin Wang, Mingsheng Long#

Conference on Neural Information Processing Systems, 2024.

arXiv Accepted

arxiv

Deep Time Series Models: A Comprehensive Survey and Benchmark

Yuxuan Wang*, Haixu Wu*, Jiaxiang Dong, Yong Liu, Mingsheng Long, Jianmin Wang#

arxiv preprint

arXiv arXiv preprint, 2025

JMLR

Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs

Kaichao You*, Yong Liu*, Ziyang Zhang, Jianmin Wang, Michael I. Jordan, Mingsheng Long#

Journal of Machine Learning Research, 2022.

arXiv Code Accepted

ICML

LogME: Practical Assessment of Pre-trained Models for Transfer Learning

Kaichao You*, Yong Liu*, Jianmin Wang, Mingsheng Long#

International Conference on Machine Learning, 2021.

arXiv Code Accepted

Selected Projects

HuggingFace Models

Sundial - Generative times series foundation models (Pre-trained on 1 trillion pts).
Timer - Large times-series models (Pre-trained on 260 billion pts).

Deep Models for Time Series

iTransformer - Foundation Multivariate Time Series Model.
Non-stationary Transformers - Transformers for Non-stationary Forecasting.
Koopa - Theory-inspired efficient non-stationary time series forecaster.
AutoTimes - LLM-based time series forecasting with texts.

Algorithms and Model Package

Large-Time-Series-Model - Maintainer.
OpenLTM - Maintainer.
Time Series Library - Co-Author.
Transfer Learning Library - Committer.

System and Applications

Apache IoTDB - AINode: Native machine learning engine in time series database.
Ant Group - iTransformer: Green computing of data center, developed in Ant Group.

Invited Talks

Large Time Series Models and Resources at ISF 2025. [Slides]
Foundation Models and MLSys for Time Series at Apache IoTDB. [Slides]
Large Models for Native Database Analysis at TPCTC 2024. [Slides]
Exploring Large Models for Time Series at IoA, CAS. [Slides]
Deep Learning for Time Series Applications at DoA, THU. [Slides]

Services

Academic Services

Conference Reviewer, International Conference on Learning Representations (ICLR) 2024-2025.
Conference Reviewer, International Conference on Machine Learning (ICML) 2022-2025.
Conference Reviewer, Conference on Neural Information Processing Systems (NeurIPS) 2023-2025.
Conference Reviewer, International Conference on Machine Learning (CVPR) 2023.
Conference Reviewer, International Conference on Very Large Databases (VLDB) 2023.

Teaching Experiences

Teaching Assistant, Database System, Spring 2024, Prof. Jianmin Wang.
Teaching Assistant, Machine Learning, Fall 2023, Prof. Mingsheng Long.
Teaching Assistant, Introduction to Artificial Intelligence, Spring 2023, Prof. Mingsheng Long.
Teaching Assistant, Deep Learning, Fall 2022, Prof. Mingsheng Long.
Teaching Assistant, Introduction to Artificial Intelligence, Spring 2022, Prof. Mingsheng Long.
Teaching Assistant, Machine Learning, Fall 2021, Prof. Mingsheng Long.
Teaching Assistant, Introduction to Artificial Intelligence, Spring 2021, Prof. Mingsheng Long.

Education

Ph.D. in Software Engineering (School of Software, Tsinghua University), 2021 to present.
Second Degree Bachelor in Economics (School of Economics and Management, Tsinghua University), 2018 to 2021.
Bachelor in Software Engineering (School of Software, Tsinghua University), 2021 to present, 2017 to 2021.

Honors & Awards

Outstanding Papers of Beijing (北京市优秀毕业论文), 2021.
Outstanding Graduates of Beijing (北京市优秀毕业生), 2021.
Excellent Graduates of Tsinghua (清华大学优秀毕业生), 2021.
Future Researcher Scholarship of Tsinghua (清华大学未来学者奖学金), 2021.
Tuyoo Scholarship (途游奖学金), 2024.
Shenzhen Stock Exchange Scholarship (深交所奖学金), 2023.
Boeing Scholarship (波音奖学金), 2020.
Tang Lixin Scholarship (唐立新优秀奖学金), 2020.
Jiang Nanxiang Scholarship (蒋南翔奖学金), 2019.
Huawei Scholarship (华为奖学金), 2018.