Tong Guan

Tong Guan

PhD Candidate, Zhejiang University
Visiting PhD Student, Griffith University

Hugging Face

Tong Guan is currently a Visiting PhD Student at the School of Information and Communication Technology, Griffith University (2024–present), where he is mentored by Dr Ming Jin and Prof. Shirui Pan in the Trustworthy AGI (TrustAGI) Lab, where his research focuses on multimodal time series analysis.

He is a PhD candidate in the College of Control Science and Engineering at Zhejiang University (2021–present), advised by Prof. Jun Liang. Prior to that, he received his B.Eng. from the College of Control Science and Engineering, Zhejiang University (2017–2021).

His research interests include multimodal learning, time series, and generative AI.

🔥 News

  • 2026.06:  Serving as a Program Committee member for MILETS Workshop @ KDD 2026, Mining and Learning from Time Series, Jeju, South Korea.
  • 2026.05:  📝 Our latest preprint AION: Next-Generation Tasks and Practical Harness for Time Series is out on arXiv. See the project page.
  • 2026.04:  🎉 TimeOmni-VL: Unified Models for Time Series Understanding and Generation accepted at ICML 2026.
  • 2026.01:  🎉 TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models accepted at ICLR 2026.
  • 2025.11:  Serving as a Program Committee member for AI4TS Workshop @ AAAI 2026, AI for Time Series Analysis, Singapore.
  • 2025.11:  Served as a Program Committee member for the Workshop on Rethinking Financial Time-Series (RFTS) at ICAIF ‘25, Singapore.

📝 Selected Publications

ICLR 2026

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

Tong Guan, Z. Meng, D. Li, S. Wang, C.-H. H. Yang, Q. Wen, Z. Liu, S. M. Siniscalchi, et al.

  • Incentivizing complex reasoning with time series in large language models.

Total Hugging Face downloads (4B + 7B + 9B): 📥7,561

Demo Video Model Dataset Demo Inference Code

ICML 2026
TimeOmni-VL

TimeOmni-VL: Unified Models for Time Series Understanding and Generation

Tong Guan, S. Pan, J. Barthelemy, Z. Li, Y. Cai, C. Alippi, M. Jin, S. Pan

  • Unified models for time series understanding and generation.

Total Hugging Face downloads: 📥113

Model Dataset Demo Code

WWW WebST'25 Workshop
GraphSTAGE

GraphSTAGE: Channel-Preserving Graph Neural Networks for Time Series Forecasting

Tong Guan, K. Ma, J. Peng, J. Liang, B. Du, M. Jin, S. Pan

  • Channel-preserving graph neural networks for time series forecasting.
ITSC 2023
STGMMOE

Spatial-Temporal Graph Multi-Gate Mixture-of-Expert Model for Traffic Prediction

Tong Guan, J. Peng, J. Liang

  • A spatial-temporal graph multi-gate mixture-of-expert model for traffic prediction.

Other Publications

  • Accurate Spatial Representation and Propagation Without Prior Knowledge for Traffic Forecasting. K. Ma, X. Yan, Tong Guan, J. Peng, J. Liang. CCC 2025.
  • Trajectory Planning for Unmanned Surface Vessels in Confined Waters. Y. Zhan, J. Fan, Tong Guan, J. Liang. CAC 2024.
  • An Optimal Trajectory Planning for Automated On-Ramp Merging. J. Liang, Tong Guan, D. Liu, X. Liu, Z. Luan, H. Liu, X. Yuan. IET Intelligent Transport Systems, 17(5):835–847, 2023.
  • Spatial-Temporal Graph Discriminant AutoEncoder for Traffic Congestion Forecasting. J. Peng, Tong Guan, J. Liang. ITSC 2023.
  • MND-GAN: A Research on Image Deblurring Algorithm Based on Generative Adversarial Network. J. Peng, Tong Guan, F. Liu, J. Liang. CCC 2023.
  • A Bipartite Graph Based Method for Traffic Continuous Data Imputation. J. Peng, Tong Guan, J. Liang. CAC 2023.

📖 Educations

  • 2021.09 - present, PhD candidate, College of Control Science and Engineering, Zhejiang University.
  • 2024 - present, Visiting PhD Student, School of ICT, Griffith University.
  • 2017.09 - 2021.06, B.Eng., College of Control Science and Engineering, Zhejiang University.

🧑‍🏫 Academic Services

💬 Conference Reviewer

  • NeurIPS 2026 — Conference on Neural Information Processing Systems, Sydney, Australia

  • ICLR 2026 — Int’l Conference on Learning Representations, Rio de Janeiro, Brazil

  • ICLR 2025 — Int’l Conference on Learning Representations, Singapore

  • ICASSP 2026 — IEEE Int’l Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain

📄 Journal Reviewer

🗒️ Program Committee