🏷 About Me
I am currently a 4th year PhD student in East China Normal University, a member of the Decision Intelligence Lab, advised by Prof. Bin Yang. I earned my bachelor’s degree (2019-2023) at Shanghai University. For more information, you may take a look at my Google Scholar and GitHub
. If you have any questions, feel free to contact me via WeChat (ID: EmpyreanBrightMoon).
I am actively seeking research internships and Top Talent Internship opportunities in LLM foundation model development.
Research Interests
My current research interests cover Sequential Modeling, Foundation Models, and Agentic Systems. Here are some selected works:
- Agentic Systems: Exploring the potential of agentic systems in real-world applications (ST-EVO, DMoA, CRPO, ClawTrack);
- Sequential Modeling: Focusing on expert models and representation learning (CATCH, DUET, K2VAE, SRSNet);
- Foundation Models: Developing general-purpose Sequence Foundation Models (Aurora, FLAME, Horai, CoRA).
Internship (LLM Foundation Model)
At MiniMax (2026.08 - Present), I work on post-training computer-use agents for Office tasks through automated data generation, evaluation, and reinforcement learning.
At Meituan LongCat (2026.03 - 2026.08), I worked on LongCat 2.0 (1.6T), developing ClawTrack for trace-level agent evaluation and CRPO for long-horizon agentic reinforcement learning.
🔥 News
- 2026.09: 🎉🎉 Our paper TFB-2 has been accepted by VLDBJ 2026!
- 2026.09: 🎉🎉 Three of our papers, FLAME, Hermes, and Horai, have been accepted by NeurIPS 2026!
- 2026.08: 🎈🎈 Our paper ST-EVO has been accepted by EMNLP 2026 Main Conference!
- 2026.06: 🏖️🏖️ Our paper CCD has been accepted by SIGKDD 2026!
- 2026.05: 🥂🥂 Four of our papers, PATRA, SEER, Bridging Time and Frequency, and DAG, have been accepted by ICML 2026, and our survey paper A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective has been accepted by IJCAI 2026!
- 2026.03: 🏖️🏖️ Time Series Agentic System (EasyTime) was selected as one of the most influential papers by Paper Digest.
- 2026.01: 🥂🥂 Four of our papers are accepted by ICLR 2026!
- 2025.12: ⭐️⭐️ Time series model (DUET) was selected as one of the most influential papers by Paper Digest.
- 2025.11: 🎉🎉 Our paper "Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline" has been accepted as an Oral paper by AAAI 2026!
- 2025.09: 🎈🎈 Our paper "Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective" has been accepted as a Spotlight Poster by NeurIPS 2025!
- 2025.09: 📑📑 Our paper "DBLoss: Decomposition-based Loss Function for Time Series Forecasting" has been accepted by NeurIPS 2025!
- 2025.05: ⭐️⭐️ Our paper "TAB: Unified Benchmarking of Time Series Anomaly Detection Methods" has been accepted by PVLDB 2025!
- 2025.05: 🎉🎉 Our paper "K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting" has been accepted as a Spotlight Poster by ICML 2025!
- 2025.01: 🎈🎈 Our paper "CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching" has been accepted by ICLR 2025!
- 2024.12: 🏖️🏖️ Our paper "EasyTime: Time Series Forecasting Made Easy" has been accepted by ICDE 2025!
- 2024.11: 🤖🤖 Our paper "DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting" has been accepted by SIGKDD 2025
- 2024.10: ⭐️⭐️ I have been awarded the National Scholarship!
- 2024.08: 🎉🎉 Our paper "TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods" receives VLDB 2024 Best Research Paper Award Nomination!
- 2024.08: 🥂🥂 The AutoCTS series is integrated into the leaderboard for time series analytics, called OpenTS
- 2024.07: 📑📑 Our paper "FACTS: Fully Automated Correlated Time Series Forecasting in Minutes" has been accepted by PVLDB 2025
- 2024.07: 🎓🎓 Our paper "AutoCTS++: Zero-shot Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting" has been accepted by VLDBJ 2024.
📝 Publications
Filter publications
Accepted Papers

TFB-2: benchmarking and automated ensemble for time series forecasting
🧑💻 Zhengyu Li, Xingjian Wu, Xiangfei Qiu, Jilin Hu, Lekui Zhou, Chenjuan Guo, Aoying Zhou, Christian S. Jensen, Zhenli Sheng, Bin Yang
🏛️ VLDB Journal (VLDBJ), 2026. CCF A.

FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
🧑💻 Xingjian Wu*, Zhengyu Li*, Hanyin Cheng*, Xiangfei Qiu*, Jilin Hu, Chenjuan Guo, Bin Yang#
🏛️ Conference on Neural Information Processing Systems (NeurIPS), 2026. CCF A.

🧑💻 Xiangfei Qiu, Liu Yang, Hanyin Cheng, Xingjian Wu, Rongjia Wu, Zhigang Zhang, Ding Tu, Chenjuan Guo, Bin Yang, Christian S. Jensen, Jilin Hu#
🏛️ Conference on Neural Information Processing Systems (NeurIPS), 2026. CCF A.

Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
🧑💻 Peng Chen, Siyuan Wang, Shiyan Hu, Xingjian Wu, Yang Shu, Zhongwen Rao, Meng Wang, Yijie Li, Bin Yang, Chenjuan Guo#
🏛️ Conference on Neural Information Processing Systems (NeurIPS), 2026. CCF A.

ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies
🧑💻 Xingjian Wu*, Xvyuan Liu*, Junkai Lu*, Siyuan Wang, Xiangfei Qiu, Yang Shu, Jilin Hu, Chenjuan Guo, Bin Yang#
🏛️ Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026. CCF B, CORE A*.

🧑💻 Hanyin Cheng, Xingjian Wu, Xiangfei Qiu, Yang Shu, Bin Yang, Chenjuan Guo#
🏛️ ACM Knowledge Discovery and Data Mining (SIGKDD), 2026. CCF A.

PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
🧑💻 Junkai Lu*, Peng Chen*, Xingjian Wu*, Yang Shu, Chenjuan Guo, Christian S. Jensen, Bin Yang#
🏛️ International Conference on Machine Learning (ICML), 2026. CCF A.

🧑💻 Xiangfei Qiu, Xvyuan Liu, Tianen Shen, Xingjian Wu, Hanyin Cheng, Bin Yang, Jilin Hu#
🏛️ International Conference on Machine Learning (ICML), 2026. CCF A.

🧑💻 Xiangfei Qiu, Kangjia Yan, Xvyuan Liu, Xingjian Wu, Jilin Hu#
🏛️ International Conference on Machine Learning (ICML), 2026. CCF A.

DAG: A Dual Causal Network for Time Series Forecasting with Exogenous Variables
🧑💻 Xiangfei Qiu, Yuhan Zhu, Zhengyu Li, Hanyin Cheng, Xingjian Wu, Chenjuan Guo, Bin Yang, Jilin Hu#
🏛️ International Conference on Machine Learning (ICML), 2026. CCF A.

🧑💻 Xiangfei Qiu, Hanyin Cheng, Xingjian Wu, Jilin Hu, Chenjuan Guo, Bin Yang
🏛️ International Joint Conference on Artificial Intelligence (IJCAI), 2026. CCF B, CORE A*.

Aurora: Towards Universal Generative Multimodal Time Series Forecasting
🧑💻 Xingjian Wu, Jianxin Jin, Wanghui Qiu, Peng Chen, Yang Shu, Bin Yang, Chenjuan Guo#
🏛️ International Conference on Learning Representations (ICLR), 2026. CCF A.

🧑💻 Hanyin Cheng, Xingjian Wu, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo#
🏛️ International Conference on Learning Representations (ICLR), 2026. CCF A.

GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables
🧑💻 Zhengyu Li, Xiangfei Qiu, Yuhan Zhu, Xingjian Wu, Jilin Hu, Chenjuan Guo, Bin Yang#
🏛️ International Conference on Learning Representations (ICLR), 2026. CCF A.

🧑💻 Xvyuan Liu, Xiangfei Qiu, Hanyin Cheng, Xingjian Wu, Chenjuan Guo, Bin Yang, Jilin Hu#
🏛️ International Conference on Learning Representations (ICLR), 2026. CCF A.

Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
🧑💻 Xvyuan Liu*, Xiangfei Qiu*, Xingjian Wu*, Zhengyu Li, Chenjuan Guo, Jilin Hu#, Bin Yang
🏛️ Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI), 2026. CCF A.
🏆 Accepted as an Oral paper (Top 4%).

Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective
🧑💻 Xingjian Wu, Xiangfei Qiu, Hanyin Cheng, Zhengyu Li, Jilin Hu, Chenjuan Guo, Bin Yang#
🏛️ Conference on Neural Information Processing Systems (NeurIPS), 2025. CCF A.
🏆 Accepted as a Spotlight poster (Top 3.2%).

Decomposition-based Loss Function for Time Series Forecasting
🧑💻 Xiangfei Qiu, Xingjian Wu, Hanyin Cheng, Xvyuan Liu, Chenjuan Guo, Jilin Hu#, Bin Yang
🏛️ Conference on Neural Information Processing Systems (NeurIPS), 2025. CCF A.

K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
🧑💻 Xingjian Wu*, Xiangfei Qiu*, Hongfan Gao, Jilin Hu, Bin Yang#, Chenjuan Guo
🏛️ International Conference on Machine Learning (ICML), 2025. CCF A.
🏆 Accepted as a Spotlight poster (Top 2.6%).

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, Bin Yang
🏛️ International Conference on Very Large Databases (PVLDB), 2025. CCF A.

CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
🧑💻 Xingjian Wu, Xiangfei Qiu, Zhengyu Li, Yihang Wang, Jilin Hu, Chenjuan Guo, Hui Xiong, Bin Yang#
🏛️ International Conference on Learning Representations (ICLR), 2025. CCF A.

EasyTime: Time Series Forecasting Made Easy
🧑💻 Xiangfei Qiu*, Xiuwen Li*, Ruiyang Pang*, Zhicheng Pan*, Xingjian Wu*, Liu Yang*, Jilin Hu, Yang Shu, Xuesong Lu, Chengcheng Yang, Chenjuan Guo, Aoying Zhou, Christian S. Jensen and Bin Yang#.
🏛️ IEEE International Conference on Data Engineering (ICDE), 2025. CCF A.

DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
🧑💻 Xiangfei Qiu, Xingjian Wu, Yan Lin, Chenjuan Guo, Jilin Hu#, Bin Yang
🏛️ ACM Knowledge Discovery and Data Mining (SIGKDD), 2025. CCF A.

Fully Automated Correlated Time Series Forecasting in Minutes
🧑💻 Xinle Wu, Xingjian Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Bin Yang#, Christian S. Jensen
🏛️ International Conference on Very Large Databases (PVLDB), 2025. CCF A.

🧑💻 Xinle Wu*, Xingjian Wu*, Bin Yang#, Lekui Zhou, Chenjuan Guo, Xiangfei Qiu, Jilin Hu, Zhenli Sheng, Christian S. Jensen
🏛️ VLDB Journal (VLDBJ), 2024. CCF A.

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, Bin Yang
🏛️ International Conference on Very Large Databases (PVLDB), 2024. CCF A.
Preprints

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation
🧑💻 Xingjian Wu*, Junlin Liu*, Xingchen Liu*, Xuhang Zhu, Jianing Wang, Linsen Guo#, Xiaoyu Li, Xuezhi Cao, Xunliang Cai
arXiv preprint, 2026.

ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents
🧑💻 Xingjian Wu*, Xuhang Zhu*, Xingchen Liu*, Junlin Liu, Jianing Wang, Linsen Guo#, Xiaoyu Li, Xuezhi Cao, Xunliang Cai
arXiv preprint, 2026.

🧑💻 Junlin Liu*#, Jiangwang Chen*, Zixin Song*, Shuaiyu Zhou*, Chunji Lv, Xingjian Wu, Kailin Jiang, Jinyang Wu, Bohan Yu, Chenxi Zhou
arXiv preprint, 2026.

Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models
🧑💻 Xingjian Wu, Junkai Lu, Siyu Yan, Xiangfei Qiu, Jilin Hu, Chenjuan Guo, Bin Yang#
arXiv preprint, 2026.

TimeART: Towards Agentic Time Series Reasoning via Tool-Agumentation
🧑💻 Xingjian Wu, Junkai Lu, Zhengyu Li, Xiangfei Qiu, Jilin Hu, Chenjuan Guo, Christian S. Jensen, Bin Yang#
arXiv preprint, 2026.

Task-Aware Mixture-of-Experts for Time Series Analysis
🧑💻 Xingjian Wu, Zhengyu Li, Hanyin Cheng, Xiangfei Qiu, Jilin Hu, Chenjuan Guo, Bin Yang#
arXiv preprint, 2025.
*Equal Contribution, # Corresponding Author. More working drafts / preprints under review will be released later ⌛️
🎓 Educations
- 2016.09 - 2019.06 |
High School Affiliated to Fudan University - 2019.09 - 2023.06 |
Bachelor in Computer Science (Shanghai University) - 2023.09 - 2028.06 (Expected) |
PhD in Data Science (East China Normal University)
🎖 Honors and Awards
-
2025.12 PaperDigest Most Influential Paper
-
2025.10 First-class Scholarship for Academic Excellence
-
2024.10 National Scholarship
-
2024.11 Outstanding Student of East China Normal University
-
2024.08 VLDB Best Research Paper Award Nomination
-
2023.08 Outstanding Graduate of Shanghai University
-
2023.06 Ministry of Education-Huawei, Future Star Scholarship
-
2022.12 ASC STUDENT SUPERCOMPUTER CHALLENGE, (International Second Prize)
-
2021.10 Outstanding Student of Shanghai University
📖 Service
- 2026.02 Proceedings Chair of ST-FM Workshop at MDM26.
- 2026.02 PC Member of International Conference on Machine Learning (ICML 2026), (Main Track).
- 2026.02 PC Member of International Joint Conference on Artificial Intelligence (IJCAI 2026), (Main & Survey Track). Gold Reviewer.
- 2025.12 The 45th Academic Salon of DASE, ECNU.
- 2025.10 PC Member of International Conference on Learning Representations (ICLR 2026), (Main Track).
- 2025.08 PC Member of Association for the Advancement of Artificial Intelligence (AAAI 2026), (Main Technical Track).
- 2025.04 Conduct a popular science lecture on large language models for Shanghai No.1 Welfare Institute (a department - level unit).
- 2025.03 Conduct a popular science lecture on large language models for Shanghai Art & Design Academy (a department - level unit).
- 2025.02 PC Member of International Joint Conference on Artificial Intelligence (IJCAI 2025), (Main & Survey Track).
- 2024.12 PC Member of International Conference on Learning Representations (ICLR 2025), (Main Track).