尚宗江个人照片

尚宗江Zongjiang Shang

湖南大学人工智能与机器人学院助理教授，浙江大学人工智能方向博士研究生，师从陈岭教授。研究方向为图神经网络、超图神经网络、大模型，智能体与具身智能，致力于以人工智能驱动的方式理解现实世界中复杂的时间序列信号。

zongjiangshang@cs.zju.edu.cn GitHub talented__jiang 小红书 ORCID 简历 PDF
时间序列预测 工业异常检测 时空数据挖掘 AI for Science 超图神经网络 大模型 智能体 AutoML
01

简介

我的研究主要围绕人工智能驱动的复杂时空数据分析与智能建模展开，重点面向时间序列预测、工业异常检测以及地球系统与气候科学等应用场景。 重点涉及四个相关联的方向：面向地球系统建模与气候分析的人工智能科学研究；新型深度学习框架研究； 基于通用表征学习、知识迁移与自主推理的大模型、大语言模型以及智能体研究；聚焦于机器学习系统的自动化设计与优化算法研究。

AI for Science

面向地球系统与科学计算场景：
  • Weather Forecasting
  • Climate Forecasting
  • Earth Foundation Model

Deep Learning Architectures

探索新型深度学习架构设计：
  • Hypergraph Neural Networks
  • Graph Neural Networks
  • State Space Models (Mamba)
  • Neural ODE

Foundation Models

研究通用表征学习、知识迁移与自主推理模型：
  • Large Language Models (LLMs)
  • Time Series Foundation Models
  • AI Agents

Automated Machine Learning

聚焦于机器学习系统的自动化设计与优化，提升模型性能、效率和可扩展性：
  • Neural Architecture Search
  • Automated Deep Learning
  • Efficient AI
  • LLM Fine-tuning
02

教育&工作背景

2026.03 – 至今
湖南大学 · 人工智能与机器人学院
助理教授  |  刘敏教授/王耀南院士团队成员
2021.09 – 2026.03
浙江大学 · 软件学院
人工智能 · 博士研究生  |  导师：陈岭教授（陈纯院士团队）
2020.06 – 2021.06
崂山国家实验室
助理工程师  |  笪良龙院士团队
2017.09 – 2020.06
西北工业大学 · 电子信息学院
电路与系统 · 硕士研究生  |  导师：吴俊（IEEE Member, ACM Member, CCF Member）
2013.09 – 2017.06
东北林业大学 · 机械工程学院
机械电子工程 · 本科
03

论文

  1. Zongjiang Shang, Dongliang Cui, Binqing Wu, Ling Chen, Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis. [ICLR 2026]
  2. Yue Yu, Weiqi Chen, Binqing Wu, Dongliang Cui, Wanyi Jiang, Zongjiang Shang, Bo Wu, Liang Sun, Ling Chen, ClimateAR: Multi-scale autoregressive generative modeling for climate forecasting. [ICML 2026]
  3. Zongjiang Shang, Chengxi Jin, Binqing Wu, Dongliang Cui, Yue Yu, Haobang Sun, Chuanlin Xu, Ling Chen, TimeMRA: LLM-empowered time series forecasting via multi-scale retrieval-augmented representations. [ICML 2026]
  4. Binqing Wu, Jian Zhou, Zongjiang Shang, Ling Chen, LagLLM: LLM-empowered lead-lag dependency learning for spatial-temporal time series forecasting. [ICML 2026]
  5. Zongjiang Shang, Binqing Wu, Dongliang Cui, Ling Chen, TimePMG: LLM-based time series forecasting with period-aware multi-scale decomposition and group-wise alignment. [AAAI 2026]
  6. Binqing Wu, Zongjiang Shang, Shiyu Liu, Jianlong Huang, Jiahui Xu, Ling Chen, AirDDE: Multifactor neural delay differential equations for air quality forecasting. [AAAI 2026]
  7. Binqing Wu, Weiqi Chen, Shiyu Liu, Zongjiang Shang, Haiou Wang, Liang Sun, Ling Chen, MoCast: Learning turbulent motions under physical guidance for precipitation nowcasting. [AAAI 2026]
  8. Binqing Wu, Jianlong Huang, Zongjiang Shang, Ling Chen, ST-Hyper: Learning high-order dependencies across multiple spatial-temporal scales for multivariate time series forecasting. [CIKM 2025]
  9. Ling Chen, Jiahua Cui, Zongjiang Shang, Dongliang Cui, TPRNN: A top-down pyramidal recurrent neural network for time series forecasting. [INS 2025]
  10. Zongjiang Shang, Ling Chen, Binqing Wu, Dongliang Cui, Ada-MSHyper: Adaptive multi-scale hypergraph transformer for time series forecasting. [NeurIPS 2024]
  11. Ling Chen, Donghui Chen, Zongjiang Shang, Binqing Wu, Cen Zheng, Bo Wen, Wei Zhang, Multi-scale adaptive graph neural network for multivariate time series forecasting. [TKDE 2024]
  12. Donghui Chen, Ling Chen, Zongjiang Shang, Youdong Zhang, Bo Wen, Chenghu Yang, Scale-aware neural architecture search for multivariate time series forecasting. [TKDD 2024]
  13. Jun Wu, Zongjiang Shang, Kaiwei Wang, Jiarong Zhai, Yiting Wang, Fang Xia, Wenyuan Li, Jiajia Zhang, Fan Zhang, Partially occluded head posture estimation for 2D images using pyramid HoG features. [ICME 2019]
  14. Zongjiang Shang, Yue Yu, Binqing Wu, Dongliang Cui, Ling Chen, D-PAD: Deep-shallow multi-frequency patterns disentangling for time series forecasting. [Preprint]
  15. Zongjiang Shang, Binqing Wu, Dongliang Cui, Yue Yu, Haobang Sun, Chuanlin Xu, Ling Chen, PMHyper: Period-aware multi-scale hypergraph for time series forecasting. [Preprint]
  16. Jian Zhou, Binqing Wu, Zongjiang Shang, Chengxi Jin, Dongliang Cui, Yue Yu, Ling Chen, STMemoLLM: A spatial-temporal memory-augmented LLM for robust traffic forecasting. [Preprint]
  17. Zongjiang Shang, Chengxi Jin, Binqing Wu, Jian Zhou, Dongliang Cui, Haobang Sun, Chuanlin Xu, Yue Yu, Xinyang Wang, Ling Chen, M²TSF: LLM-empowered time series forecasting via multi-stream multi-scale modeling. [Preprint]
  18. Zongjiang Shang, Ling Chen, MSHyper: Multi-scale hypergraph transformer for long-range time series forecasting. [Preprint]
  19. Dongliang Cui, Zongjiang Shang, Weiqi Chen, Yue Yu, Wanyi Jiang, Binqing Wu, Bo Wu, Liang Sun, Ling Chen, MMRN: A multi-scale multi-task residual network for seasonal climate forecasting. [Preprint]
  20. Binqing Wu, Zongjiang Shang, Ling Chen, DSTCGCN: Learning dynamic spatial-temporal cross dependencies for traffic forecasting. [Preprint]
04

专利

  1. 一种基于层次化超图神经网络的电力负载预测方法 [202310432912.5]
  2. 一种基于自适应多尺度超图神经网络的电力负载预测方法 [202411011366.9]
  3. 一种基于多尺度超图神经网络和大语言模型对齐的电力负载预测方法 [202510546395.3]
05

专业技能

熟悉图神经网络、超图神经网络、Transformer 的基本理论；掌握大语言模型、多模态大模型、大模型训练与微调相关技术。 受邀担任 ICLR、ICML、NeurIPS、AAAI、TKDE、KDD 等顶级期刊与会议的审稿人。

Graph Neural Networks Hypergraph Neural Networks Transformers LLM Multimodal LLM Agent LLM Fine-tuning
06

荣誉奖项