学术成果


发表论文

(*代表共同第一作者,代表通讯作者)

2024

  • Naiqi Li, Zhikang Xia, Yiming Li, Ercan E. Kuruoglu, Yong Jiang, Shu-Tao Xia. Portfolio Selection via Graph-Aware Gaussian Processes With Generalized Gaussian Likelihood. IEEE Transactions on Artificial Intelligence (TAI), 2024. [paper]

  • Naiqi Li*, Wenjie Li*, Yinghua Gao, Yiming Li, Jigang Bao, Ercan E. Kuruoglu, Yong Jiang, Shu-Tao Xia. Node-Level Graph Regression With Deep Gaussian Process Models. IEEE Transactions on Artificial Intelligence (TAI), 2024. [paper]

  • Yaohua Zha, Naiqi Li, Yanzi Wang, Tao Dai, Hang Guo, Bin Chen, Zhi Wang, Zhihao Ouyang, Shu-Tao Xia. LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling. Conference on Neural Information Processing Systems (NeurIPS), 2024. [paper]

  • Tao Dai, Beiliang Wu, Peiyuan Liu, Naiqi Li, Xue Yuerong, Shu-Tao Xia, Zexuan Zhu. DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting. Conference on Neural Information Processing Systems (NeurIPS), 2024. [paper]

  • Shiqi Dai, Xuanyu Zhu, Naiqi Li, Tao Dai, Zhi Wang. Procedural Level Generation with Diffusion Models from a Single Example. AAAI Conference on Artificial Intelligence (AAAI), 2024. [paper]

  • Bolin Jiang, Yuqiu Xie, Jiawei Li, Naiqi Li, Yong Jiang, Shu-Tao Xia. CAGEN: Controllable Anomaly Generator using Diffusion Model. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. [paper]

  • Peiyuan Liu, Beiliang Wu, Naiqi Li, Tao Dai, Fengmao Lei, Jigang Bao, Yong Jiang, Shu-Tao Xia. WFTNet: Exploiting Global and Local Periodicity in Long-Term Time Series Forecasting. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. [paper]

  • Tao Dai, Beiliang Wu, Peiyuan Liu, Naiqi Li, Jigang Bao, Yong Jiang, Shu-Tao Xia. Periodicity Decoupling Framework for Long-term Series Forecasting. International Conference on Learning Representations (ICLR), 2024. [paper] [poster]

  • Yuqiu Xie, Bolin Jiang, Jiawei Li, Naiqi Li, Bin Chen, Tao Dai, Yuang Peng, Shu-Tao Xia. GladCoder: Stylized QR Code Generation with Grayscale-Aware Denoising Process. International Joint Conference on Artificial Intelligence (IJCAI), 2024. [paper]

  • Bolin Jiang, Yuqiu Xie, Jiawei Li, Naiqi Li, Bin Chen, Shu-Tao Xia. IGSPAD: Inverting 3D Gaussian Splatting for Pose-agnostic Anomaly Detection. ACM International Conference on Multimedia (MM), 2024. [paper]

2023

  • Guanghao Meng, Tao Dai, Bin Chen, Naiqi Li, Yong Jiang, Shu-Tao Xia. Difficulty-Aware Data Augmentor for Scene Text Recognition. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. [paper]

  • Xinyi Zhang*, Naiqi Li*, Jiawei Li, Tao Dai, Yong Jiang, Shu-Tao Xia. Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model. International Conference on Computer Vision (ICCV), 2023. [paper]

2022

  • Naiqi Li*, Wenjie Li*, Yong Jiang, Shu-Tao Xia. Deep Dirichlet process mixture models. Conference on Uncertainty in Artificial Intelligence (UAI), 2022. [paper]

2021

  • Xiang Liu, Naiqi Li, Shu-Tao Xia. GDTW: A Novel Differentiable DTW Loss for Time Series Tasks. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021. [paper]

  • Naiqi Li, Yinghua Gao, Wenjie Li, Yong Jiang, Shu-Tao Xia. H-GPR: A Hybrid Strategy for Large-Scale Gaussian Process Regression. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021. [paper]

2020

  • Yinghua Gao*, Naiqi Li*, Ning Ding, Yiming Li, Tao Dai, Shu-Tao Xia. Generalized Local Aggregation for Large Scale Gaussian Process Regression. International Joint Conference on Neural Networks (IJCNN), 2020. [paper]

  • Naiqi Li*, Wenjie Li*, Jifeng Sun, Yinghua Gao, Yong Jiang, Shu-Tao Xia. Stochastic Deep Gaussian Processes over Graphs. Conference on Neural Information Processing Systems (NeurIPS), 2020. [paper]

2019前

  • Peiming Mo, Naiqi Li, Yongmei Liu. Automatic Verification of Golog Programs via Predicate Abstraction. European Conference on Artificial Intelligence (ECAI), 2016. [paper]

  • Naiqi Li, Yongmei Liu. Automatic Verification of Partial Correctness of Golog Programs. International Joint Conference on Artificial Intelligence (IJCAI), 2015. [paper]

  • Naiqi Li, Yi Fan, Yongmei Liu. Reasoning about State Constraints in the Situation Calculus. International Joint Conference on Artificial Intelligence (IJCAI), 2013. [paper]

  • Yi Fan, Minghui Cai, Naiqi Li, Yongmei Liu. A First-Order Interpreter for Knowledge-Based Golog with Sensing based on Exact Progression and Limited Reasoning. AAAI Conference on Artificial Intelligence (AAAI), 2012. [paper]

项目经验

主持承担项目

2023.12 - 2024.12
项目负责人

面向金融时序预测与多源异构数据的扩散模型研究

深圳市稳定支持面上项目


作为项目组长负责项目

2023.08 - 2025.06
项目组长

时序机器学习技术在金融任务中的应用

深圳悟空投资管理有限公司横向课题


2023.04 - 2024.04
项目组长

基于二维时空融合的时间序列分析

平安银行横向课题


2022.04 - 2023.04
项目组长

面向差异化工业视觉应用的异常检测技术合作项目

华为横向课题


2023.05 - 2023.12
项目组长

工业设备时序数据分析研究

美的横向课题


其它参与项目

2022.08 - 2023.08
核心成员

面向鸿蒙开源生态发展的智能运营系统研究

华为横向课题


2019.07 - 2022.06
核心成员

复杂动态互联网行为的基准建模与异常分析

国家重点研发计划重点专项,国家级项目


发明专利
  • 李乃琦,刘昱君,鲍际刚,刘祥,江勇,夏树涛。 一种基于混合专家模型与检索增强的时序数据预测方法。 申请号:202410727323.4。

  • 李乃琦,刘培源,鲍际刚,江勇,夏树涛。 一种基于双域归一化的交通流时间序列预测方法。 申请号:202410845620.9。

学术活动

2025

  • 论文审稿:AAAI、KDD、CVPR、ICASSP

2024

  • 论文审稿:UAI、ICASSP、TNNLS

2022

  • 论文审稿:ICASSP

2020

  • 海报展示:Stochastic Deep Gaussian Processes over Graphs. Conference on Neural Information Processing Systems (NeurIPS), 2020.
  • 线上报告:深度图高斯过程

2019前

  • 会议报告:Automatic Verification of Partial Correctness of Golog Programs. nternational Chinese Scholar Workshop on Knowledge Representation and Reasoning (KRW), 2015.
  • 海报展示:Reasoning about State Constraints in the Situation Calculus. International Joint Conference on Artificial Intelligence (IJCAI), 2013.
  • 协助审稿:IJCAI-16、AAAI-16、IJCAI-15、PRIMA-15