Top AI Papers: published (NeurIPS, ICML, ICLR) x23, (KDD, WWW, ACL) x16, (AAAI, IJCAI) x11, (SIGMOD, VLDB, ICDE) x7, (IEEE Trans) x15, etc.
Workshops & Tutorials: organized 20+ events @ KDD, AAAI, IJCAI, WWW, ICDM, SDM, ICAIF, etc.
Applications: Forecasting, Forecasting+Optimization/Decision, Anomaly Detection, Anomaly Detection+Root-cause/Insight Analysis, Classification, Imputation, etc., in Cloud Computing/AIOps, Energy/Power System, Weather/Earth System, E-Commerce/BI, Healthcare/BCI, Finance, etc., related to Sequential Data (Time Series, Spatio-Temporal, Event, etc.).
Algorithm & Benchmark & Dataset & Code: (including "Time-XXX" series papers)
[ACL'25] Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement, ACL 2025. [paper]
[ICLR'25] Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts, ICLR 2025. [paper] [code] (ICLR Spotlight, Top 5%)
[ICML'25] Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting, ICML 2025. [paper]
[ICLR'24] Time-LLM: Time Series Forecasting by Reprogramming Large Language Models, ICLR 2024. [paper] [code]
[NeurIPS'24] Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis, NeurIPS 2024. [paper] [code]
[NeurIPS'24] Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting, NeurIPS 2024. [paper]
[NeurIPS'25] Multi-Scale Finetuning for Encoder-based Time Series Foundation Models, NeurIPS 2025. [arXiv]
[arXiv'25] Time-RA: Towards Time Series Reasoning for Anomaly with LLM Feedback, arXiv 2025. [paper]
[arXiv'25] Multi-Scale Finetuning for Encoder-based Time Series Foundation Models, arXiv 2025. [paper]
[arXiv'25] From Images to Signals: Are Large Vision Models Useful for Time Series Analysis? arXiv 2025. [paper]
[arXiv'25] OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting, arXiv 2025. [paper]
Survey & Position & Tutorial & Keynote:
[ICML'24] Position: What Can Large Language Models Tell Us about Time Series Analysis, ICML 2024. [paper] (Position Paper)
[KDD'24] Foundation Models for Time Series Analysis: A Tutorial and Survey, KDD 2024. [paper] [website] (Survey & Tutorial)
[KDD'25] Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey, KDD 2025. [paper] (Survey & Tutorial)
[NeurIPS'24] LLM and Foundation Model for Time Series Analysis, NeurIPS 2024 Workshop on Time Series. [Website] [slides] (Keynote Talk)
[AAAI'25] AI for Time Series Analysis: from Transformer to LLM and Foundation Models, AAAI 2025 Workshop on Time Series. [Website] (Keynote Talk)
[arXiv'23] Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook, arXiv 2023. [paper] [repo]
[arXiv'25] Position: Empowering Time Series Reasoning with Multimodal LLMs, arXiv 2025. [paper]
[arXiv'25] How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook, arXiv 2025. [paper]
[arXiv'25] Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models, arXiv 2025. [paper]
Algorithm & Benchmark & Dataset & Code: (including "XXXformer" series papers)
[ICLR'24] CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting, ICLR 2024. [paper] [code]
[ICLR'24] Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting, ICLR 2024. [paper] [code]
[ICLR'24] Explaining Time Series via Contrastive and Locally Sparse Perturbations, ICLR 2024. [paper] [code]
[KDD'22] Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting, KDD 2022. [paper] [code]
[AAAI'23] AirFormer: Predicting Nationwide Air Quality in China with Transformers, AAAI 2023. [paper] [code]
[CIKM'24] HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecasting, CIKM 2024. [paper]
[KBS'24] Rethinking Self-Supervised Learning for Time Series Forecasting: A Temporal Perspective, KBS 2024. [paper]
[KDD'25] FRT: Flow-based Reconcile Transformer for Hierarchical Time Series, KDD 2025. [paper]
Survey & Keynote:
[IJCAI'23] Transformers in Time Series: A Survey, IJCAI 2023. [paper] [repo] Selected by Paper Digest into Most Influential IJCAI Papers (Version: 2023-09), Rank 1st (1/700+ IJCAI’23 papers), (citation: 1k+)
[CIKM'22] Customized Transformers for Time Series Forecasting, CIKM 2022 Workshop on Time Series. [Website] [Slides] (Keynote Talk)
Algorithm:
[TPAMI'25] Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting," IEEE TPAMI, 2025. [arXiv]
[KDD'25] DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting, KDD 2025. [arXiv]
[KDD'24] Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting, KDD 2024. [paper] [code]
Survey:
Algorithm & Benchmark & Dataset & Code:
[NeurIPS'22] FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting, NeurIPS 2022. [paper] [code] (NeurIPS Oral, Top 2%)
[ICML'22] FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting, ICML 2022. [paper] [code]
[SIGMOD'21] RobustPeriod: Time-Frequency Mining for Robust Multiple Periodicity Detection, SIGMOD 2021. [paper]
[CIKM'22] TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis, CIKM 2022. [paper] [code]
[ICASSP'23] Robust Dominant Periodicity Detection for Time Series with Missing Data, ICASSP 2023. [paper]
[ICDE'24] Learning Multi-Pattern Normalities in the Frequency Domain for Efficient Time Series Anomaly Detection, ICDE 2024. [paper]
[KDD'25] EMD-Period: Detecting Multi-periodicity in Industrial Cloud Clusters via Time-Frequency Decomposition, KDD 2025. [paper]
[arXiv'25] Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting, arXiv 2025. [arXiv]
Tutorial and Survey:
[KDD'25] A Survey on Deep Learning based Time Series Analysis with Frequency Transformation, KDD 2025. [arXiv] (Survey & Tutorial)
Algorithm & Benchmark & Dataset & Code: (including "DiffXXX" series papers)
[TPWRS'24] DiffLoad: Uncertainty Quantification in Load Forecasting with the Diffusion Model, IEEE TPWRS 2024. [paper] [code]
[SIGSPATIAL'24] DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models, SIGSPATIAL 2024. [paper] [code]
[ECML-PKDD'25] Cross-Domain Conditional Diffusion Models for Time Series Imputation, ECML-PKDD 2025. [arXiv]
Survey:
Algorithm & Benchmark & Dataset & Code: (including "RobustXXX" series papers)
[ICLR'24] RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies, ICLR 2024. [paper] [code]
[VLDB'24] Weakly Guided Adaptation for Robust Time Series Forecasting, VLDB 2024. [paper] [code]
[TKDE'24] LogoRA: Local-Global Representation Alignment for Robust Time Series Classification, IEEE TKDE 2024. [paper]
[ICASSP'24] RobustTSVar: A Robust Time Series Variance Estimation Algorithm, ICASSP 2024. [paper]
[ICASSP'20] On Robust Variance Filtering and Change of Variance Detection, ICASSP 2020. [paper]
[KDDW'20] RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks, KDDW 2020. [paper]
[CIKM'22] Robust Time Series Dissimilarity Measure for Outlier Detection and Periodicity Detection, CIKM 2022. [paper]
[IJCAI'19] RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering, IJCAI 2019. [paper]
[ICASSP'21] A Robust and Efficient Multi-Scale Seasonal-Trend Decomposition, ICASSP 2021. [paper]
[KDD'20] Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns, KDD 2020. [paper]
[AAAI'19] RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series, AAAI 2019. [paper]
Tutorial and Survey:
[TPAMI'25] Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting, IEEE TPAMI, 2025. [arXiv]
[NeurIPS'25] ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models, NeurIPS 2025.
[NeurIPS'24] Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective, NeurIPS 2024. [paper] [code]
[ICLR'24] EasyTPP: Towards Open Benchmarking Temporal Point Processes, ICLR 2024. [paper] [code]
[AAAI'25] Unlocking the Power of LSTM for Long Term Time Series Forecasting, AAAI 2025 [paper] (AAAI Oral, Top 5%)
[IJCAI'24] Predicting Carpark Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach, IJCAI 2024. [arXiv]
[arXiv'24] PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations, arXiv 2024. [arXiv]
[arXiv'24] Toward Physics-guided Time Series Embedding, arXiv 2024. [arXiv]
[arXiv'25] From Entanglement to Alignment: Representation Space Decomposition for Unsupervised Time Series Domain Adaptation, arXiv 2025. [arXiv]
Survey and Toolkit:
[IJCAI'21] Time Series Data Augmentation for Deep Learning: A Survey, IJCAI 2021. [arXiv] Selected by Paper Digest into Most Influential IJCAI Papers (Version: 2022-02), Rank 1st (1/600+ IJCAI’21 papers). (citation: ~1k)
[arXiv'24] Time Series Analysis for Education: Methods, Applications, and Future Directions, arXiv 2024. [arXiv]
[arXiv'25] PyPOTS: A Python Toolkit for Machine Learning on Partially-Observed Time Series, arXiv 2025. [arXiv]
[NeurIPS'23] OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling, NeurIPS 2023. [paper] [code]
[NeurIPS'22] Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment, NeurIPS 2022. [paper] [code]
[IJCAI'25] Learning to Extrapolate and Adjust: Two-Stage Meta-Learning for Concept Drift in Online Time Series Forecasting, IJCAI 2025.
[arXiv'24] Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts, arXiv 2024. [arXiv]
Algorithm & Benchmark & Dataset & Code:
[KDD'25] Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels, KDD 2025. [arXiv] [code]
[VLDB'25] Noise Matters: Cross Contrastive Learning for Flink Anomaly Detection, VLDB 2025.
[TKDE'25] DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series, TKDE 2025. [arXiv]
[WWW'24] LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection, WWW 2024. [paper]
[SDM'24] Stable Synthetic Control with Anomaly Detection for Causal Inference, SDM 2024. [paper]
[CIKM'24] Advancing Multivariate Time Series Anomaly Detection: A Comprehensive Benchmark with Real-World Data from Alibaba Cloud, CIKM 2024. [paper]
[ICASSP'24] Skip-Step Contrastive Predictive Coding for Time Series Anomaly Detection, ICASSP 2024. [paper]
[KDD'23] DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection, KDD 2023. [paper] [code]
[TKDE'22] Learning Robust Deep State Space for Unsupervised Anomaly Detection in Contaminated Time-Series, IEEE TKDE 2022. [paper]
[arXiv'24] GraphSubDetector: Time Series Subsequence Anomaly Detection via Density-Aware Adaptive Graph Neural Network, arXiv 2024. [arXiv]
[arXiv'24] Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling, arXiv 2024. [arXiv]
[arXiv'25] CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series, arXiv 2025. [arXiv]
Algorithm & Benchmark & Dataset & Code:
[NeurIPS'24] Task-oriented Time Series Imputation Evaluation via Generalized Representers, NeurIPS 2024. [arXiv] [code]
[ICML'24] BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decomposition, ICML 2024. [paper] [code] (ICML Spotlight, Top 3.5%)
[arXiv'24] TSI-Bench: Benchmarking Time Series Imputation, arXiv 2024. [paper] [code]
Survey:
Weather/Earth System:
[ICML'25] OneForecast: A Universal Framework for Global and Regional Weather Forecasting, ICML 2025. [arXiv]
[KDD'25] Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting, KDD 2025. [arXiv]
[arXiv'25] NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation, arXiv 2025. [arXiv]
[arXiv'25] Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias, arXiv 2025. [arXiv]
[arXiv'25] Ocean-E2E: Hybrid Physics-Based and Data-Driven Global Forecasting of Extreme Marine Heatwaves with End-to-End Neural Assimilation, arXiv 2025. [arXiv]
[arXiv'25] Advanced Long-Term Earth System Forecasting by Learning the Small-Scale Nature, arXiv 2025. [arXiv] [code]
Energy & Power System:
[TSG'24] Deciding When to Use A Personalized Model for Load Forecasting, IEEE TSG 2024. [paper]
[TSG'24] Federated Domain Separation for Distributed Forecasting of Non-IID Household Loads, IEEE TSG 2024. [paper]
[PIEEE'23] A Cyber-Physical-Social Perspective on Future Smart Distribution Systems, Proceedings of the IEEE (PIEEE), 2023. [paper]
[AAAI'23] eForecaster: Unifying Electricity Forecasting with Robust, Flexible, and Explainable Machine Learning Algorithms, AAAI 2023. [paper] (AAAI/IAAI 2023 Innovative Application Award)
[TSG'23] Personalized Federated DARTS for Electricity Load Forecasting of Individual Buildings, IEEE TSG 2023. [paper]
[TSG'23] Improving Load Forecasting Performance via Sample Reweighting, IEEE TSG 2023. [paper]
[TSG'23] A Global Modeling Approach for Load Forecasting in Distribution Networks, IEEE TSG 2023. [arXiv] [paper] [code]
[AI Magazine'23] Energy Forecasting with Robust, Flexible, and Explainable Machine Learning Algorithms, AAAI AI Magazine, 2023. [paper]
[ICASSP'23] SaDI: A Self-Adaptive Decomposed Interpretable Framework for Electricity Load Forecasting under Extreme Events, ICASSP 2023. [arXiv]
[iEnergy'22] Adaptive Probabilistic Load Forecasting for Individual Buildings, iEnergy, 2022. [paper]
[TPWRS'22] Robust Load Forecasting towards Adversarial Attacks via Bayesian Learning, IEEE TPWRS 2022. [paper]
[arXiv'24] Benchmarks and Custom Package for Energy Forecasting, arXiv 2024. [arXiv]
[arXiv'25] PriceFM: Foundation Model for Probabilistic Electricity Price Forecasting, arXiv 2025. [arXiv]
Cloud Computing & AIOps: (including "XxxScaler" and "XxxRCA" series papers)
[VLDB'25] RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems, VLDB 2025.
[KDD'24] Cluster-Wide Task Slowdown Detection in Cloud Systems, KDD 2024. [arXiv]
[KDD'24] LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models, KDD 2024. [arXiv]
[CIKM'24] RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models, CIKM 2024. [arXiv]
[VLDB'23] MagicScaler: Uncertainty-aware, Predictive Autoscaling, VLDB 2023. [paper]
[NeurIPS'23] ADGym: Design Choices for Deep Anomaly Detection, NeurIPS 2023. [arXiv] [code]
[AAAI'23] AHPA: Adaptive Horizontal Pod Autoscaling Systems on Alibaba Cloud Container Service for Kubernetes, AAAI 2023. [arXiv] (AAAI/IAAI 2023 Innovative Application Award)
[ICDE'22] RobustScaler: QoS-Aware Autoscaling for Complex Workloads, ICDE 2022. [paper] Media Coverage: [Mo4Tech] [Alicloudnative] [Zhihu] [1024sou]
[ICASSP'22] NetRCA: An Effective Network Fault Cause Localization Algorithm, ICASSP 2022. [arXiv] [link] (ICASSP‘22 AIOps Challenge, First Place (1/382))
[CIKM'21] CloudRCA: A Root Cause Analysis Framework for Cloud Computing Platforms, CIKM 2021. [arXiv]
Finance & E-Commerce:
[JPM'24] Large Language Models for Financial and Investment Management: Models, Opportunities and Challenges, JPM, 2024. [paper]
[JPM'24] Large Language Models for Financial and Investment Management: Applications and Benchmarks, JPM, 2024. [paper]
[AAAI'26 Tutorial] Yuxuan Liang, Qingxiang Liu, Ming Jin, Xu Liu, Yushan Jian, Dongjin Song, Shirui Pan, Qingsong Wen, "Foundation Models for Time Series Analysis: A Tutorial," Tutorial at the 40th AAAI Conference on Artificial Intelligence (AAAI 2026), Singapore, Jan. 2026.
[KDD'25 Tutorial] "Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey," Tutorial at the 31st ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2025), Toronto, Canada, Aug. 2025.
[KDD'25 Tutorial] "Deep Learning in the Frequency Domain: Advances, Challenges, and Applications for Time Series Analysis," Tutorial at the 31st ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2025), Toronto, Canada, Aug. 2025.
[MM'25 Tutorial] "Multimodal Learning for Spatio-Temporal Data Mining," Tutorial at the 33rd ACM International Conference on Multimedia (MM 2025), Dublin, Ireland, Oct. 2025. [Website]
[AAAI'25 Tutorial] "Foundation Models for Time Series Analysis: A Tutorial," Tutorial at the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), Philadelphia, PA, USA, Feb. 2025. [Website]
[KDD'24 Tutorial] "Foundation Models for Time Series Analysis," Tutorial at the 30th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2024), Barcelona, Spain, Aug. 2024. [Website]
[ICDM'23 Tutorial] "Robust Time Series Analysis and Applications: An Interdisciplinary Approach", Tutorial at 23rd IEEE International Conference on Data Mining (ICDM 2023), Shanghai, China, Dec., 2023. [Website] [Slides]
[KDD'22 Tutorial] "Robust Time Series Analysis and Applications: An Industrial Perspective," Tutorial at the 28th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2022), Washington DC, USA, Aug., 2022 (70+ onsite audiences). [Website] [Slides]
KDD Workshop on Mining and Learning from Time Series (KDD'23-MiLeTS, KDD'24-MiLeTS, KDD'25-MiLeTS)
AAAI Workshop on AI for Time Series Analysis: Theory, Algorithms, and Applications (AAAI'24-AI4TS, AAAI'25-AI4TS, AAAI'26-AI4TS)
IJCAI Workshop on AI for Time Series Analysis: Theory, Algorithms, and Applications (IJCAI'23-AI4TS, IJCAI'24-AI4TS, IJCAI'25-AI4TS)
WWW Workshop on Spatio-Temporal Data Mining from the Web (WWW'25-WebST)
WWW Workshop on AI for Web-Centric Time Series Analysis (AI4TS): Theory, Algorithms, and Applications (WWW'25-AI4TS)
ICAIF 2025 Workshop on Rethinking Financial Time-Series: Foundations, Frontiers, and Future Directions (link)
ICAIF 2024 Workshop on Foundation Models for Time Series: Exploring New Frontiers (ICAIF'24-FM4TS)
SDM Workshop on AI for Time Series Analysis: Theory, Algorithms, and Applications (SDM'24-AI4TS, SDM'25-AI4TS)
ICDM Workshop on AI for Time Series Analysis: Theory, Algorithms, and Applications (ICDM'23-AI4TS)