AAAI 2026 accepted papers on Time series
105 of the 4,417 papers accepted at AAAI 2026 (2.4%) are on Time series, compared with 2.1% at AAAI 2025. They fall into 4 topics.
See AAAI 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Long-term forecasting · 57 papers
- FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition (7 citations)
- Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency Differencing (6 citations)
- EMAformer: Enhancing Transformer Through Embedding Armor for Time Series Forecasting (4 citations)
- XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series Forecasting with Exogenous Inputs (4 citations)
- M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting (3 citations)
- TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding (3 citations)
- APT: Affine Prototype-Timestamp for Time Series Forecasting Under Distribution Shift (2 citations)
- C3RL: Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning (2 citations)
- DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting (2 citations)
- Generalising Traffic Forecasting to Regions Without Traffic Observations (2 citations)
- MedSpaformer: A Transferable Transformer with Multi-Granularity Token Sparsification for Medical Time Series Classification (2 citations)
- Optimal Look-back Horizon for Time Series Forecasting in Federated Learning (2 citations)
and 45 more in the interactive map.
Causal and generative time series · 22 papers
- Time Series Forecasting via Direct Per-Step Probability Distribution Modeling (2 citations)
- Beyond MSE: Ordinal Cross-Entropy for Probabilistic Time Series Forecasting (1 citation)
- Continuum Dropout for Neural Differential Equations (1 citation)
- DiM-TS: Bridge the Gap Between Selective State Space Models and Time Series for Generative Modeling (1 citation)
- EcoDiffusion: Uncertainty-Aware Emulation of Ecosystem Processes with Conditional Diffusion for Long Sequences with Single-Step Initialization (1 citation)
- A Theoretical Analysis of Detecting Large Model-Generated Time Series
- Active Learning of Symbolic Automata over Rational Numbers
- CaT-Diff: Cascaded Text-enhanced Diffusion Model for Time-Series Imputation
- COGS: A Causal Representation Learning Framework for Out-of-Distribution Generalization in Time Series
- Counterfactual eXplainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification
- Feature Attribution for Human Sensing with Radio Signals
- FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification
and 10 more in the interactive map.
Foundation models for time series · 20 papers
- Kronos: A Foundation Model for the Language of Financial Markets (5 citations)
- Mask the Redundancy: Evolving Masking Representation Learning for Multivariate Time-Series Clustering (5 citations)
- MTP: Exploring Multimodal Urban Traffic Profiling with Modality Augmentation and Spectrum Fusion (5 citations)
- OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting (4 citations)
- DeepSenseMoE: Harnessing Power of Time Series Foundation Models for Few-Shot Human Activity Recognition (3 citations)
- A Unified Shape-Aware Foundation Model for Time Series Classification (2 citations)
- EdgeMTSC: A Lightweight Large-Kernel ConvNet for Multivariate Time Series Classification (1 citation)
- HeartLLM: Discretized ECG Tokenization for LLM-Based Diagnostic Reasoning (1 citation)
- HyperLoad: A Cross-Modality Enhanced Large Language Model-Based Framework for Green Data Center Cooling Load Prediction (1 citation)
- Koopman Invariants as Drivers of Emergent Time-Series Clustering in Joint-Embedding Predictive Architectures (1 citation)
- M3Time: LLM-Enhanced Multi-Modal, Multi-Scale, and Multi-Frequency Multivariate Time Series Forecasting (1 citation)
- ORTCL: Towards Continual Learning of Time Series Foundation Models on Streaming Data via Orthogonal Rotation (1 citation)
and 8 more in the interactive map.
Anomaly detection · 6 papers
- CANDI: Curated Test-Time Adaptation for Multivariate Time-Series Anomaly Detection Under Distribution Shift (2 citations)
- State-Derivative-Aware Neural Controlled Differential Equations for Multivariate Time Series Anomaly Detection and Diagnosis (2 citations)
- Harnessing Vision-Language Models for Time Series Anomaly Detection (1 citation)
- DoKnowAD: Calibrating Normal Representations with Refined Domain Knowledge to Enhance Time Series Anomaly Detection
- Finding Time Series Anomalies Using Granular-Ball Vector Data Description
- FreqTAD: Multi-scale Frequency Encoding and Time-Frequency Attention for Anomaly Detection in Dynamic Graphs