ICLR 2026 accepted papers on Time series
110 of the 5,358 papers accepted at ICLR 2026 (2.1%) are on Time series, compared with 1.7% at ICLR 2025. They fall into 4 topics.
See ICLR 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
Causal and generative time series · 36 papers
- TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology State (1 citation)
- Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?
- Characteristic Root Analysis and Regularization for Linear Time Series Forecasting
- CRONOS: Continuous time reconstruction for 4D medical longitudinal series
- Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring
- DeNOTS: Stable Deep Neural ODEs for Time Series
- Detecting Invariant Manifolds in ReLU-Based RNNs
- DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
- Flow-based Conformal Prediction for Multi-dimensional Time Series
- Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification
- In-Context Learning of Temporal Point Processes with Foundation Inference Models
- Latent-to-Data Cascaded Diffusion Models for Unconditional Time Series Generation
and 24 more in the interactive map.
Foundation models for time series · 31 papers
- Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative (1 citation)
- Repurposing Foundation Model for Generalizable Medical Time Series Classification (1 citation)
- Semantic-Enhanced Time-Series Forecasting via Large Language Models (1 citation)
- TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis (1 citation)
- Zero-shot Forecasting by Simulation Alone (1 citation)
- Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models
- Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
- Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
- Can we generate portable representations for clinical time series data using LLMs?
- CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data
- Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning
- GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series data
and 19 more in the interactive map.
Long-term forecasting · 31 papers
- A foundation model with multi-variate parallel attention to generate neuronal activity
- CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter
- CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting
- Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series
- Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning
- Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
- Extreme Weather Nowcasting via Local Precipitation Pattern Prediction
- GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care
- GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables
- Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting
- MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with $0.1K$ Parameters
- Numerion: A Multi-Hypercomplex Model for Time Series Forecasting
and 19 more in the interactive map.
Anomaly detection · 12 papers
- Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring.
- Contextual and Seasonal LSTMs for Time Series Anomaly Detection
- Low Rank Transformer for Multivariate Time Series Anomaly Detection and Localization
- PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
- Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction
- When Foundation Models are One-Liners: Limitations and Future Directions for Time Series Anomaly Detection
- Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation Models
- Enhancing Sparse Event Detection in Healthcare Time-Series via Adaptive Gate of Context–Detail Interaction
- EVEREST: A Transformer for Probabilistic Rare-Event Anomaly Detection with Evidential and Tail-Aware Uncertainty
- Free Point-wise Anomaly Detection via Fold-bifurcation
- ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly Detection
- PGRF-Net: A Prototype-Guided Relational Fusion Network for Diagnostic Multivariate Time-Series Anomaly Detection