NeurIPS 2025 accepted papers on Time series
99 of the 5,812 papers accepted at NeurIPS 2025 (1.7%) are on Time series, compared with 1.9% at NeurIPS 2024. They fall into 4 topics.
See NeurIPS 2025 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
Foundation models for time series · 38 papers
- TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning (4 citations)
- TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster (4 citations)
- Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens (2 citations)
- GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images (2 citations)
- SEMPO: Lightweight Foundation Models for Time Series Forecasting (2 citations)
- This Time is Different: An Observability Perspective on Time Series Foundation Models (2 citations)
- TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop (2 citations)
- AdaTS: Learning Adaptive Time Series Representations via Dynamic Soft Contrasts (1 citation)
- Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning (1 citation)
- Multi-Scale Finetuning for Encoder-based Time Series Foundation Models (1 citation)
- Synthetic Series-Symbol Data Generation for Time Series Foundation Models (1 citation)
- Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach (1 citation)
and 26 more in the interactive map.
Long-term forecasting · 28 papers
- OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain (3 citations)
- DBLoss: Decomposition-based Loss Function for Time Series Forecasting (2 citations)
- Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift (2 citations)
- MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling (2 citations)
- Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation (2 citations)
- TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting (2 citations)
- xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories (2 citations)
- Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency (1 citation)
- FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution (1 citation)
- Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting (1 citation)
- Towards Accurate Time Series Forecasting via Implicit Decoding (1 citation)
- DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space
and 16 more in the interactive map.
Causal and generative time series · 23 papers
- Conformal Prediction for Time-series Forecasting with Change Points (2 citations)
- A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking (1 citation)
- Deep Continuous-Time State-Space Models for Marked Event Sequences (1 citation)
- TimeWak: Temporal Chained-Hashing Watermark for Time Series Data (1 citation)
- TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents (1 citation)
- A Geometry-Aware Metric for Mode Collapse in Time Series Generative Models
- Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction
- Addressing Mark Imbalance in Integration-free Marked Temporal Point Processes
- Constrained Posterior Sampling: Time Series Generation with Hard Constraints
- Contimask: Explaining Irregular Time Series via Perturbations in Continuous Time
- Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
- Glocal Information Bottleneck for Time Series Imputation
and 11 more in the interactive map.
Anomaly detection · 10 papers
- CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling (3 citations)
- Multivariate Time Series Anomaly Detection with Idempotent Reconstruction (2 citations)
- PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection (1 citation)
- ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection (1 citation)
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection (1 citation)
- Channel Matters: Estimating Channel Influence for Multivariate Time Series
- Delving into Large Language Models for Effective Time-Series Anomaly Detection
- Fortifying Time Series: DTW-Certified Robust Anomaly Detection
- NoBOOM: Chemical Process Datasets for Industrial Anomaly Detection
- Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection