NeurIPS 2025PastLarge language modelsTime series
Recent Advances in Time Series Foundation Models Have We Reached the 'BERT Moment'?
BERT2S
- Submission deadline
- Aug 30, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (33)
Fetched from OpenReview (v2) on 2026-06-10.
A More Realistic Evaluation of Cross-Frequency Transfer Learning and Foundation Forecasting Models
Adaptive Refinement of Time Series Foundation Models via Pattern and Context-Awareness
Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction
Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs
CHRONOGRAPH: A Real-World Graph-Based Multivariate Time Series Dataset
Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models
FlowState: Sampling-Rate Invariant Time Series Foundation Model with Dynamic Forecasting Horizons
FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
Frequency Matters: When Time Series Foundation Models Fail Under Spectral Shift
Goal-Oriented Time-Series Forecasting: Foundation Framework Design
HORIZON: A Benchmark for In-the-wild User Behaviour Modeling
How Foundational are Foundation Models for Time Series Forecasting?
Kronos: A Foundation Model for the Language of Financial Markets
Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative
Leveraging Generic Time Series Foundation Models for EEG Classification
Linear Regression as a Litmus Test for Time Series Forecasting Benchmarks
LiveDrill: Multimodal Segment-Triggered Data-to-Text for Time Series Foundation Models
LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting
LTSM-Bundle: A Toolbox and Benchmark on Large Language Models for Time Series Forecasting
OATS: Online Data Augmentation for Time Series Foundation Models
On the Internal Semantics of Time-Series Foundation Models
Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification
qHuBERT: Quantized Model for ECG Classification
TempusBench: An Evaluation Framework for Time-Series Forecasting
Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models
TimeCopilot
TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
TimeSeriesExamAgent: Creating TimeSeries Reasoning Benchmarks at Scale
TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting
Zero Shot Time Series Forecasting: Do Time Series FMs Outperform Cross Modal FMs?
Zero-shot forecasting of epidemics
Zero-to-Forecast: Natural Language to Time Series Prediction via Cross-Modal Ensembles