time-series-foundation-models

The machine learning toolkit for time series analysis in Python

About model release for "Sundial: A Family of Highly Capable Time Series Foundation Models" (ICML 2025 Oral)

A curated list of papers & resources on anomaly detection foundation models using large language model, vision-language model, graph foundation model, time series foundation model, etc

Python sdk for zero-shot time-series forecasting

[NeurIPS 2026] Inertia-1: An Open Exploration of Wearable Motion Foundation Models

[KDD 2026] Official implementation of KDD'26 paper "TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection"

The official PyTorch implementation of our NeurIPS'25 paper: Synthetic Series-Symbol Data Generation for Time Series Foundation Models.

JS sdk for zero-shot time-series forecasting

The official code repository for our ICLR 2026 paper, Adaptive Transformation Optimization for Domain-Shared Time Series Foundation Models.

Manifest-backed, local-first reproducibility layer for fair time-series forecasting — official model bridges, sealed run cards, and interactive evidence views.

Forecasting airport terminal passenger flows with known-future flight schedule information: simulator, schedule-conditioned models and controls for the paper "The Schedule Is the Signal"

[NIPS2026] VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection