Sundial uses TimeFlow Loss for native pre-training of Transformers on continuous time series from TimeBench, achieving SOTA point and probabilistic forecasting with millisecond inference.
hub
Long-term forecasting with tide: Time-series dense encoder
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.LG 12representative citing papers
This survey and benchmark of deep time series models using the released TSLib library finds that models with specific structures perform well only on distinct analysis tasks.
STAIR's three-stage training enables simple temporal models to match or exceed complex baselines on long-term forecasting benchmarks by combining shared learning, individual adaptation, and residual cross-variable modeling.
GeoCert uses hyperbolic geometry to unify forecasting with physical reasoning and built-in formal certification, claiming major gains in accuracy and efficiency.
UniMamba integrates Mamba state-space dynamics with attention layers and transforms like FFT-Laplace to outperform prior models on multivariate time series forecasting benchmarks.
DAG proposes a dual correlation network for time series forecasting with exogenous variables that captures temporal and channel correlations to better leverage future covariates.
Logo-LLM improves time series forecasting by pulling local dynamics from shallow LLM layers and global trends from deeper layers, then aligning them via new Local-Mixer and Global-Mixer modules.
By applying attention and feed-forward networks to inverted variate tokens instead of temporal tokens, iTransformer achieves state-of-the-art performance on real-world time series forecasting datasets.
A dynamics-informed Temporal Fusion Transformer surrogate emulates stochastic tipping events in global ocean transport simulations with 465x speedup and high-fidelity timing predictions.
Characteristic roots govern dynamics in linear forecasting models but noise induces spurious roots; rank reduction and Root Purge regularization mitigate this for more robust predictions.
Multi-horizon time series forecasting framework with DLinear/NLinear models for ED boarding time prediction, integrated with external contextual data and deployed via an MLOps prototype.
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.
citing papers explorer
-
Sundial: A Family of Highly Capable Time Series Foundation Models
Sundial uses TimeFlow Loss for native pre-training of Transformers on continuous time series from TimeBench, achieving SOTA point and probabilistic forecasting with millisecond inference.
-
Deep Time Series Models: A Comprehensive Survey and Benchmark
This survey and benchmark of deep time series models using the released TSLib library finds that models with specific structures perform well only on distinct analysis tasks.
-
Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting
STAIR's three-stage training enables simple temporal models to match or exceed complex baselines on long-term forecasting benchmarks by combining shared learning, individual adaptation, and residual cross-variable modeling.
-
GeoCert: Certified Geometric AI for Reliable Forecasting
GeoCert uses hyperbolic geometry to unify forecasting with physical reasoning and built-in formal certification, claiming major gains in accuracy and efficiency.
-
UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration
UniMamba integrates Mamba state-space dynamics with attention layers and transforms like FFT-Laplace to outperform prior models on multivariate time series forecasting benchmarks.
-
DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
DAG proposes a dual correlation network for time series forecasting with exogenous variables that captures temporal and channel correlations to better leverage future covariates.
-
Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting
Logo-LLM improves time series forecasting by pulling local dynamics from shallow LLM layers and global trends from deeper layers, then aligning them via new Local-Mixer and Global-Mixer modules.
-
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
By applying attention and feed-forward networks to inverted variate tokens instead of temporal tokens, iTransformer achieves state-of-the-art performance on real-world time series forecasting datasets.
-
Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics
A dynamics-informed Temporal Fusion Transformer surrogate emulates stochastic tipping events in global ocean transport simulations with 465x speedup and high-fidelity timing predictions.
-
Characteristic Root Analysis and Regularization for Linear Time Series Forecasting
Characteristic roots govern dynamics in linear forecasting models but noise induces spurious roots; rank reduction and Root Purge regularization mitigate this for more robust predictions.
-
An Integrated Forecasting Prototype for Emergency Department Boarding Time to Support Proactive Operational Decision Making
Multi-horizon time series forecasting framework with DLinear/NLinear models for ED boarding time prediction, integrated with external contextual data and deployed via an MLOps prototype.
-
Time Series Forecasting Through the Lens of Dynamics
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.