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.
Autotimes: Autoregressive time series forecasters via large language models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Foundation models of time series have not been fully developed due to the limited availability of time series corpora and the underexploration of scalable pre-training. Based on the similar sequential formulation of time series and natural language, increasing research demonstrates the feasibility of leveraging large language models (LLM) for time series. Nevertheless, the inherent autoregressive property and decoder-only architecture of LLMs have not been fully considered, resulting in insufficient utilization of LLM abilities. To fully revitalize the general-purpose token transition and multi-step generation capability of large language models, we propose AutoTimes to repurpose LLMs as autoregressive time series forecasters, which projects time series into the embedding space of language tokens and autoregressively generates future predictions with arbitrary lengths. Compatible with any decoder-only LLMs, the consequent forecaster exhibits the flexibility of the lookback length and scalability with larger LLMs. Further, we formulate time series as prompts, extending the context for prediction beyond the lookback window, termed in-context forecasting. By introducing LLM-embedded textual timestamps, AutoTimes can utilize chronological information to align multivariate time series. Empirically, AutoTimes achieves state-of-the-art with 0.1% trainable parameters and over $5\times$ training/inference speedup compared to advanced LLM-based forecasters. Code is available at this repository: https://github.com/thuml/AutoTimes.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
LLM-derived measurement semantics enable a lightweight pre-inference correction step that reduces industrial prediction MAE by 30.7% on real tests and 80.3% under controlled sensor corruption.
A survey proposing a taxonomy of Injective, Bridging, and Internal Alignment paradigms to evolve TSA into user-driven Time Series Question Answering with LLMs.
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
ESE enables simultaneous forecasting of multiple interacting systems by estimating an equilibrium state in a single pass, matching SOTA accuracy with 10-70x speedup and linear complexity.
TSF converts process variable documents into frozen semantic vectors that scale the numerical input window before a time-series backbone, yielding average MAE reductions of 2.9–3.6% across industrial forecasting tasks.
citing papers explorer
-
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.
-
LLM-Guided Measurement Credibility Correction for Trustworthy Industrial Process Inference
LLM-derived measurement semantics enable a lightweight pre-inference correction step that reduces industrial prediction MAE by 30.7% on real tests and 80.3% under controlled sensor corruption.
-
From Time Series Analysis to Question Answering: A Survey in the LLM Era
A survey proposing a taxonomy of Injective, Bridging, and Internal Alignment paradigms to evolve TSA into user-driven Time Series Question Answering with LLMs.
-
Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
-
Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation
ESE enables simultaneous forecasting of multiple interacting systems by estimating an equilibrium state in a single pass, matching SOTA accuracy with 10-70x speedup and linear complexity.
-
LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting
TSF converts process variable documents into frozen semantic vectors that scale the numerical input window before a time-series backbone, yielding average MAE reductions of 2.9–3.6% across industrial forecasting tasks.