Skip to content

Aurora-X: Built for Extreme Time Series Forecasting

Sep 2026 · arXiv.org · Vol abs/2609.31038 · 0 citations · 63 references
Computer Science

TL;DR

A novel pattern-guided mixture-of-experts that expands model capacity through sparse activation and uses shallow patch similarities to constrain deep-layer routing, guiding expert specialization across heterogeneous time series and an implicit quantile network head that predicts arbitrary quantiles to characterize predictive distributions, enhancing probabilistic forecasting flexibility.

Abstract

Time series foundation models (TSFMs) enable cross-domain forecasting, but their development as general-purpose forecasters remains constrained by underexplored training potential and limited architectural versatility. To address these challenges, we introduce Aurora-X, a billion-scale TSFM with a progressive curriculum and a unified architecture. We first use channel-independent pretraining to learn temporal patterns, then introduce cross-variable dependencies, varied context and horizon lengths, and future covariates if available during midtraining. Variable-resolution post-training further enables an adjustable temporal span per token at inference. With fixed model weights, this supports longer histories under a fixed token budget or fewer tokens for the same history, enabling test-time scaling. With a versatile architecture, Aurora-X supports cross-variable modeling, covariate conditioning, and parallel decoding of future patches for probabilistic forecasting. These are supported by a novel pattern-guided mixture-of-experts that expands model capacity through sparse activation and uses shallow patch similarities to constrain deep-layer routing, guiding expert specialization across heterogeneous time series. Furthermore, we propose an implicit quantile network head that predicts arbitrary quantiles to characterize predictive distributions, enhancing probabilistic forecasting flexibility. Comprehensive experiments on GIFT-Eval, TIME, FEV-Bench, TFB, and DAG-Bench demonstrate state-of-the-art forecasting performance against pretrained TSFMs and task-specific supervised models.

View source

Similar papers

Preprint Aug 2026

Into the ORBIT for Time Series: Training Regimes for Foundation Models

This work introduces ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this distribution explicit and controllable and introduces Rank-Guided Cross-Depth Alignment, a training objective that uses late-layer representations as stop-gradient teachers for shallow layers without additional i...

Hongjie Xia, Yi-Ding Liu, Yi-Fan Hu et al. · 5 citations

Scale-Invariant Conditional VAE for Coarse-Grained Economic Time-Series Forecasting

Results show that replacing or augmenting the original training set with SI-CVAE–generated data yields consistent accuracy gains across multiple forecasting baselines, and that SI-CVAE attains higher synthetic-data quality than state-of-the-art generators on standard metrics.

Jian-Ping Zhu, Lei Wang, Yang Chen et al. · 0 citations
#machine learning Preprint Sep 2026

Tabby: An Open Pretraining Recipe for Time Series Foundation Models

Tabby, a long context probabilistic time series foundation model, is released together with a complete and open recipe of how it was built, which achieves competitive zero-shot forecasting performance on GIFT-Eval and the out-of-distribution TIME benchmark.

Shi-Feng Xie, Bahaeddine Abdessalem, Ze-Hao Xiao et al. · 1 citation

Loss-Guided Pretraining Data Selection for Time-Series Foundation Models

This work connects forecasting loss to optimization difficulty by showing that normalized squared loss controls the per-sample gradient norm under a local Jacobian condition and defines a reference loss score and applies dataset-stratified selection to preserve the diversity of samples.

Yi-Ke Li, Shao-Xu Song, Jian-Min Wang · 0 citations

Latent Inference-Time Guidance of Time Series Foundation Models

Latent Inference-Time Guidance for TSFMs is introduced, which adaptively combines a pool of TSFM forecasts through a time-dependent latent space with independent components that comes equipped with identifiability and reconstruction guarantees, whilst maintaining the off-the-shelf aspect of foundation models.

Chloé Hashimoto-Cullen, Amaury Durand, Laurent Bozzi et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.