PulseAugur
EN
LIVE 07:57:22

New time series foundation models tackle zero-shot forecasting and scale invariance

Researchers have introduced Timer-M1, a novel multivariate time series foundation model designed for zero-shot forecasting by learning temporal and relational primitives. This model utilizes a primitive-based data synthesis and pretraining pipeline, incorporating gated two-dimensional Transformer blocks for dynamic cross-variate attention. In parallel, a separate study proposes Scale-Invariant Training (ScaleIn) for time series foundation models, addressing issues of scale-contaminated training (ScaleCon) where series with larger scales disproportionately influence the model. ScaleIn aims to improve convergence and forecasting accuracy by ensuring gradients are not dominated by high-scale series, showing significant reductions in error across various benchmarks and architectures. AI

IMPACT These advancements in time series foundation models could lead to more robust and accurate forecasting across various domains, impacting fields like finance, climate science, and resource management.

RANK_REASON Two research papers published on arXiv detailing new methods for time series foundation models.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New time series foundation models tackle zero-shot forecasting and scale invariance

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
Two research papers published on arXiv detailing new methods for time series foundation models.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
46 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Haoran Zhang, Haixuan Liu, Xingjian Su, Yong Liu, Zhi Chen, Yuxuan Wang, Jianmin Wang, Mingsheng Long ·

    Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives

    arXiv:2610.11734v1 Announce Type: cross Abstract: We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting. Across domains, time series share elementary temporal and relational patterns, termed primitives,…

  2. arXiv cs.AI TIER_1 English(EN) · Ignacy Stepka, Willa Potosnak, Kin G. Olivares, Artur Dubrawski ·

    Scale-Invariant Training for Time Series Foundation Models

    arXiv:2610.07324v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are trained on large collections of time series datasets that span various morphologies and domains. This setting exposes models to series whose scales -- typical magnitudes of their values --…