PulseAugur
中
实时 05:14:21
English(EN) RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting

新研究增强了用于预测的时序基础模型

作者 PulseAugur 编辑部 · [4 个来源] ·

四篇新研究论文探讨了时序基础模型（TSFM）的进展，重点是提高其预测能力。一篇论文介绍了一种在稀疏事件数据上评估TSFM的方法，发现当前模型相比简单参考模型改进有限，并建议使用事件监督。另一篇论文提出了一个损失引导的预训练数据选择框架，以优化来自大型数据集的学习信号。第三篇论文提出了潜在推理时引导（Latent Inference-Time Guidance），一种TSFM的自适应集成方法，通过时变潜在空间组合预测。第四篇论文介绍了RACE，一个用于测试时适应性的框架，通过对相关序列的证据进行对齐和聚合，提高了邻域丰富的预测场景下的TSFM性能。 AI

影响 这些进展可能带来更准确、更高效的各领域预测，从金融市场到资源管理。

排序理由 该集群包含多篇关于特定人工智能研究主题的学术论文。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

新研究增强了用于预测的时序基础模型

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含多篇关于特定人工智能研究主题的学术论文。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
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
4 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [4]

  1. arXiv cs.LG TIER_1 English(EN) · Daniel Schoess, Florian von Wangenheim ·

    何时而非多少：评估稀疏事件上的时间序列基础模型

    arXiv:2609.39386v1 Announce Type: new Abstract: Pretrained time-series foundation models (TSFMs) are evaluated as forecasters of future values, yet for sparse series many decisions depend only on which future periods contain activity. Standard benchmarks do not assess this. On fi…

  2. arXiv cs.AI TIER_1 English(EN) · Yike Li, Shaoxu Song, Jianmin Wang ·

    面向时间序列基础模型的损失引导预训练数据选择

    arXiv:2609.37255v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are pretrained on heterogeneous collections containing billions of observations, yet their training windows are typically sampled without estimating whether they provide useful learning signal…

  3. arXiv cs.LG TIER_1 English(EN) · Chlo\'e Hashimoto-Cullen, Amaury Durand, Laurent Bozzi, Benjamin Guedj, Yannig Goude, Sylvain Le Corff ·

    时间序列基础模型的潜在推理时间引导

    arXiv:2609.38058v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) currently provide state-of-the-art results in forecasting tasks. They are available out-of-the-box and rely on in-context learning to make their predictions, which makes the quality of their p…

  4. arXiv stat.ML TIER_1 English(EN) · Hao-Nan Shi, Tong Wu, Chen-Cong Sun, Yuan Jiang, Han-Jia Ye, De-Chuan Zhan ·

    RACE：面向邻居丰富的时序基础模型的残差感知测试时自适应预测

    arXiv:2610.00405v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich forecasting, where each query has access to related but nonidentical historical series.…

相关实体

相关话题