English(EN) Test-Time Forecasting: Recurrent Depth Enables In-Context Dynamics Prediction

新的测试时预测框架使基础模型能够预测未见的动力学

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员引入了一个名为测试时预测（TTF）的新框架，使基础模型能够预测未见动力学系统的动力学。该框架利用循环 Transformer 和梯度下降作为循环深度来模拟偏微分方程（PDE）、常微分方程（ODE）和时间序列的传播器。经过一步预测训练的 TTF 模型在自回归展开过程中表现出对分布外系统动力学的泛化能力。 AI

影响该框架可以增强基础模型泛化和预测复杂系统动力学能力，可能影响科学研究和模拟。

排序理由该集群包含一篇详细介绍基础模型新框架和方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍基础模型新框架和方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Jeffrey B. Lai, John Quinn, Anthony Bao, William Gilpin · 2026-10-15 04:00

测试时预测：循环深度实现上下文动力学预测

arXiv:2610.19552v1 Announce Type: new Abstract: Foundation models for dynamical systems can forecast unseen partial differential equations (PDEs), ordinary differential equations (ODEs), and time series during inference. However, it remains an open question whether these foundati…

本文如何被排名

报道来源 [1]

测试时预测：循环深度实现上下文动力学预测

相关实体

相关话题