1
Falcon TST 2.0获世界权威测评第一名，推动时间序列基础模型从通用预测走向金融应用
蚂蚁国际日前正式发布自研时序AI预测大模型“鹰序TST”2.0版。
2
TSQueryBench: LLM-as-a-Judge for Time Series Explanations
用LLM当裁判，给时间序列解释打分，评估框架新思路值得关注。
arXiv:2604.02118v2 Announce Type: replace Abstract: Natural language explanations of time series data are increasingly produced by foundation models i…
3
Macroeconomic Forecasting with Large Language Models
大模型也能预测GDP和通胀？这项研究把LLM用在了宏观经济预测上，看它如何从海量文本中捕捉经济动向。
arXiv:2407.00890v5 Announce Type: replace-cross Abstract: This paper presents a comparative analysis evaluating the accuracy of Large Language Models …
4
Representation Matters in Longitudinal Affective Computing
探究表征方式如何影响长期情感建模的可靠性，为纵向情感计算提供关键洞见。
arXiv:2608.07518v1 Announce Type: cross Abstract: Longitudinal, in-the-wild, wearable sensing yields day-level physiology, sleep, activity, and enviro…
5
TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning
一种将时间序列基础模型与LLM推理对齐的新方法，破解时序预测难点，论文被TMLR 2026收录。
arXiv:2510.03519v2 Announce Type: replace-cross Abstract: Time series reasoning is crucial to decision-making in diverse domains, including finance, e…
6
LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models
无需训练，让大模型为时间序列预测注入语义上下文，前沿研究思路亮眼。
arXiv:2607.24892v1 Announce Type: cross Abstract: Text-conditioned time-series forecasting predicts a series from both its numerical history and natur…
7
Using LLMs for Explainable, Data-Driven Insight Generation from Time Series
用大语言模型为时间序列预测生成数据驱动的可解释洞察，提升关键决策的可信度与透明度。
arXiv:2607.18271v1 Announce Type: new Abstract: Time series forecasts are widely used in decision-critical domains, where they are rarely consumed wit…
8
LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting
用大模型引导任务语义场分解，革新工业过程预测的精度与可解释性
arXiv:2607.06623v1 Announce Type: cross Abstract: Process industries rely on time-series forecasting and soft sensing to estimate quality variables th…
9
Modular Foundation Models for Time-Series Perception in Digital Twins
模块化基础模型让数字孪生更懂时间序列，设计思路值得AI领域关注。
arXiv:2607.03585v1 Announce Type: new Abstract: Engineering Digital Twins and Prognostics and Health Management (PHM) systems rely on robust perceptio…
10
Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins
论文提出Timesynth框架，专为健康信号数字孪生设计，解决时间保真度问题，推动精准医疗建模。
arXiv:2607.00431v1 Announce Type: new Abstract: Forecasting models for health-signal digital twins must preserve the oscillatory, frequency, phase, an…
11
fev-bench: A Realistic Benchmark for Time Series Forecasting
真实场景的时间序列预测基准FEV-Bench来了，多团队联合打造，评估更贴近实际应用
arXiv:2509.26468v3 Announce Type: replace Abstract: Benchmark quality is critical for meaningful evaluation and sustained progress in time series fore…
12
HEARTS: Benchmarking LLM Reasoning on Health Time Series
首项评估LLM在健康时间序列推理能力的通用基准测试，覆盖多模态数据。
arXiv:2603.06638v3 Announce Type: replace Abstract: The rise of large language models (LLMs) has shifted time series analysis from narrow analytics to…
13
How Good Can Linear Models Be for Time-Series Forecasting?
线性模型在时间序列预测中能有多强？这篇论文给出严谨评估与新结论，值得关注
arXiv:2606.27282v1 Announce Type: new Abstract: Time-series forecasting research has been moving steadily toward larger architectures, from specialize…
14
Frequency Domain Reservoir Computing
频域视角重构储备池计算，为时间序列预测与信号处理开辟全新路径
arXiv:2606.24969v1 Announce Type: new Abstract: While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent mo…
15
Rolling Aggregations for Real-Time AI
实时AI核心技巧：滚动聚合如何高效处理时间窗口特征，一文讲透原理与实战
Article URL: https://www.hopsworks.ai/post/rolling-aggregations-for-real-time-ai Comments URL: https://news.ycombinator.com/item?id=48659199 Points: 1…
16
From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMs
用LLM解锁时间序列认知推理，从模式识别迈向深层理解，为智能分析带来全新可能。
arXiv:2606.22126v1 Announce Type: new Abstract: Time series analysis has recently been coupled with Large Language Models (LLMs) to leverage their rea…
17
Kolmogorov-Arnold Reservoir Computing
KAN与储层计算碰撞，跳出传统激活函数，解锁时序建模新范式。
arXiv:2606.19984v1 Announce Type: new Abstract: Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle …
18
From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization
将连续数值转化为离散 token，驱动LLM实现上下文感知的时间序列预测，突破传统方法边界。
arXiv:2508.09191v2 Announce Type: replace Abstract: Time series forecasting plays a vital role in supporting decision-making across a wide range of cr…
19
A tensor network approach for chaotic time series prediction
张量网络新方法破解混沌时间序列预测难题，四张图诠释15页核心理论。
arXiv:2505.17740v2 Announce Type: replace Abstract: Making accurate predictions of chaotic time series is a complex challenge. Reservoir computing, a …
20
FlowState: Sampling-Rate-Equivariant Time-Series Forecasting
FlowState实现采样率等变的时间序列预测，能有效处理不同频率数据，提升模型泛化能力。
arXiv:2508.05287v3 Announce Type: replace-cross Abstract: Existing time series foundation models (TSFMs), often based on transformer variants, lack ad…