Core Viewpoint - The release of the Antelope Energy Model 3.0 marks a significant advancement in the integration of AI and energy sectors, providing replicable solutions for the intelligent transformation of China's energy industry [1][9]. Group 1: Model Upgrades and Applications - Antelope Energy Model 3.0 features three major upgrades: continuous enhancement of foundational capabilities, deep integration of AI into business scenarios, and the establishment of a comprehensive toolchain for data processing and model evaluation [3][4]. - The model addresses key industry challenges by enhancing time-series modeling capabilities, which are crucial for maintaining the dynamic balance of power systems [4][6]. - The model has been successfully applied in various scenarios, including power forecasting, load forecasting, and electricity price prediction, achieving significant improvements in accuracy [6][7]. Group 2: Industry Collaboration and Ecosystem Building - The launch event was attended by government officials, industry leaders, and academic experts, emphasizing the collaborative effort in exploring the integration of AI and the energy industry [3][8]. - Antelope Company is actively building an industrial ecosystem by partnering with major state-owned enterprises and assisting in the development of large models for various applications [8][9]. - The company aims to support the high-quality development of the energy sector and contribute to achieving carbon neutrality goals through continuous technological iteration and scenario expansion [9].

针对这些痛点，羚羊能源大模型3.0构建起统一时序基础框架，完成时序信号统一表征与多任务统一建 模，解决传统模型碎片化问题。借助千亿级时序数据的自监督学习能力，模型可自主挖掘深层特征，建 立长周期建模能力，即便新场景数据稀缺也能快速泛化，让"沉睡"数据真正"开口说话"。 工业能源设备运维长期受困于预警规则固化、故障诊断依赖专家、检修经验难沉淀等痛点。羚羊设备运 维大模型通过融合语言与时序基础模型，利用"双擎驱动"架构，结合数据与知识的时空对齐机制，构建 起覆盖运行监控、消缺管理、定修管理、检修质量管理、智能分析的全流程智能化体系。 在日前举办的第八届世界声博会上，羚羊能源大模型3.0发布。会上同期发布了电力交易、设备运维两 大垂直场景模型，标志着羚羊公司在"AI+能源"领域实现升级，为我国能源行业智能化转型，探索可复 制推广的解决方案。 羚羊公司总裁徐甲甲阐述了羚羊能源大模型3.0的升级方向：一是基础能力持续升级，除语言、视觉能 力外，重点提升时序能力；二是将AI深度融入业务场景，解决实际问题；三是构建完善的全流程工具 链，包括数据清洗、训练框架、模型评估等。 新能源的安全高效消纳与电网稳定运行，核心在于精准把 ...

Core Insights - The article discusses the development and application of the Kronos model, a Time-Series Foundation Model (TSFM) specifically designed for financial market data, particularly K-line data [3][9][17] - Kronos aims to address the challenges of low signal-to-noise ratio and strong non-stationarity in financial time series data, which often hinder the performance of general-purpose models [3][9] - The model employs a two-phase framework: K-line tokenization and autoregressive pre-training, allowing it to effectively learn the complex "language" of financial markets [12][13][17] Summary by Sections Introduction to TSFM - TSFMs have emerged from the success of large-scale language models in NLP and CV, focusing on pre-training on diverse time series data to create a general-purpose model adaptable to various tasks [2][6] - The key advantages of TSFMs include their generalization and transfer learning capabilities, enabling them to learn universal time patterns and trends from vast datasets [2][6] Overview of Kronos Model - Kronos is tailored for financial K-line data, utilizing a "domain pre-training + fine-tuning" approach to deeply understand financial market characteristics [3][9] - The model's architecture includes a specialized tokenizer and a large autoregressive Transformer model, which learns the syntax and dynamics of financial data [9][12][17] Performance Evaluation of Kronos - Initial tests of the Kronos standard model on major A-share indices showed a high correlation between predicted and actual closing prices, with a Spearman correlation coefficient of 0.732 for the 5-day forecast [4][19] - The model's predictive performance improved significantly when fine-tuned, achieving a Spearman correlation of 0.856 for the same forecast [4][39] Application of Kronos in Timing Strategies - The article explores the application of Kronos in constructing timing strategies based on predicted closing prices, specifically for the CSI 1000 index [30][33] - The strategy generated positive returns, but it missed significant upward trends since July 2025, indicating a reliance on prior index reversal logic [30][33] Enhanced Performance with Fine-Tuning - A fine-tuned version of Kronos demonstrated a 33.9% return in 2025, with an annualized excess return of 9%, outperforming the original method by over 20 percentage points [5][42] - The fine-tuning process involved adjusting model parameters and rolling adjustments to better adapt to market conditions, leading to improved predictive accuracy [34][42] Conclusion - Kronos represents a significant advancement in financial time series forecasting, effectively capturing the complexities of financial data and translating predictions into actionable investment strategies [17][42]