关于LLMQuant
LLMQuant起源于剑桥大学校内，是由一群来自世界顶尖高校和量化金融从业人员组成的前沿社区，致力于探索人工智能（AI）与量化（Quant）领域的无限可能。我们的团队成员来自剑桥大学、牛津大学、哈佛大学、苏黎世联邦理工学院、北京大学、中科大等世界知名高校，外部顾问来自Microsoft、HSBC、Jump Trading、Man Group、国内顶尖私募等一流企业。
LLMQuant前沿讲座
LLMQuant前沿讲座系列旨在邀请杰出的学者和业界专家，分享他们在量化金融领域的最新研究成果和实践经验。
第一期前沿讲座，我们邀请到南加州大学计算机科学系的博士生Defu Cao，他曾在著名对冲基金Point72 Cubist工作，将以AI in Quant: New Frontiers in Time Series Foundation Models为主题，分享最新的时间序列基础模型的研究进展，以及这些模型在量化金融领域的应用前景。
讲座信息
时间：10月20日（周日）上午10:00（北京时间）
地点：线上（使用腾讯会议）
报名方式：扫描下方二维码，报名成功后在会在邮箱收到会议链接
日程：
-
? 10:00-10:45 嘉宾报告
-
? 10:45-11:00 交流讨论
主题简介
Recent advancements in foundation models have revolutionized natural language processing and computer vision, but their application to time series data has remained limited. This talk explores the emerging frontier of foundation models for temporal data, highlighting recent breakthroughs that promise to transform time series analysis and forecasting across diverse domains. We begin by examining TEMPO, a novel prompt-based generative pre-trained transformer for time series forecasting. Building on TEMPO’s insights, we discuss the latest developments in transformer diffusion architectures like TimeDiT, which push the boundaries of performance in tasks such as imputation, forecasting, and anomaly detection. We explore how these models capture intricate temporal dependencies and generalize across diverse time series data, from weather patterns to financial markets. The talk will cover the challenges and opportunities in scaling these models to larger datasets and more complex temporal phenomena. We’ll examine their potential impact on real-world applications in energy management, healthcare, and finance. Finally, we’ll look ahead to future research directions, including multimodal integration and interpretability, that could further expand the capabilities of time series foundation models.
嘉宾简介
Defu Cao is a Ph.D. in Computer Science at the University of Southern California, working with Prof. Yan Liu. His work focuses on developing innovative approaches to modeling complex temporal data and developing foundation models for time series, including pioneering work on TEMPO and TimeDiT. His research has been published in top-tier conferences such as NeurIPS, ICLR, ICML, CVPR, AAAI, etc. His innovative work has earned him the 2024 Viterbi Graduate Student Award for Best Research Assistant and a Graduate School Endowed Fellowship. Cao is actively involved in the academic community, serving as a reviewer for prestigious conferences and journals, including NeurIPS, ICML, and IEEE TPAMI, as well as mentoring in programs like the EAAI Undergraduate Mentorship Program.
主持人简介
Yuhao Huang is a Ph.D. student in Computer Science at Nanjing University, supervised by Prof. Wu-Jun Li. His research interests include generative time series modeling, reinforcement learning, and their applications in quantitive finance. He worked as a research intern with the Machine Learning group at Microsoft Research Asia from 2023 to 2024.
关于LLMQuant
-
?? 每日资讯：人工智能与量化金融的前沿动态，附中英文原文，助你紧跟行业发展。
-
?? 策略详解：获取量化策略的完整代码，支持多平台回测，提升你的实战能力。
-
? 免费答疑：每日解答社区成员问题，高效提升你的知识水平。
-
?? 线上交流：与国内外量化从业者互动，参与深度知识分享，拓展你的专业网络。
搜索 LLMQuant
关注我们