BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal//recurring_events_ical//2.0//EN
BEGIN:VEVENT
UID:d6dd1fd4-1259-42cd-ad90-2732a492fc31@support.access-ci.org
DTSTAMP:20250520T133346Z
DTSTART:20250611T170000Z
DTEND:20250611T180000Z
SUMMARY:Recent Advances in Time Series Foundation Modeling
DESCRIPTION:Time series foundation models are changing how we work with tim
 e-based data, similar to how large pre-trained language and vision models 
 transformed text and image modeling. In this talk, we will briefly introdu
 ce MOMENT, one of the first families of open-source time series foundation
  models. MOMENT models offer three key advantages: they work as building b
 locks for various time series tasks (like forecasting, classification, ano
 maly detection, and imputation); they perform well immediately without nee
 ding many examples (enabling zero-shot forecasting and few-shot classifica
 tion); and they can be fine-tuned with in-distribution, task-specific data
  to improve results. We will show how MOMENT is already being used in real
  applications. The talk will conclude with our latest research on developi
 ng foundation models that can handle longer and multivariate time series, 
 methods to understand and steer these models, and how large language model
  agents can enhance time series machine learning engineering.Bios:Artur Du
 brawski, Ph.D. M.Eng, is an Alumni Research Professor Chair of Computer Sc
 ience at Carnegie Mellon University where he directs the Auton Lab, one of
  the largest applied machine learning and artificial intelligence teams in
  academia. For more than 3 decades he has been working on the forefront of
  development of AI serving in technical leadership roles in industry and l
 eading multiple research endeavors in academia.Mononito Goswami recently g
 raduated with a Ph.D. in Robotics from Carnegie Mellon University. He is i
 nterested in developing foundational machine learning (ML) techniques for 
 real-world applications. His research tackles the limitations of tradition
 al ML approaches, focusing on scenarios with inaccurate, decentralized, an
 d insufficient data, all in effort to democratize ML. He led the developme
 nt of one of the first open-source foundation models for time series data.
URL:https://support.access-ci.org/events/8017
END:VEVENT
END:VCALENDAR