3 papers
cs.LG2026
Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language
Xinran Feng, Yi Xie, Chao Zhang +4
Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to read a series and write a description, so label qua…
cs.LG2025
The language of time: a language model perspective on time-series foundation models
Yi Xie, Yun Xiong, Zejian Shi +2
With the rise of large language models, the paradigm of training foundation models with massive parameter counts on vast datasets has been adopted in multiple domains to achieve re…
stat.ML2024
Enhancing Masked Time-Series Modeling via Dropping Patches
Tianyu Qiu, Yi Xie, Yun Xiong +2
This paper explores how to enhance existing masked time-series modeling by randomly dropping sub-sequence level patches of time series. On this basis, a simple yet effective method…