IBM's Tiny TSPulse Beats Models 100x Bigger Across 75 Datasets
IBM's 1M-parameter TSPulse foundation model handles classification, anomaly detection, imputation, and search with GPU-free inference and open weights.
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read
IBM's 1M-parameter TSPulse foundation model handles classification, anomaly detection, imputation, and search with GPU-free inference and open weights.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
