U
UniTS
mims-harvard/UniTS
A unified multi-task time series model.
★646stars
Python
MIT
Updated: 1w ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Models project, built with Python, focusing on anomaly-detection and classification
Who made it?Maintained by mims-harvard team, 646⭐ on GitHub, #1568 out of 3201 in Models
Why does it exist?The mims-harvard team recognized that existing anomaly-detection tools in Models were hard to use. UniTS was designed to make classification more accessible.
What can it do?Key use cases: ecg, eeg, few-shot
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/mims-harvard/UniTS | 官网 https://zitniklab.hms.harvard.edu/projects/UniTS/
🔗 github.com/mims-harvard/UniTS | 官网 https://zitniklab.hms.harvard.edu/projects/UniTS/
Topics
anomaly-detectionclassificationecgeegfew-shotforecastingfoundation-modelsimputationmulti-taskprompt-tuningtime-seriesunified-modelzero-shot