Published September 29, 2025 | Version v1
Dataset Open

MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series

Authors/Creators

  • 1. Northwestern University

Description

This is the accompanying processed dataset for the paper : MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series, appearing in Neurips 2025.

Files

daliahar_data.zip

Files (4.7 GB)

Name Size
md5:92011780b403c8e31e7d3d4bc3533dcc
1.8 GB Preview Download
md5:924072a3eac6c442b2ce7f97fd1a3acc
1.3 GB Preview Download
md5:21760ee75b011beeb594ca852a2ba06d
1.5 GB Preview Download

Additional details

Identifiers

arXiv
arXiv:2509.25278

Related works

Is supplement to
Dataset: arXiv:2509.25278 (arXiv)

Dates

Accepted
2025-09-29

Software

Repository URL
https://github.com/payalmohapatra/MAESTRO