absorb.md

Adapt

2 mentions across 0 people

Unknown speaker
paper · 2026-04-10
Recommended

To address this challenge, we present a new pre-training paradigm for time-series data called ADAPT, which can efficiently align the physical properties of data in the time-series domain, enabling mixed-batch pre-training despite the extreme discrepancies in the input sizes and channel dimensions of pre-training data.

ADAPT: A Novel Pre-training Paradigm for Generalizable Time-Series Foundation Mo