Guillaume Doquet
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Frequent co-authors
Research Timeline
2026
STEP: Learning STructured Embeddings for Progressive Time Series
The paper introduces STEP, a self-supervised method that learns interpretable, structured embeddings for progressive time series, allowing the state progression and active mode to be read out using polar coordinates.
Highlighted terms show continued research focus across papers