pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

MSTN: A Lightweight and Fast Model for General TimeSeries Analysis

cs.LG · 2025-11-25 · unverdicted · novelty 5.0 · 2 refs

MSTN introduces a lightweight multi-scale temporal network using convolutional encoding, recurrent or attention-based modeling, and gated fusion to achieve claimed state-of-the-art results on 21 of 27 time series benchmarks while using under 1.1M parameters and fast inference.

citing papers explorer

Showing 1 of 1 citing paper.

  • MSTN: A Lightweight and Fast Model for General TimeSeries Analysis cs.LG · 2025-11-25 · unverdicted · none · ref 11 · 2 links

    MSTN introduces a lightweight multi-scale temporal network using convolutional encoding, recurrent or attention-based modeling, and gated fusion to achieve claimed state-of-the-art results on 21 of 27 time series benchmarks while using under 1.1M parameters and fast inference.