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

CONDITIONAL 1

representative citing papers

Investigating Compositional Reasoning in Time Series Foundation Models

cs.LG · 2025-02-09 · conditional · novelty 6.0

On a benchmark where models train on Fourier components and test on their sums, patch-based Transformers and residual MLP architectures show the strongest compositional generalization, while most standard transformers and linear models fail.

citing papers explorer

Showing 1 of 1 citing paper.

  • Investigating Compositional Reasoning in Time Series Foundation Models cs.LG · 2025-02-09 · conditional · none · ref 6

    On a benchmark where models train on Fourier components and test on their sums, patch-based Transformers and residual MLP architectures show the strongest compositional generalization, while most standard transformers and linear models fail.