Pith. sign in

A large an- notated corpus for learning natural language inference

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

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Parameter-Efficient Transformer Embeddings

cs.CL · 2025-05-04 · conditional · novelty 4.0

A deterministic Fourier expansion of token IDs plus a lightweight shared MLP matches learned embeddings on STS-B at a fraction of the parameter count in small transformers.

citing papers explorer

Showing 1 of 1 citing paper.

  • Parameter-Efficient Transformer Embeddings cs.CL · 2025-05-04 · conditional · none · ref 2

    A deterministic Fourier expansion of token IDs plus a lightweight shared MLP matches learned embeddings on STS-B at a fraction of the parameter count in small transformers.