pith. sign in

Attention is all you need

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it

fields

cs.LG 2 cs.CL 1

years

2021 2 2020 1

clear filters

representative citing papers

Scaling Laws for Autoregressive Generative Modeling

cs.LG · 2020-10-28 · accept · novelty 7.0

Autoregressive transformers follow power-law scaling laws for cross-entropy loss with nearly universal exponents relating optimal model size to compute budget across four domains.

Scaling Laws for Transfer

cs.LG · 2021-02-02 · unverdicted · novelty 6.0

Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Scaling Laws for Autoregressive Generative Modeling cs.LG · 2020-10-28 · accept · none · ref 28

    Autoregressive transformers follow power-law scaling laws for cross-entropy loss with nearly universal exponents relating optimal model size to compute budget across four domains.