Pith. sign in

REVIEW 1 cited by

Reservoir Transformers

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2012.15045 v2 pith:KKUJ66P5 submitted 2020-12-30 cs.CL

Sheng Shen , Alexei Baevski , Ari S. Morcos , Kurt Keutzer , Michael Auli , Douwe Kiela This is my paper
classification cs.CL
keywords layersmachineperformancereservoirtransformerscomputeconvergencedemonstrate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We demonstrate that transformers obtain impressive performance even when some of the layers are randomly initialized and never updated. Inspired by old and well-established ideas in machine learning, we explore a variety of non-linear "reservoir" layers interspersed with regular transformer layers, and show improvements in wall-clock compute time until convergence, as well as overall performance, on various machine translation and (masked) language modelling tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Quantum Reservoir Computing: Recent Advances and Future Directions

    quant-ph 2026-07 accept novelty 4.0 of 10

    A comprehensive survey of quantum reservoir computing that proposes a common system model, a memory-architecture taxonomy, and resource-accounting standards, concluding that no broad quantum advantage is currently dem...

Pith tools