pith. sign in

On the role of attention masks and layernorm in transformers

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

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Attention Drift: What Autoregressive Speculative Decoding Models Learn

cs.LG · 2026-05-11 · unverdicted · novelty 6.0

Drafter models in speculative decoding suffer progressive attention drift caused by monotonically growing hidden-state magnitudes along the residual path; post-norm plus per-state RMSNorm reduces this drift and improves acceptance length up to 2x on perturbed templates and 1.18x on long-context data

citing papers explorer

Showing 1 of 1 citing paper.

  • Attention Drift: What Autoregressive Speculative Decoding Models Learn cs.LG · 2026-05-11 · unverdicted · none · ref 22

    Drafter models in speculative decoding suffer progressive attention drift caused by monotonically growing hidden-state magnitudes along the residual path; post-norm plus per-state RMSNorm reduces this drift and improves acceptance length up to 2x on perturbed templates and 1.18x on long-context data