pith. sign in

Distributional associations vs in-context reasoning: A study of feed-forward and attention layers.arXiv preprint arXiv:2406.03068,

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

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction

cs.LG · 2026-03-10 · unverdicted · novelty 5.0

HTMuon modifies Muon to produce heavier-tailed updates and weight spectra via HT-SR theory, yielding up to 0.98 lower perplexity on LLaMA pretraining and serving as a plug-in for other Muon variants.

citing papers explorer

Showing 2 of 2 citing papers.

  • Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs cs.CL · 2026-04-14 · unverdicted · none · ref 7

    HETA is a new attribution framework for decoder-only LLMs that combines semantic transition vectors, Hessian-based sensitivity scores, and KL divergence to produce more faithful and human-aligned token attributions than prior methods.

  • HTMuon: Improving Muon via Heavy-Tailed Spectral Correction cs.LG · 2026-03-10 · unverdicted · none · ref 3

    HTMuon modifies Muon to produce heavier-tailed updates and weight spectra via HT-SR theory, yielding up to 0.98 lower perplexity on LLaMA pretraining and serving as a plug-in for other Muon variants.