Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Claudio Mayrink Verdun

Claudio Mayrink Verdun

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

NLP×1AI×1ML×1

Frequent co-authors

Kaley Brauer1×
Samuel Marks1×

Research Timeline

2026
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

This paper shows that Frontier LLMs can perform multi-step reasoning over filler tokens, and introduces an unsupervised decoding pipeline to recover intermediate values.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.LGEmpiricalRecentJul 3, 2026

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks

This paper shows that Frontier LLMs can perform multi-step reasoning over filler tokens, and introduces an unsupervised decoding pipeline to recover intermediate values.

View →