Claudio Mayrink Verdun
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1ML×1
Frequent co-authors
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