← Search

Martin Menten

2 accepted papers

2026

Efficient numeracy in language models through single-token number embeddings

ICML 2026spotlight

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or extensive reasoning chains, either weakening the numerical …

Cited by 4SourceScholar
2026

Step-resolved data attribution for looped transformers

ICML 2026poster

We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for $\tau$ recurrent iterations to enable latent reasoning. Existing training-data influence estimators such as TracIn yield a single scalar score that aggregates over all…

Cited by 0SourceScholar