← Search

Ruan Silva

2 accepted papers

2026

Rethinking Thinking Tokens: LLMs as Improvement Operators

ICML 2026poster

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length, token/compute cost, and answer latency. We ask: Can current models…

Cited by 0SourceScholar
2025

BTS: Harmonizing Specialized Experts into a Generalist LLM

EMNLP 2025

We present Branch-Train-Stitch (BTS), an efficient and flexible training algorithm for combining independently trained large language model (LLM) experts into a single, capable generalist model. Following Li et al., we start with a single seed language model which is branched into domain-specific (e

Cited by 0SourcePDFScholar