Skip to content

Author

Jaeho Lee

We have 1 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

PARTREP: Learning What to Repeat for Decoder-only LLMs

A lightweight gate is trained that predicts high-NLL tokens from early-layer hidden states, enabling token selection during mid-prefill via early exit, motivated by the hypothesis that less predictable tokens are less recoverable from surrounding context and therefore benefit more from late-position repetition.

Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim et al. · 0 citations