3 papers
cs.CL2026
Reconsidering Positional Supervision in Masked Diffusion Language Model Training
Mengyu Ye, Keito Kudo, Ryosuke Takahashi +1
Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive language models. They can be view…
cs.CL2026
Suppressing Final Layer Hidden State Jumps in Transformer Pretraining
Keigo Shibata, Kazuki Yano, Ryosuke Takahashi +3
This paper discusses the internal behavior of Transformer language models. Many recent pre-trained models have been reported to exhibit only slight changes in the angular distance…
cs.CL2025
Layerwise Importance Analysis of Feed-Forward Networks in Transformer-based Language Models
Wataru Ikeda, Kazuki Yano, Ryosuke Takahashi +3
This study investigates the layerwise importance of feed-forward networks (FFNs) in Transformer-based language models during pretraining. We introduce an experimental approach that…