Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models
Caner Erden
Dynamic Rank Reinforcement Learning (DR-RL) approximations rely on static rank assumptions, limiting their flexibility across diverse linguistic contexts. Our method dynamically mo…
cs.LG2025
Q-Sat AI: Machine Learning-Based Decision Support for Data Saturation in Qualitative Studies
Hasan Tutar, Caner Erden, Ãmit Åentürk
The determination of sample size in qualitative research has traditionally relied on the subjective and often ambiguous principle of data saturation, which can lead to inconsistenc…