3 accepted papers
Parameter-Efficient Fine-Tuning (PEFT) methods are crucial for adapting large pre-trained models. Among these, LoRA is considered a foundational approach. Building on this, the influential DoRA method enhances performance by decomposing weight updates into magnitude and direction. However, its under
Efficient optimization is essential for training large language models. Although intra-layer selective updates have been explored, a general mechanism that enables fine-grained control while ensuring convergence guarantees is still lacking. To bridge this gap, we propose \textbf{MGUP}, a novel mecha…
To estimate the brain entropy (BEN) trajectories during aging and distinguish the age and cohort effects. All participants’ data included in this study were downloaded from the PREVENT-AD database. Global BEN and BENs in eight cerebral cortex network architectures were calculated from the rsfMRI dat…