From the 2 of 5 linked papers with an AI index.
5 papers
LoSA-Net: A Localized and Scale-Adaptive Network for Boundary-Sensitive Prediction of Perineural Invasion in 3D MRI
Youngung Han, Hyunsu Go, Kyeonghun Kim +9
The paper introduces LoSA-Net, a neural network that uses localized self‑attention and scale‑adaptive processing to improve detection of perineural invasion boundaries in 3D contra…
MMA-Former: Multi-Window Mixture-of-Head Attention Transformer for Adaptive PNI Prediction in 3D MRI
Youngung Han, Induk Um, Kyeonghun Kim +9
The paper introduces MMA-Former, a 3D transformer model with a multi-window mixture-of-head attention mechanism, to predict perineural invasion from T1-weighted MRI scans.
GriNNder: Breaking the Memory Capacity Wall in Full-Graph GNN Training with Storage Offloading
Jaeyong Song, Seongyeon Park, Hongsun Jang +4
Full-graph training of graph neural networks (GNNs) is widely used as it enables direct validation of algorithmic improvements by preserving complete neighborhood information. Howe…
LUMINA: Laplacian-Unifying Mechanism for Interpretable Neurodevelopmental Analysis via Quad-Stream GCN
Minkyung Cha, Jooyoung Bae, Jaewon Jung +3
Functional Magnetic Resonance Imaging(fMRI) has now become a classic way for measuring brain activity, and recent trend is shifting toward utilizing fMRI brain data for AI-driven d…
A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs
Hongsun Jang, Jaeyong Song, Changmin Shin +4
The computational and memory demands of large language models for generative inference present significant challenges for practical deployment. One promising solution targeting off…