LUNA: A Model-Based Universal Analysis Framework for Large Language Models

D Song, X Xie, J Song, D Zhu, Y Huang… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Over the past decade, Artificial Intelligence (AI) has had great success recently and is being
used in a wide range of academic and industrial fields. More recently, Large Language …

Modularizing while training: A new paradigm for modularizing DNN models

B Qi, H Sun, H Zhang, R Zhao, X Gao - Proceedings of the 46th IEEE …, 2024 - dl.acm.org
Deep neural network (DNN) models have become increasingly crucial components of
intelligent software systems. However, training a DNN model is typically expensive in terms …

FATS: Feature Distribution Analysis-Based Test Selection for Deep Learning Enhancement

L Li, C Tao, H Guo, J Zhang… - IEEE Transactions on Big …, 2023 - ieeexplore.ieee.org
Deep Learning has been applied to many applications across different domains. However,
the distribution shift between the test data and training data is a major factor impacting the …