ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models
Paper
•
2410.09637
•
Published
•
2
•
2
Nandan Kumar Jha
nandan523
AI & ML interests
Privacy and security of LLMs, Cryptographically-secure machine learning, Efficient nonlinearity in neural networks.
Organizations
None yet
nandan523's activity
commented
a
paper
1 day ago