HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization
Paper
•
2503.04598
•
Published
•
18
•
8
Haoze Wu
WaitHZ
·
AI & ML interests
Modular DL, Complex Reasoning
Recent Activity
commented on
a paper
28 days ago
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid
Normalization
upvoted
a
paper
28 days ago
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid
Normalization
commented on
a paper
28 days ago
HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid
Normalization
Organizations
None yet
WaitHZ's activity
commented
a
paper
28 days ago
upvoted
a
paper
28 days ago
commented
a
paper
28 days ago
upvoted
a
paper
about 2 months ago
upvoted
2
articles
about 2 months ago
Article
How to generate text: using different decoding methods for language generation with Transformers
•
181
Article
You could have designed state of the art positional encoding
•
204
upvoted
2
papers
2 months ago
commented
a
paper
2 months ago
upvoted
2
papers
7 months ago
upvoted
a
paper
9 months ago
authored
a
paper
9 months ago
upvoted
a
paper
12 months ago
A little question about aux_loss
2
#4 opened about 1 year ago
by
WaitHZ
A little question about aux_loss
2
#4 opened about 1 year ago
by
WaitHZ
A little question about aux_loss
2
#4 opened about 1 year ago
by
WaitHZ