ROOT: Robust Orthogonalized Optimizer for Neural Network Training
Paper
โข
2511.20626
โข
Published
โข
169
โข
4
hankai
hankaixyz
AI & ML interests
None yet
Recent Activity
authored
a paper
11 days ago
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
authored
a paper
11 days ago
Revealing the Power of Post-Training for Small Language Models via
Knowledge Distillation
authored
a paper
11 days ago
ROOT: Robust Orthogonalized Optimizer for Neural Network Training
Organizations
None yet
commented
a
paper
11 days ago
Seems lagging behind Pangu-1B
๐
๐
5
3
#4 opened about 2 months ago
by
hankaixyz
commented
a
paper
almost 2 years ago