ROOT: Robust Orthogonalized Optimizer for Neural Network Training
Paper
โข
2511.20626
โข
Published
โข
43
โข
5
hankai
hankaixyz
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
20 days ago
VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse
submitted
a paper
20 days ago
VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse
authored
a paper
about 1 month ago
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
Organizations
None yet
commented
a
paper
about 1 month ago
Seems lagging behind Pangu-1B
๐
๐
5
3
#4 opened 3 months ago
by
hankaixyz
commented
a
paper
almost 2 years ago