SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
Paper
•
2602.02472
•
Published
•
42
MarcusBryan
MBMorePubs
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 16 hours ago
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
upvoted
a
paper
about 1 month ago
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Organizations
None yet