FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models
Paper
•
2602.08818
•
Published
•
2
Mogens From
Kuchenpferd
·
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes
updated
a collection
2 months ago
EuroEvalReasoning
Organizations
