ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
Paper
•
2412.14711
•
Published
•
15
Ziteng Wang
thuwzt
AI & ML interests
None yet
Recent Activity
authored
a paper
7 days ago
Efficient Backpropagation with Variance-Controlled Adaptive Sampling
authored
a paper
7 days ago
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
upvoted
a
paper
13 days ago
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
Organizations
None yet
thuwzt's activity
upvoted
2
papers
13 days ago