Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
Paper • 2503.16057 • Published • 15 •
2
Defa Zhu
mathfinder
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Linear-Time Global Visual Modeling without Explicit Attention upvoted a paper 4 months ago
ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation upvoted a paper 4 months ago
mHC: Manifold-Constrained Hyper-ConnectionsOrganizations
None yet