Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
Paper
•
2503.16057
•
Published
•
14
min
qiyang-attn
AI & ML interests
GNN, LLM, Generative Models, MultiModal, Recommendation Models
Recent Activity
authored
a paper
5 days ago
Frac-Connections: Fractional Extension of Hyper-Connections
authored
a paper
about 2 months ago
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
Organizations
None yet