Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts Paper • 2503.16057 • Published Mar 20, 2025 • 14 • 2
Frac-Connections: Fractional Extension of Hyper-Connections Paper • 2503.14125 • Published Mar 18, 2025 • 22 • 5
Frac-Connections: Fractional Extension of Hyper-Connections Paper • 2503.14125 • Published Mar 18, 2025 • 22 • 5
