Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts Paper • 2503.16057 • Published 2 days ago • 11
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts Paper • 2503.16057 • Published 2 days ago • 11
Frac-Connections: Fractional Extension of Hyper-Connections Paper • 2503.14125 • Published 4 days ago • 18
Frac-Connections: Fractional Extension of Hyper-Connections Paper • 2503.14125 • Published 4 days ago • 18
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling Paper • 2501.16975 • Published Jan 28 • 26
Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models Paper • 2411.03884 • Published Nov 6, 2024 • 26