Defa Zhu

mathfinder's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 days ago

Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts

Paper • 2503.16057 • Published 4 days ago • 14

upvoted a paper 6 days ago

Frac-Connections: Fractional Extension of Hyper-Connections

Paper • 2503.14125 • Published 7 days ago • 19

upvoted a paper about 2 months ago

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

Paper • 2501.16975 • Published Jan 28 • 27

upvoted 2 papers 4 months ago

Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models

Paper • 2411.03884 • Published Nov 6, 2024 • 28

Ultra-Sparse Memory Network

Paper • 2411.12364 • Published Nov 19, 2024 • 23

upvoted a paper 6 months ago

Hyper-Connections

Paper • 2409.19606 • Published Sep 29, 2024 • 23