Redesign Mixture-of-Experts Routers with Manifold Power Iteration Paper • 2606.12397 • Published 23 days ago • 89
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings Paper • 2606.07502 • Published 28 days ago • 99
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Paper • 2602.02472 • Published Feb 2 • 48
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss Paper • 2512.23447 • Published Dec 29, 2025 • 100