HiRAE: Hierarchical Representation Autoencoding with Residual Budgets Paper • 2609.37775 • Published 3 days ago • 17
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression Paper • 2609.36322 • Published 4 days ago • 99
ICA Lens: Interpreting Language Models Without Training Another Dictionary Paper • 2606.11722 • Published Jun 10 • 18
Redesign Mixture-of-Experts Routers with Manifold Power Iteration Paper • 2606.12397 • Published Jun 10 • 91
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings Paper • 2606.07502 • Published Jun 5 • 100
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