Jerry Huang

Hierarchical Routers for Efficient Top-k Retrieval in Sparse Attention

SafeMoE: Leveraging Unsafe Data to Train Safer, More Informative LLMs

Resona: Improving Context Copying in Linear Recurrence Models with Retrieval

ZETA: Leveraging $Z$-order Curves for Efficient Top-$k$ Attention

Mamba Modulation: On the Length Generalization of Mamba Models

Calibrated Language Models and How to Find Them with Label Smoothing