Yingfa Chen

StateX: Enhancing RNN Recall via Post-training State Expansion

Sparsing Law: Towards Large Language Models with Greater Activation Sparsity

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity

Stuffed Mamba: Oversized States Lead to the Inability to Forget

Sparsing Law: Towards Large Language Models with Greater Activation Sparsity

Stuffed Mamba: State Collapse and State Capacity of RNN-Based Long-Context Modeling