by Chenyang Song Papers
2 papers found
Conference
BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
Chenyang Song, Weilin Zhao, Xu Han et al.
COLM 2025paperarXiv:2507.08771
1
citations
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
Yuqi Luo, Chenyang Song, Xu Han et al.
ICML 2025arXiv:2411.02335
16
citations