tracked author

Jingkai Zhou

MiniMax Sparse Attention coauthor with MiniMax and Hangzhou Dianzi University affiliation. A LinkedIn search result matches this name, school and MiniMax context, but no open homepage/GitHub/X evidence was found with enough confidence.

1 archived notes X: not-found

Related Notes

按论文归档时间排序,展示该作者在本站已经出现的材料。

Jun 24, 2026

MiniMax Sparse Attention

MiniMax Sparse Attention (MSA) 是 MiniMax M3 的长上下文技术核心:它在 GQA (Grouped Query Attention,分组查询注意力) 之上增加轻量 Index Branch,为每个 query token 和每个 GQA group 选择少量 KV blocks,再由 Main Branch 对被选 block 做精确 softmax attention;论文的强证据在于 109...

2606.13392-minimax-sparse-attention-m3 Sparse AttentionLong ContextMoE Architecture