tracked author

Yushi Bai (白雨石)

IndexCache first author and HiLS-Attention author. Homepage identifies Yushi Bai (白雨石) as a Tsinghua PhD student advised by Juanzi Li and records GLM-5 architecture contributions; the paper marks IndexCache as work completed during a Z.ai internship. High-confidence X is linked from the homepage.

2 archived notes X: high Homepage GitHub X

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。

归档 Jul 14, 2026

IndexCache: Accelerating Sparse Attention via Cross Layer Index Reuse

用 loss guided layer search 或 multi layer distillation 划分 Full / Shared 层，跨层复用 top k positions 并跳过最多 75% 的 DSA indexer 计算。

待审阅 2603.12201-indexcache-cross-layer-index-reuse Sparse Attention Long Context Serving Runtime

归档 Jul 09, 2026

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

HiLS Attention 用 landmark 压缩键、熵偏置与分层 softmax 训练 chunk 选择器，使 8K 训练的 345M 模型在 4M RULER 单针检索仍得 96 分，并在 512K 单 H800、batch size 1 的同 Triton 基线上将 prefill 与 decode 分别加速 13.5 倍和 15.7 倍。

待审阅 2607.02980-hils-attention-infinite-context Sparse Attention Long Context