HISA speeds up fine-grained sparse attention indexers via block-then-token hierarchy, delivering substantial speedups at 64K context with no training and quality matching the original DSA on long-context benchmarks.
Hierarchi- cal attention networks for document classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention
HISA speeds up fine-grained sparse attention indexers via block-then-token hierarchy, delivering substantial speedups at 64K context with no training and quality matching the original DSA on long-context benchmarks.