Lessismore
1 mentions across 1 person
Visit ↗All mentions
Ravi Netravali
Recommendedpaper · 2025-08-09
“We introduce LessIsMore, a training-free sparse attention mechanism for reasoning tasks, which leverages global attention patterns rather than relying on traditional head-specific local optimizations.”
Training-Free Sparse Attention via Cross-Head Token Aggregation Cuts Reasoning L ↗