Lisa2 min read
LiSA: Linear Stochastic Attention for Long-Range Visual Modeling
Self-attention has become the standard for modern sequence modeling, enabling Transformers to model long-range dependencies across a wide range of modalities. Despite these advances, its quadratic cost with respect to sequence length remains a significant computational bottleneck.
By Sahar Dastani, Fereshteh Shakeri, Samuel Barbeau, Kunal Mahatha, Ismail Ben Ayed, Herve Lombaert, Christian DesrosiersarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 4, 2026.
Comments
Sign in to join the discussion.