AI RESEARCH
Locality Does Not Imply Reachability: Boundary Repair in Block-Sparse Causal Attention
arXiv CS.LG
•
ArXi:2606.02680v1 Announce Type: new Sparse causal attention is usually described by sequence locality: nearby tokens should remain easy to access, while distant tokens may be dropped to reduce cost. This paper studies a mismatch between sequence locality and attention-graph reachability. In fixed block causal attention, two adjacent tokens can be disconnected in the attention graph at every depth.