Sinks are equivalent to hard attention switches that zero out outputs and are cheaper than diagonal patterns when self-communication is allowed, closing the gap between oversmoothing prevention needs and what sinks provide.
What are you sinking? a geometric approach on attention sink
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
-
Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
Sinks are equivalent to hard attention switches that zero out outputs and are cheaper than diagonal patterns when self-communication is allowed, closing the gap between oversmoothing prevention needs and what sinks provide.