Replace dense cross-attention weights with a balanced transport plan whose nonzero query-key edges are maintained by a multiscale active-set procedure. Solve the coarse token-group problem first, lift its support to the fine token grid, add only edges indicated by local cost or marginal residuals, and warm-start the fine problem from the lifted plan. This should provide a principled sparse attention pattern rather than fixing a global top-k pattern before seeing the transport solution.
Compress a transformer KV cache by selecting actual past tokens whose key or hidden-state columns form a stable basis for all cached tokens. Instead of retaining tokens with the largest attention scores or leverage scores independently, compute rank-revealing pivoting of the leading right-singular-vector matrix and retain its pivot columns, then evaluate attention using the representatives plus an optional low-cost residual correction.
Remove a latent relay or hub token from an attention or graph layer and replace its two-hop influence by direct effective edges between retained tokens. The correction is a normalized rank-one update, so it can preserve hub-mediated communication while reducing the number of stored and processed states.
Use the sharp exponential tail bound to set a local clipping threshold from a desired exceedance probability. Instead of globally clipping activations at a fixed value or percentile, clip each local window at its minimum plus B log(e/delta), where delta is the tolerated fraction of clipped entries.