Replace the usual random or elementwise-positive linear-attention feature map with a rank-one positive-semidefinite feature map derived from query and key vectors. For normalized inputs, the resulting kernel is the squared inner product, which is nonnegative and gives a geometrically structured interference pattern that is better suited to associative recall than an arbitrary low-rank feature map.
Replace token-by-token KV storage after an SSM or recurrent encoder with an online allocate-on-novelty cache. A new slot is created only when the incoming key is sufficiently dissimilar from every stored key; otherwise the incoming value is merged into its nearest slot, so repeated or redundant content does not grow the cache.
Replace ordinary per-channel or per-token KV quantization with a structured orthogonal transform followed by blockwise 3-bit quantization. Use a normalized Walsh-Hadamard transform and small SO(4) rotations to spread outliers across coordinates, quantize the transformed vectors, and exploit orthogonality to rotate queries and attention outputs so unquantized attention remains mathematically equivalent.
Attach a certificate to a cached transformer KV state or recurrent latent state and refresh it only while its predicted certificate remains inside a latency-contracted admissible region. The controller uses a bound on certificate drift to guarantee that the state will remain admissible throughout the next sampling, communication, and execution delay, reducing unnecessary recomputation while exposing a measurable refresh boundary.
Replace a global attention truncation rule with a per-query local-tail budget. For each query token, retain nearby or high-priority keys until the estimated discarded interaction strength is below a target epsilon; this uses the paper's central distinction between local tail mass and the extensive norm of the discarded operator. The resulting attention pattern can allocate long-range computation only to tokens whose local tail is large.
Replace coordinatewise rounding of activation or embedding vectors with nearest-point quantization in a learned full-rank lattice. Learn an affine transform that makes the empirical activation region more isotropic, while regularizing the lattice covering density so it does not become inefficient as dimension grows.