Memory ideas

External memories, state compression, retrieval-style read/write policies and calibrated stopping rules.

2 ideas found

Status: Beats tuned baseline Category: Memory ML: Attention Clear all

✓✓ Beats tuned baseline 2026

Resolving Landmark Bottleneck

Compress a directed graph into a small set of landmark vertices while guaranteeing that every node receives a distinct restricted adjacency signature. Use these signatures as structural positional features and as the only graph-to-token interface for a graph transformer, reducing landmark-mediated connectivity from O(n^2) to O(ns).

Useful6/10

Difficulty5/10

Novelty7/10

Memory Memory Scalability Accuracy

Paper: Localization and metric dimension for families of highly structured digraphs arXiv:2607.05152

✓✓ Beats tuned baseline 2026

Boundary-Compressed Approximate Pruning

Use an approximate decision diagram to select a structured subset of neurons, channels, attention heads, or attention edges when their quadratic interactions are sparse or inverse-sparse. Merge states that agree on a local interaction boundary and accept a tunable epsilon loss in the pruning objective, obtaining a representation whose size is linear in model width for fixed accuracy tolerance.

Useful6/10

Difficulty6/10

Novelty7/10

Memory Memory Scalability Generalization

Paper: Convexification of mixed-integer quadratic optimization via decision diagrams arXiv:2608.22815