arXiv Machine Learning
Finite-Horizon Fisher Memory in Two-Sided Power-Bounded Recurrent Systems
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 24
Naju: A Native Discrete State-Space Model with Independent Retention and Writing for Long-Sequence Memory
arXiv:2607. 21000v1 Announce Type: new Abstract: Long-sequence memory tracking places two opposing demands on a recurrent state: near-lossless retention of stored bindings over long horizons, and active overwriting of stale ones.
arXiv Machine Learning
Jul 23
The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory
arXiv:2607. 19390v1 Announce Type: new Abstract: A recent report finds that orthogonalizing the mLSTM memory matrix at read time (five Newton-Schulz iterations, trained through) substantially improves noisy associative recall.
Hugging Face Trending Papers
Jul 23
Naju: A Native Discrete State-Space Model with Independent Retention and Writing for Long-Sequence Memory
Long-sequence memory tracking places two opposing demands on a recurrent state: near-lossless retention of stored bindings over long horizons, and active overwriting of stale ones. In our diagnostic suite, the strongest efficient baselines tend to solve only one side well.
arXiv Machine Learning
Aug 5
ForgettingOT: Certified Speculative Batching from Sinkhorn's Projective Forgetting
arXiv:2607. 24741v2 Announce Type: replace-cross Abstract: Positive two-marginal entropic optimal transport is solved by a nonlinear, positive, order-preserving, homogeneous Sinkhorn map.
arXiv AI
Jul 7
Hidden-State Privacy Has an Empty Middle
arXiv:2605. 24042v3 Announce Type: replace-cross Abstract: Of $1{,}536$ Gaussian release covariances we tested for single-layer hidden-state privacy, zero achieve both moderate utility and moderate privacy against an adaptive retrieval attacker.
arXiv Machine Learning
Jul 8
Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
arXiv:2505. 11602v3 Announce Type: replace Abstract: Selective State-Space Models (SSMs) such as Mamba have become central to long-sequence modeling.