Inhibitory Cross-Talk Enables Functional Lateralization in Attention-Coupled Latent Memory

• URL: http://arxiv.org/abs/2603.03355v1
• Date: Fri, 27 Feb 2026 08:58:51 GMT
• Title: Inhibitory Cross-Talk Enables Functional Lateralization in Attention-Coupled Latent Memory
• Abstract summary: We present a memory-augmented transformer in which attention serves simultaneously as a retrieval, consolidation, and write-back operator.<n>We partition the memory into lateralized left and right banks coupled through a sign-controlled cross-talk matrix $W_s$, and show that the sign of this coupling is decisive for specialization.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a memory-augmented transformer in which attention serves simultaneously as a retrieval, consolidation, and write-back operator. The core update, $A^\top A V W$, re-grounds retrieved values into persistent memory slots via the Gram matrix $A^\top A$, providing a principled tripartite projection: observation space $\to$ latent memory $\to$ supervised transformation. We partition the memory into lateralized left and right banks coupled through a sign-controlled cross-talk matrix $W_s$, and show that the sign of this coupling is decisive for specialization. Excitatory cross-talk ($s=+1$) causes bank-dominance collapse: one bank monopolises all inputs and $\mathcal{P}_{ct} \to 0.5$, despite lowering task loss. Inhibitory cross-talk ($s=-1$), motivated by the net inhibitory effect of callosal projections in human cortex, actively suppresses contralateral bank activation and achieves saturated specialization ($\mathcal{D}_{sep} = \pm 1.00$, $\mathcal{P}_{ct} \approx 0$). On a controlled symbolic benchmark combining an episodic bijection cipher (requiring associative recall) with a strict arithmetic progression (requiring rule extraction), the inhibitory model reduces cipher-domain loss by $124{\times}$ over the baseline while matching it on the arithmetic domain, confirming that persistent lateralized memory is necessary for episodic recall but not for rule-based prediction.

Related papers

• Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots [9.539275654775706]
  Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown.<n>We show that differential privacy (DP) is treated as a proxy against all of them at once.
  arXiv  Detail & Related papers  (2026-08-27T23:28:08Z)
• Thermodynamics of Learning: A Typed Four-Component Accounting of Memory, Fit, and Value [0.0]
  We show that what a finite learning device has recorded and what will hold value for it on future tasks are not the same quantity.<n>We develop a typed accounting for finite-state learning devices that separates four components: a training-side fit functional $_mathrmfit$, the record-correlation stock $J_D=I(M;D)$, an update-side search ledger $_M$, and an operational capital value $V(M;T,b)$.
  arXiv  Detail & Related papers  (2026-08-13T03:52:23Z)
• Maglev: Sliding Recurrent Memory [8.788753986099902]
  ours is a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention.<n>We train ours with a memory consistency loss that aligns $m_t$ with $m'_t$, allowing inference to use $P$ alone.
  arXiv  Detail & Related papers  (2026-08-03T20:40:49Z)
• Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones [4.847095054351615]
  Linear attention promises constant-time recurrent inference but degrades sharply on associative recall.<n>We introduce Kernelized Linear Attention Activations (KATA), a framework whose feature maps are derived from first principles.<n>We show that rank-one positive semi-definite features offer a favorable capacity--interference tradeoff.
  arXiv  Detail & Related papers  (2026-07-19T21:46:09Z)
• Near-Optimal Regret in Adversarial Kernel Bandits [50.68324062892194]
  We study the adversarial kernel bandit problem, in which the loss at each round is induced by an arbitrary bounded element.<n>Our main result bounds the regret by $widetildeObig(sqrtT, d_*(),log|X|big)$, where $d_*()$ is a widely-adopted notion of effective dimension.
  arXiv  Detail & Related papers  (2026-05-26T06:10:24Z)
• Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval [59.859592671274704]
  How many key-value associations can a $dtimes d$ linear memory store?<n>We show that the answer depends not only on the $d2$ degrees of freedom in the memory matrix, but also on the retrieval criterion.
  arXiv  Detail & Related papers  (2026-05-06T17:53:20Z)
• Scaling Federated Linear Contextual Bandits via Sketching [49.12000877146222]
  This paper proposes Federated Sketch Contextual Linear Bandits (FSCLB)<n>Experiments on both synthetic and real-world datasets show that FSCLB significantly reduces computational and communication costs by over 90 %.
  arXiv  Detail & Related papers  (2026-05-01T08:22:06Z)
• Persistent Memory Through Triple-Loop Consolidation in a Non-Gradient Dissipative Cognitive Architecture [0.0]
  We introduce Deep Memory, a non-gradient persistent memory mechanism operating through a triple-loop consolidation cycle.<n>We demonstrate that discrete expert routing via Mixture-of-Experts (MoE) gating is a causal prerequisite for DM.<n>These results establish DM as a falsifiable mechanism for persistent memory in non-gradient cognitive systems, with functional parallels to hippocampal consolidation.
  arXiv  Detail & Related papers  (2026-03-28T08:29:48Z)
• Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training [0.0]
  Attention scores in transformers are bilinear forms $S_ij = x_itop M x_j / sqrtd_h$ whose maximum magnitude governs overflow risk in low-precision training.<n>We derive a emphrank-aware concentration inequality: when the interaction matrix $M = WQ WKtop$ has rank $r ll d$, tail probabilities for $max_i,j|S_ij|$ decay as $exp(-d22/(
  arXiv  Detail & Related papers  (2026-02-21T14:29:22Z)
• Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality [52.424255020469595]
  Transformers excel through content-addressable retrieval and the ability to exploit contexts, in principle, length.<n>We recast associative memory at the level of probability measures, treating a context as a distribution over unbounded tokens.<n>We show that a shallow measure-theoretic Transformer learns the recall-and-predict map under a spectral assumption on the input densities.
  arXiv  Detail & Related papers  (2026-02-02T09:34:17Z)
• Evolution Strategies at the Hyperscale [57.75314521465674]
  We introduce EGGROLL, an evolution strategies (ES) algorithm designed to scale backprop-free optimization to large population sizes.<n>ES is a set of powerful blackbox optimisation methods that can handle non-differentiable or noisy objectives.<n>EGGROLL overcomes these bottlenecks by generating random matrices $Ain mathbbRmtimes r, Bin mathbbRntimes r$ with $rll min(m,n)$ to form a low-rank matrix perturbation $A Btop$
  arXiv  Detail & Related papers  (2025-11-20T18:56:05Z)
• Burau representation, Squier's form, and non-Abelian anyons [53.92822954974537]
  We introduce a frequency-tunable, two-dimensional non-Abelian control of operation order constructed from the Burau representation of the braid group $B_3$.<n>The sign change of $Delta(omega)$ across the Squier positivity window reveals alternating constructive and destructive interference of causal orders.<n> Numerical simulations confirm both enhancement and suppression regimes, establishing a minimal $B_3$ braid control.
  arXiv  Detail & Related papers  (2025-10-21T00:25:21Z)
• Emergence and scaling laws in SGD learning of shallow neural networks [64.48316762675141]
  We study the complexity of online gradient descent (SGD) for learning a two-layer neural network with $P$ neurons on isotropic Gaussian data.<n>We provide a precise analysis of SGD dynamics for the training of a student two-layer network to minimize the mean squared error (MSE) objective.
  arXiv  Detail & Related papers  (2025-04-28T16:58:55Z)
• ZETA: Leveraging Z-order Curves for Efficient Top-k Attention [22.90397380324185]
  We propose ZETA to enable parallel querying of past tokens for entire sequences.<n>ZETA matches the performance of standard attention on the synthetic textscMulti-Query Associative Recall task.
  arXiv  Detail & Related papers  (2025-01-24T15:33:05Z)
• Weight decay induces low-rank attention layers [8.746774382296008]
  We study the influence of weight decay as well as $L2$-regularization when training neural network models. We verify that the key-query and value-projection matrix products $W_KTW_Q, PW_V$ within attention layers, when optimized with weight decay, indeed induce a significant reduction in the rank.
  arXiv  Detail & Related papers  (2024-10-31T11:04:07Z)
• Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition [71.33787410075577]
  We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses. We propose a new algorithm that attains an $widetildeO(dsqrtHS3K + sqrtHSAK)$ regret with high probability.
  arXiv  Detail & Related papers  (2024-03-07T15:03:50Z)
• SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer [22.77860269955347]
  Pre-training suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms.<n>We propose $mathttSynGhost$, an invisible and universal task-agnostic backdoor attack via syntactic transfer.<n>$mathttSynGhost$ adaptively selects optimal targets based on contrastive learning, creating a uniform distribution in the pre-training space.
  arXiv  Detail & Related papers  (2024-02-29T08:20:49Z)
• Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality [0.0]
  neural networks with a single hidden layer and ReLU activation interpolate data drawn from a radially symmetric distribution with target labels 1 at the origin and 0 outside the unit ball. We prove that a unique radially symmetric minimizer exists, whose weight decay regularizer and Lipschitz constant grow as $d$ and $sqrtd$ respectively. We furthermore show that the weight decay regularizer grows exponentially in $d$ if the label $1$ is imposed on a ball of radius $varepsilon$ rather than just at the origin.
  arXiv  Detail & Related papers  (2022-09-02T17:14:36Z)
• On Submodular Contextual Bandits [92.45432756301231]
  We consider the problem of contextual bandits where actions are subsets of a ground set and mean rewards are modeled by an unknown monotone submodular function. We show that our algorithm efficiently randomizes around local optima of estimated functions according to the Inverse Gap Weighting strategy.
  arXiv  Detail & Related papers  (2021-12-03T21:42:33Z)
• Projection-free Graph-based Classifier Learning using Gershgorin Disc Perfect Alignment [59.87663954467815]
  In graph-based binary learning, a subset of known labels $hatx_i$ are used to infer unknown labels. When restricting labels $x_i$ to binary values, the problem is NP-hard. We propose a fast projection-free method by solving a sequence of linear programs (LP) instead.
  arXiv  Detail & Related papers  (2021-06-03T07:22:48Z)
• GMAT: Global Memory Augmentation for Transformers [45.584411593847406]
  We propose to augment sparse Transformer blocks with a dense attention-based $textitglobal memory$ of length $M$ ($ll L$) Our augmentation has a manageable $O(Mcdot(L+M))$ memory overhead, and can be seamlessly integrated with prior sparse solutions.
  arXiv  Detail & Related papers  (2020-06-05T07:50:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.