# Scalable Machines with Intrinsic Higher Mental-State Dynamics

Source: [Scalable Machines with Intrinsic Higher Mental-State Dynamics](<https://www.sota2.com/research/paper/69b8e00c0636e5bf4afbea39>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-18T05:00:04.466Z

Authors: Ahsan Adeel, M. Bilal

Published: 2026-03-13T16:16:50.000Z

## Abstract

Drawing on recent breakthroughs in cellular neurobiology and detailed biophysical modeling linking neocortical pyramidal neurons to distinct mental-state regimes, this work introduces a mathematically grounded formulation showing how models (e.g., Transformers) can implement computational principles underlying awake imaginative thought to pre-select relevant information before attention is applied via triadic modulation loops among queries ($Q$), keys ($K$), and values ($V$).~Scalability experiments on ImageNet-1K, benchmarked against a standard Vision Transformer (ViT), demonstrate significantly faster learning with reduced computational demand (fewer heads, layers, and tokens), consistent with our prior findings in reinforcement learning and language modeling. The approach operates at approximately $\\mathcal{O}(N)$ complexity with respect to the number of input tokens $N$.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.13453>)

[PDF](<https://arxiv.org/pdf/2603.13453.pdf>)