# Neural Computers

Source: [Neural Computers](<https://www.sota2.com/research/paper/69d732747d0172140ec76a3d>)

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

Data updated: 2026-04-21T05:00:04.784Z

Authors: Mingchen Zhuge, Changsheng Zhao, Haozhe Liu, Zijian Zhou, Shuming Liu, Wenyi Wang, Ernie Chang, Gael Le Lan, Junjie Fei, Wenxuan Zhang, Yasheng Sun, Zhipeng Cai, Zechun Liu, Yunyang Xiong, Yining Yang, Yuandong Tian, Yangyang Shi, Vikas Chandra, J\\"urgen Schmidhuber

Published: 2026-04-07T20:01:05.000Z

## Abstract

We propose a new frontier: Neural Computers (NCs) that unify computation, memory, and I/O of traditional computers in a learned runtime state. Our long-term goal is the Completely Neural Computer (CNC): the mature, general-purpose realization of this emerging machine form, with stable execution, explicit reprogramming, and durable capability reuse. As an initial step, we study whether elementary NC primitives can be learned solely from collected I/O traces, without instrumented program state. Concretely, we instantiate NCs as video models that roll out screen frames from instructions, pixels, and user actions (when available) in CLI and GUI settings. We show that NCs can acquire elementary interface primitives, especially I/O alignment and short-horizon control, while routine reuse, controlled updates, and symbolic stability remain challenging. We outline a roadmap toward CNCs, to establish a new computing paradigm beyond today's agents and conventional computers.

## 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.

- [Arithmetic Reasoning on CLI Arithmetic 100-problem (held-out pool)](<https://www.sota2.com/research/sota/arithmetic-reasoning-on-cli-arithmetic-100-problem-held-out-pool.md>): Arithmetic Reasoning; CLI Arithmetic 100-problem (held-out pool); Accuracy: 4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.06425>)

[PDF](<https://arxiv.org/pdf/2604.06425.pdf>)
