# Neural Computers

arXiv: https://arxiv.org/abs/2604.06425 · HTML: https://mlsanity.com/paper/2604.06425/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 110 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Matrix-game 2.0: An open-source real-time and streaming interactive world model](https://mlsanity.com/paper/2508.13009/) (2025)
- [Neural Programmer-Interpreters](https://mlsanity.com/paper/1511.06279/) (2015)
- [Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions](https://mlsanity.com/paper/1802.04730/) (2018)
- [A Differentiable Programming System to Bridge Machine Learning and Scientific Computing](https://mlsanity.com/paper/1907.07587/) (2019)
- [Estimating Risk and Uncertainty in Deep Reinforcement Learning](https://mlsanity.com/paper/1905.09638/) (2019)
- [On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models](https://mlsanity.com/paper/1511.09249/) (2015)
- [Finetuning Offline World Models in the Real World](https://mlsanity.com/paper/2310.16029/) (2023)
- [A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions](https://mlsanity.com/paper/2501.16150/) (2025)
- [NeuralOS: Towards Simulating Operating Systems via Neural Generative Models](https://mlsanity.com/paper/2507.08800/) (2025)
- [One Big Net For Everything](https://mlsanity.com/paper/1802.08864/) (2018)

## Built on by (most cited first, 3 of 3)

- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution](https://mlsanity.com/paper/2607.10021/) (2026)
- [World models of environment, agent and joint agent-environment systems](https://mlsanity.com/paper/2608.20401/) (2026)

## Abstract (arXiv)

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.