mlsanityData to 14 Oct 2026

Neural Computers

arXiv 2604.06425 ↗First posted 7 Apr 2026cs.LG cs.AIcited by 3

Not on the map. Why?

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.

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

27 of 110 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2021Program Synthesis with Large Language Modelscited by 3,637
  7. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  8. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  9. 2018World Modelscited by 1,513
  10. 2016Progressive Neural Networkscited by 1,361
  11. 2016HyperNetworkscited by 1,027
  12. 2022A Generalist Agentcited by 808
15 more
  1. 2014Neural Turing Machinescited by 644
  2. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  3. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 238
  4. 2025Video models are zero-shot learners and reasonerscited by 220
  5. 2018Deep Learning: A Critical Appraisalcited by 217
  6. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 186
  7. 2015Neural Programmer-Interpreterscited by 101
  8. 2018Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractionscited by 85
  9. 2019A Differentiable Programming System to Bridge Machine Learning and Scientific Computingcited by 83
  10. 2019Estimating Risk and Uncertainty in Deep Reinforcement Learningcited by 70
  11. 2015On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Modelscited by 55
  12. 2023Finetuning Offline World Models in the Real Worldcited by 41
  13. 2025A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directionscited by 34
  14. 2025NeuralOS: Towards Simulating Operating Systems via Neural Generative Modelscited by 19
  15. 2018One Big Net For Everythingcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  2. 2026A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Executioncited by 0
  3. 2026World models of environment, agent and joint agent-environment systemscited by 0