Neural Computers

• URL: http://arxiv.org/abs/2604.06425v1
• Date: Tue, 07 Apr 2026 20:01:05 GMT
• Title: Neural Computers
• Abstract summary: We propose an emerging machine form that unifies computation, memory, and I/O in a learned runtime state.<n>Our long-term goal is the Completely Neural Computer (CNC), with stable execution, explicit reprogramming, and durable capability reuse.<n>CNCs could establish a new computing paradigm beyond today's agents, world models, and conventional computers.
• Score: 86.49306026762082
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a new frontier: Neural Computers (NCs) -- an emerging machine form that unifies computation, memory, and I/O in a learned runtime state. Unlike conventional computers, which execute explicit programs, agents, which act over external execution environments, and world models, which learn environment dynamics, NCs aim to make the model itself the running computer. 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 early 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. These implementations show that learned runtimes can acquire early interface primitives, especially I/O alignment and short-horizon control, while routine reuse, controlled updates, and symbolic stability remain open. We outline a roadmap toward CNCs around these challenges. If overcome, CNCs could establish a new computing paradigm beyond today's agents, world models, and conventional computers.

Related papers

• Computer-Using World Model [58.59112582915026]
  We introduce the Computer-Using World Model (CUWM), a world model for desktop software that predicts the next user interface (UI) state.<n> CUWM first predicts a textual description of agent-relevant state changes, and then realizes these changes visually to synthesize the next screenshot.<n>We evaluate CUWM via test-time action search, where a frozen agent uses the world model to simulate and compare candidate actions before execution.
  arXiv  Detail & Related papers  (2026-02-19T13:48:29Z)
• From RISC-V Cores to Neuromorphic Arrays: A Tutorial on Building Scalable Digital Neuromorphic Processors [0.37863160479533026]
  Digital neuromorphic processors are emerging as a promising computing substrate for low-power, always-on EdgeAI applications.<n>This tutorial paper outlines the main architectural design principles behind fully digital neuromorphic processors.
  arXiv  Detail & Related papers  (2025-11-27T14:14:23Z)
• Watch and Learn: Learning to Use Computers from Online Videos [50.10702690339142]
  Watch & Learn (W&L) is a framework that converts human demonstration videos readily available on the Internet into executable UI trajectories at scale.<n>We develop an inverse dynamics labeling pipeline with task-aware video retrieval, generate over 53k high-quality trajectories from raw web videos.<n>These results highlight web-scale human demonstration videos as a practical and scalable foundation for advancing CUAs towards real-world deployment.
  arXiv  Detail & Related papers  (2025-10-06T10:29:00Z)
• Rulebook: bringing co-routines to reinforcement learning environments [0.688204255655161]
  Rulebook is a compiled language designed to automatically generate the state machine required to interact with machine learning algorithms.<n>It allows users to express programs without needing to be aware of the specific interface required by the ML components.
  arXiv  Detail & Related papers  (2025-04-28T09:34:34Z)
• NNTile: a machine learning framework capable of training extremely large GPT language models on a single node [83.9328245724548]
  NNTile is based on a StarPU library, which implements task-based parallelism and schedules all provided tasks onto all available processing units.<n>It means that a particular operation, necessary to train a large neural network, can be performed on any of the CPU cores or GPU devices.
  arXiv  Detail & Related papers  (2025-04-17T16:22:32Z)
• OscNet: Machine Learning on CMOS Oscillator Networks [0.0]
  We propose a new and energy efficient machine learning framework implemented on CMOS Networks (OscNet)<n>We model the developmental processes of the prenatal brain's visual system using OscNet, updating based on the biologically inspired Hebbian rule.<n> Experimental results demonstrate that Hebbian learning pipeline on OscNet achieves performance comparable to or even surpassing traditional machine learning algorithms.
  arXiv  Detail & Related papers  (2025-02-11T02:32:32Z)
• CNC-Net: Self-Supervised Learning for CNC Machining Operations [49.55380246503274]
  We introduce a pioneering approach named CNC-Net, representing the use of deep neural networks (DNNs) to simulate CNC machines. Our method has the potential to transformative automation in manufacturing by offering a cost-effective alternative to the high costs of manual CNC programming.
  arXiv  Detail & Related papers  (2023-12-15T16:31:17Z)
• Intelligence-Endogenous Management Platform for Computing and Network Convergence [33.45559800534038]
  We present the concept of an intelligence-endogenous management platform for CNCs called emphCNC brain based on artificial intelligence technologies. It aims at efficiently matching the supply and demand with high heterogeneity in a CNC via four key building blocks, i.e., perception, scheduling, adaptation, and governance. It is evaluated on a CNC testbed that integrates two open-source and popular frameworks and a real-world business dataset provided by Microsoft Azure.
  arXiv  Detail & Related papers  (2023-08-07T10:12:15Z)
• End-to-end AI framework for interpretable prediction of molecular and crystal properties [3.8878792624088856]
  The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties.
  arXiv  Detail & Related papers  (2022-12-21T19:27:51Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)

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.