Neural Computers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915941615403008 |
|---|---|
| author | Zhuge, Mingchen Zhao, Changsheng Liu, Haozhe Zhou, Zijian Liu, Shuming Wang, Wenyi Chang, Ernie Lan, Gael Le Fei, Junjie Zhang, Wenxuan Sun, Yasheng Cai, Zhipeng Liu, Zechun Xiong, Yunyang Yang, Yining Tian, Yuandong Shi, Yangyang Chandra, Vikas Schmidhuber, Jürgen |
| author_facet | Zhuge, Mingchen Zhao, Changsheng Liu, Haozhe Zhou, Zijian Liu, Shuming Wang, Wenyi Chang, Ernie Lan, Gael Le Fei, Junjie Zhang, Wenxuan Sun, Yasheng Cai, Zhipeng Liu, Zechun Xiong, Yunyang Yang, Yining Tian, Yuandong Shi, Yangyang Chandra, Vikas Schmidhuber, Jürgen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06425 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Neural Computers Zhuge, Mingchen Zhao, Changsheng Liu, Haozhe Zhou, Zijian Liu, Shuming Wang, Wenyi Chang, Ernie Lan, Gael Le Fei, Junjie Zhang, Wenxuan Sun, Yasheng Cai, Zhipeng Liu, Zechun Xiong, Yunyang Yang, Yining Tian, Yuandong Shi, Yangyang Chandra, Vikas Schmidhuber, Jürgen Machine Learning Artificial Intelligence 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. |
| title | Neural Computers |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.06425 |