Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2603.25636 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911546613956608 |
|---|---|
| author | Yang, Chengshuai |
| author_facet | Yang, Chengshuai |
| contents | Designing a computational imaging system -- selecting operators, setting parameters, validating consistency -- requires weeks of specialist effort per modality, creating an expertise bottleneck that excludes the
broader scientific community from prototyping imaging instruments. We introduce spec.md, a structured specification format, and three autonomous agents -- Plan, Judge, and Execute -- that translate a one-sentence
natural-language description into a validated forward model with bounded reconstruction error. A design-to-real error theorem decomposes total reconstruction error into five independently bounded terms, each linked
to a corrective action. On 6 real-data modalities spanning all 5 carrier families, the automated pipeline matches expert-library quality (98.1 +/- 4.2%). Ten novel designs -- composing primitives into chains from 3D
to 5D -- demonstrate compositional reach beyond any single-modality tool. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25636 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Designing Any Imaging System from Natural Language: Agent-Constrained Composition over a Finite Primitive Basis Yang, Chengshuai Computer Vision and Pattern Recognition 68U10, 65F22, 94A08 I.4.5; I.2.2; J.3 Designing a computational imaging system -- selecting operators, setting parameters, validating consistency -- requires weeks of specialist effort per modality, creating an expertise bottleneck that excludes the broader scientific community from prototyping imaging instruments. We introduce spec.md, a structured specification format, and three autonomous agents -- Plan, Judge, and Execute -- that translate a one-sentence natural-language description into a validated forward model with bounded reconstruction error. A design-to-real error theorem decomposes total reconstruction error into five independently bounded terms, each linked to a corrective action. On 6 real-data modalities spanning all 5 carrier families, the automated pipeline matches expert-library quality (98.1 +/- 4.2%). Ten novel designs -- composing primitives into chains from 3D to 5D -- demonstrate compositional reach beyond any single-modality tool. |
| title | Designing Any Imaging System from Natural Language: Agent-Constrained Composition over a Finite Primitive Basis |
| topic | Computer Vision and Pattern Recognition 68U10, 65F22, 94A08 I.4.5; I.2.2; J.3 |
| url | https://arxiv.org/abs/2603.25636 |