Aspire
Model Overview
Aspire is a undisclosed-parameter model developed by NVIDIA. Released on 2026-07-01.
📊 Quick Specs
| Specification | Value |
|---|---|
| Parameters | undisclosed |
| Task | other |
| Modality | text, image, multimodal |
| License | Other/Custom |
| Type | open-weights |
✨ Key Features
- Code-as-Policy Paradigm: Translates task goals into executable Python control programs for interpretable, modular robot behaviors
- Closed-Loop Execution Engine: Exposes per-primitive execution traces (perception, grasp candidates, trajectory data, contact dynamics) for failure diagnosis
- Continually Expanding Skill Library: Automatically extracts and indexes validated code repairs into a persistent library of reusable skills
- Evolutionary Search for Task & Code Optimization: Systematically generates and debugs task sequences and control programs
- Zero-Shot Long-Horizon Generalization: Adapts rapidly to unseen manipulation and household tasks without fine-tuning model weights
🔗 Resources
- Hugging Face: Aspire
- Paper: arXiv
- Website: Project Page
📜 License & Access
Other/Custom — See repository for specific license details.
Key Features
Code-as-Policy Paradigm: Translates task goals into executable Python control programs for interpretable, modular robot behaviors
Closed-Loop Execution Engine: Exposes per-primitive execution traces (perception, grasp candidates, trajectory data, contact dynamics) for failure diagnosis
Continually Expanding Skill Library: Automatically extracts and indexes validated code repairs into a persistent library of reusable skills
Evolutionary Search for Task & Code Optimization: Systematically generates and debugs task sequences and control programs
Zero-Shot Long-Horizon Generalization: Adapts rapidly to unseen manipulation and household tasks without fine-tuning model weights
You might also want to compare
Verified Sources
Tags
Model Specs
Parameters
Undisclosed
Context Window
undisclosed
License
Other/Custom
Deployment
Resources & Links
Curator Notes
Partially enriched via migration on 2026-07-25. Manual review recommended.
Compare Specs
Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.
Compare Model