Alpamayo 2 Super is a 34B-parameter foundation model designed to tackle multiple autonomous vehicle (AV) development tasks. It combines a 32B VLM backbone with a 2B diffusion expert.
Explainability Subcard
Intended Task/Domain:
Advanced Driver Assistance System
Model Type:
Transformer
Intended Users:
Developers and researchers working on autonomous vehicle systems for end-to-end perception, reasoning, and motion planning in autonomous driving software.
Output:
Types: Text. Formats: Text: String, Trajectory: Vector
Describe how the model works:
This Vision-Language-Action (VLA) model uses a transformer-based VLM backbone for processing multimodal inputs and a diffusion-based action decoder for generating outputs, enabling end-to-end perception, reasoning, and motion planning for autonomous vehicles.
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:
Not Applicable
Technical Limitations and Mitigation:
The Model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text, producing socially unacceptable or undesirable text.
Verified to have met prescribed NVIDIA quality standards:
Yes
Performance Metrics:
Accuracy (Top-1), F-1 Score, Throughput & Latency
Potential Known Risks:
This model may [describe potential failure mode based on model type]
Terms of Use/Licensing:
None