VLA model of NVIDIA’s Alpamayo 1 and Alpamayo1.5, Add visualization, fine-tuning, RL fine-tuning, consistency training.
-
Updated
Mar 22, 2026 - Python
#
alpamayo
Here are 2 public repositories matching this topic...
VLA ≠ VLM. Side-by-side viewer running NVIDIA Alpamayo R1 (vision-language-action) alongside Qwen2.5-VL (vision-language) on the same 44-sec SF dashcam clip at 5 Hz. 220 paired traces. Surfaces what an action-trained model sees that a scene-trained model doesn't, and vice versa.
machine-learning robotics autonomous-vehicles vla self-driving vlm multimodal huggingface qwen vision-language-action end-to-end-driving alpamayo evaluation-harness av-evaluation
-
Updated
May 8, 2026 - HTML
Improve this page
Add a description, image, and links to the alpamayo topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the alpamayo topic, visit your repo's landing page and select "manage topics."