OpenVLA: Robot actions as language: fused DINO+SigLIP → Llama → 256-bin action tokens
Click any block in the architecture to see what it does, the math behind it, and the exact source lines. Then walk one sample end-to-end and stress-test yourself with the debug lab.
VisionFused DINOv2 + SigLIP
BackbonePrismatic VLM (Llama-2 7B)
Actions256 bins → last vocab tokens
StateNone (no proprio encoder)
Click a stageMath cardSample stepperDebug trace
Upstream: https://arxiv.org/abs/2406.09246 · code snapshot openvla/openvla @ c8f03f4 · MIT
Mental model
The ideas that make this code readable
Layer-by-layer math
Every formula links to the source that implements it
Follow one sample
Tensor flow
Shapes must agree across every stage
| Stage | Input | Output | Op | Note |
|---|
Debug lab
Pick the symptom, work one boundary at a time
Code excerpts
Only the lines these notes point at, from the upstream repository at the pinned commit. Gaps are marked.
Select a file
Knowledge check
Click a question to reveal the answer