Emergence of Human to Robot Transfer in Vision-Language-Action Models

What this post added

Demonstrates emergent human-to-robot transfer in VLAs by fine-tuning with human video data, achieving a 2x performance improvement. Investigates the correlation between pre-training data scale/diversity and the effectiveness of human data transfer, showing that increased robot pre-training data improves the model's ability to absorb human data. Visualizes latent embeddings to show emergent alignment between human and robot data representations as pre-training scales.