Rhoda AI: scaling web-video pre-training keeps improving real-robot manipulation policies

stepjamUK · x · 2026-09-16

Rhoda AI rigorously tests the belief that scaling web-video pre-training improves downstream robot performance, using Direct Video-Action models (DVA) evaluated on a real industrial manipulation task across model sizes and compute budgets.

Key findings from 200+ hours of real-robot evaluation:

The results support scaling web-video pre-training as a core recipe for robot foundation models.

Related event: Rhoda's Thousands of Trials Confirm Web-Video Pre-training Boosts Real Robots(3 posts)→

Original post →

More from Embodied

Embodied channel →