# RynnVLA-Latent: Scaling robotic manipulation foundation models with 3D latent actions

- Source: HuggingFace Daily Papers
- Published: 2026-10-25T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/nxbne1psh7e87da7y0onyfq1b
- Original: https://huggingface.co/papers/2610.34356

## Summary

The research team proposes the RynnVLA-Latent framework, which uses RynnLAM to learn continuous, 3D-grounded latent actions from visual changes without requiring native robot control signals. The method processes 30.1K hours of human, robot, and simulation video, generating 745.52M latent action descriptors, then uses flow matching to predict latent action chunks and adapt them to specific embodiments.

## Why it matters

This work converts heterogeneous interaction videos into 3D latent action supervision, offering a reusable data pathway for VLA pretraining that bypasses the scarcity of action annotations.