RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded
Overview
This research presents RynnVLA-Latent, a framework that enables scalable pretraining of robotic manipulation policies by learning 3D-grounded latent actions from heterogeneous interaction videos. The method avoids reliance on native robot controls and leverages visual transitions, future-feature prediction, and camera-motion decoupling to capture control-relevant motion. The results show strong performance on multiple benchmarks, including LIBERO, LIBERO-Plus, VLABench, and RoboTwin 2.0, with success rates exceeding those of competing methods in several real-world tasks.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · latent-action descriptors: 745520000 other · trajectory count
“al transitions without requiring native robot controls. By combining residual future-feature prediction, camera-compensated 3D-flow supervision, and camera-motion decoupling, RynnLAM encourages representations that capture control-relevant motion rather than appearance changes alone. We apply RynnLAM to 30.1K hours of human, robot, and simulation videos, producing 745.52M latent-action descriptors. RynnVLA-Latent the”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T19:48:09.327Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T19:47:57.503Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalRynnVLA-Lat, Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions
This research presents RynnVLA-Latent, a framework that enables scalable pretraining of robotic manipulation policies by learning 3D-grounded latent actions from heterogeneous interaction videos. The method avoids reliance on native robot controls and leverages visual transitions, future-feature prediction, and camera-motion decoupling to capture control-relevant motion. The results show strong performance on multiple benchmarks, including LIBERO, LIBERO-Plus, VLABench, and RoboTwin 2.0, with success rates exceeding those of competing methods in several real-world tasks.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).