MODEL PROFILE · World-action research
DVA
Uses predicted motion and visual changes as part of robot-action generation.
Research organisationRhoda AI
Research approachInverse dynamics
Published year2026
BackboneCausal video model
Overview
Rhoda AI describes a causal video model that predicts the near future, followed by an inverse-dynamics model that translates those predictions into robot actions. NVIDIA groups this formulation with inverse-dynamics approaches.
Source record
- Causal Video Models Are Data-Efficient Robot Policy Learners
- NVIDIA WAM technical synthesis (Moritz Reuss, 15 Jun 2026)
Core research identity and broad method were source-checked as of 2026-11-03. Independent benchmarking, commercial availability, weights and licensing have not been assessed.