Article

LY-GWM-RoboCasa-Human300: Prediction-Guided Action Selection with a Graph Dynamics Model

LY-GWM-RoboCasa-Human300 combines a Human300-fine-tuned GR00T-N1.5 action generator, an action-conditioned graph dynamics model, and a binary state-reward scorer; at inference it samples 4 action chunks and executes the candidate with the highest predicted-state reward.

Part of the event: Technical Report Released on Graph Dynamics Model Policy for Prediction-Guided Action Selection

This page provides a summary and source link only.