Article

UBTECH releases unified multimodal world model Thinker-WM

Thinker-WM is a unified multimodal world model that jointly models and generates RGB, metric depth, and robot actions through a shared Unified Dynamics Transformer; the same set of parameters supports joint video-action generation, world prediction, policy inference, action-conditioned generation, video-to-action generation, and inverse dynamics.

Part of the event: UBTECH Releases Unified Multimodal World Model Thinker-WM

This page provides a summary and source link only.