GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

TL;DR

GigaBrain-0.5M* is a vision-language-action model that leverages world model-based reinforcement learning to improve multi-step action prediction, demonstrating significant performance gains and reliable long-horizon task execution in robotic manipulation.

Contribution

The paper introduces GigaBrain-0.5M*, integrating world model-based reinforcement learning with a pre-trained VLA model for enhanced cross-task robotic manipulation.

Findings

30% performance improvement on complex tasks

Reliable long-horizon task execution in real-world settings

Effective cross-task adaptation via RAMP

Abstract

Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and weak future anticipation capabilities. In contrast, video world models pre-trained on web-scale video corpora exhibit robust spatiotemporal reasoning and accurate future prediction, making them a natural foundation for enhancing VLA learning. Therefore, we propose \textit{GigaBrain-0.5M*}, a VLA model trained via world model-based reinforcement learning. Built upon \textit{GigaBrain-0.5}, which is pre-trained on over 10,000 hours of robotic manipulation data, whose intermediate version currently ranks first on the international RoboChallenge benchmark. \textit{GigaBrain-0.5M*} further integrates world model-based reinforcement learning via \textit{RAMP} (Reinforcement leArning via world Model-conditioned Policy) to enable robust cross-task adaptation. Empirical results demonstrate that \textit{RAMP} achieves substantial performance gains over the RECAP baseline, yielding improvements of approximately 30\% on challenging tasks including \texttt{Laundry Folding}, \texttt{Box Packing}, and \texttt{Espresso Preparation}. Critically, \textit{GigaBrain-0.5M$^*$} exhibits reliable long-horizon execution, consistently accomplishing complex manipulation tasks without failure as validated by real-world deployment videos on our \href{https://gigabrain05m.github.io}{project page}.