Skip to content
LatestDefenceResearchIndustryConsumer
Latest

InternVLA-A1.5

Robot AI model

A vision-language-action model for robots that the authors pre-trained on recordings of human gameplay.

Description from arXiv Robotics (cs.RO)

Stories

  • 10 November 2026

    Pretraining on human gameplay raised a robot model's LIBERO success by 4.65 points

Share this profile

LinkedInXBlueskyWhatsAppEmail
DroneNews.org
AboutContactPrivacy policyRSS feed