A Humanoid Head Gains Personalized Episodic Memory
German researchers evaluated lightweight personalized memory for sustained human-humanoid interaction.
German researchers evaluated lightweight personalized memory for sustained human-humanoid interaction.
Korean researchers transfer structural motion priors from robot arms to coordinated aerial relay planning.
Action-conditioned predictive models are used to improve generalizable embodied decision-making.
RedFlow converts failed robot actions into localized corrections for vision-language-action policy improvement.
A framework integrates hardware degradation into autonomous planning, mission execution and maintenance decisions.
Researchers map cyber-physical attacks across sensing, world modelling, planning, control and human interaction.
RynnWorld-Teleop combines action conditioning, depth awareness and skeletal structure for egocentric teleoperation prediction.
The work argues embodied operators should be evaluated as holistic deployable components rather than isolated models.
An AMD-accelerated stack spans data-center training, simulation and Ryzen AI edge deployment for VLA manipulation.
Researchers consolidate fragmented human-robot teamwork requirements into six categories and twenty-one subcategories.