Tag
Researchers introduce the Unified Hand Action Space (UHAS), a representation enabling a single policy to control robotic hands with different kinematic structures and numbers of fingers, advancing cross-embodiment dexterous manipulation.
Introducing ASPIRE, a framework for robots to continuously evolve a library of skills through evolutionary search and distillation, enabling efficient sim-to-real and cross-embodiment transfer with up to 10x reduction in transfer learning tokens. The full stack is open-sourced.
Kairos is a native world model framework for Physical AI that learns from diverse experiences using a cross-embodiment data curriculum, maintains persistent states with hybrid temporal attention, and supports efficient deployment on server and consumer hardware.
This paper introduces a retrieval-augmented vision-language-action policy that eliminates per-task fine-tuning by using pre-trained models with indexed demonstrations, enabling efficient cross-embodiment generalization and task adaptation at test time.
This paper introduces World-Language-Action (WLA) models, embodied foundation models that jointly predict textual subtasks, subgoal images, and robot actions from text, images, and robot states, achieving state-of-the-art multi-task and long-horizon learning in simulated and real-world environments.
OmniHumanoid is a framework that enables scalable cross-embodiment video generation by factorizing motion transfer and embodiment-specific adaptation, using unpaired data and branch-isolated attention to reduce interference.