Scales a latent dynamics action model to 1B parameters by ingesting diverse embodied datasets into a unified training pipeline for generalist robot policies.

Jointly predicts future RGB frames, 3D pointmaps, DINO semantics, and actions within a unified world-action model. Can be deployed flexibly as a VLA, full world-action model, or hybrid from a single checkpoint.

An ECCV 2026 paper that converts a single static closed-state image into a simulation-ready articulated asset using video diffusion for joint hypothesis generation, requiring no motion data. Enables articulated object reconstruction without dynamic observations.

Proposes a new agent architecture that unifies digital and physical (embodied) action spaces, supporting human-state trajectories with explicit handling of consent, uncertainty, and reversibility for safer human-robot interaction.

Introduces a unified hand action space that enables seamless cross-embodiment transfer for dexterous manipulation policies across different robot hands.

Soft gripper systems have inherent flexibility and remarkable interactivity security. However, balancing load-bearing capacity, deformation, complexity, and adaptability in a single gripper remains a substantial challenge.

Pre-trained on 1 million hours of human video, Dyna-2 demonstrates scaling laws for world-action models across four orders of magnitude on human data, with emergent scaling on unseen robot data and joint video + action objectives enabling cross-embodiment transfer.

Vision-Language-Action (VLA) models have shown remarkable success in robotic tasks like manipulation by fusing a language model's reasoning with a vision model's 3D understanding. However, their high computational cost remains...

We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulation tasks in unseen environments out-of-the-box, and (2) rapidly adapting to new tasks with minimal demonstrations through efficient fine-tuning.

Explicit task reasoning empowering robotic manipulation