Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world. Recent VLAs and video world-action models lack explicit 3D geometric reasoning.

We present a new robotic foundation model, π0.7, that can enable strong out-of-the-box performance in a wide range of scenarios, following diverse language instructions in unseen environments.

Introduces a dataset and method for learning loco-manipulation policies directly from egocentric human videos without any robot data collection, enabling real-world humanoid deployment in unstructured environments.

CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control

Proposes a unified RL policy that jointly learns force and position control in simulation without force sensors, enabling compliant behaviors and force-aware imitation learning. Includes a force estimator trained as an auxiliary task and integration with Diffusion Policy for contact-rich tasks on quadrupeds and humanoids.

Digital Twin-enabled adaptive robotics: multi-agent reasoning over language, vision, and structured database

Language-conditioned robot manipulation is an emerging field aimed at enabling seamless communication and cooperation between humans and robotic agents by teaching robots to comprehend and execute instructions conveyed in natural language.

Autonomous operation in confined spaces demands robots that can simultaneously navigate tight passages and manipulate objects. However, conventional mobile manipulators are often too large, while compliant soft manipulators are typically too weak.

Semantic–Geometric Task Representations for Bimanual Manipulation From Human Demonstrations to Robot Action Planning

Robots that execute language-conditioned tasks in dynamic environments often rely on feedback only after an action has failed, which can be insufficient when failures involve collisions or workspace conflicts.