Unitree's UnifoLM is a 6B-parameter world model trained on 2,500 hours of real robot data that predicts only dynamic pixels and optical flow rather than full frames, enabling efficient robot action prediction. This interaction-centric design reduces computational overhead while maintaining high fidelity for embodied control.

A new world model architecture that decouples world-state evolution from rendering: an agent writes executable rules, a persistent engine tracks entities, and a video model renders the output. This separation enables more controllable and interpretable world simulation for embodied agents.

Atlas is a unified spatial intelligence model that reconstructs real scenes from 2–3 images, generates 1440p video along camera paths, and supports real-to-sim robotics workflows using Gaussian Splats to create photorealistic 3D digital twins from phone scans. This represents a significant step toward scalable spatial understanding for physical AI and robot training.

Purpose This study aims to develop a robust vision-guided framework for instance-level recognition and grasp-based classification of metal waste in dense, multi-scale and highly reflective industrial environments, addressing the challenges...

Multi-agent UAV navigation in cluttered environments is challenged by deadlock, starvation-like persistent yielding, oscillation, and unsafe congestion, particularly in narrow passages and dynamically emerging bottlenecks. Existing approaches often rely on...

A method for preference-based learning applied to dexterous robotic manipulation, enabling robots to learn from human preferences in freeform settings. Discussed publicly around September 8, 2026.

TANGO directly predicts 29-DoF joint actions from RGB observations for zero-shot real-world humanoid navigation, enabling coordinated arms, torso, and gait control in cluttered 3D spaces. Presented at CoRL 2026.

Vision-language-action (VLA) models predict robot actions from visual observations and language instructions. These actions are defined in the robot's own 3D coordinate frame, yet most VLAs observe the scene in 2D. This paper proposes robot-centric pointmaps to bridge this gap for vision-language-action models.

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments.

Physics-Regularized Learning for Robust Sim-to-Real Tactile Friction Estimation