34 articles · Last covered
On Day 5 of AI Week, AGIBOT shifts focus from model intelligence to operational infrastructure with a zero-code platform designed to eliminate the engineering bottleneck in humanoid rollouts.
As "world models" become the dominant paradigm in robotics, the industry is grappling with a term that means everything and nothing. We map out the competing visions from LeCun, NVIDIA, 1X, and Tesla.
Researchers from Tsinghua and Peking University have introduced LATENT, a system that enables the Unitree G1 humanoid to perform high-speed tennis rallies by learning from "imperfect" human motion data and applying corrective residual actions.
A joint team from BIGAI and Unitree has unveiled OmniXtreme, a unified control policy that enables humanoid robots to perform diverse extreme motions—from backflips to breakdancing—without the need for task-specific overfitting.
Physical Intelligence (Pi) has unveiled Multi-Scale Embodied Memory (MEM), a hybrid architecture that combines short-term video encoding with long-term textual summarization to help robots master long-horizon tasks like kitchen cleaning and in-context error recovery.
NVIDIA has released SONIC, a generalist humanoid controller trained on 100 million frames of motion data, aiming to replace manual reward engineering with a scalable "System 1" foundation for whole-body movement.
A new full-stack framework from HKUST and Shanghai AI Lab allows humanoid robots to acquire complex athletic skills like basketball and reactive fighting directly from human videos—no manual reward engineering required.
Humanoid has unveiled KinetIQ, a multi-layered AI architecture designed to orchestrate entire robot fleets across retail, industrial, and home environments using a cross-timescale approach.
In a deep dive on the Robo Papers podcast, 1X Director of Evaluations Daniel Ho explains how "imagination" via video generation is allowing humanoids to perform zero-shot tasks with minimal robot-specific training data.
NVIDIA GEAR Lab has unveiled DreamZero, a 14-billion parameter World Action Model (WAM) that uses video diffusion to grant robots physical "imagination," enabling zero-shot task completion and rapid adaptation across different robotic embodiments.
Google DeepMind has launched Project Genie, an experimental tool powered by the Genie 3 world model that creates interactive 3D environments from text and images. Beyond gaming, the technology serves as a cornerstone of DeepMind’s strategy to solve the robotics data bottleneck and achieve physical AGI.
Generalist AI's chief scientist argues that the next leap in robotics won't come from internet text, but from scaling the 'reflexive' intelligence of physical interaction.
