Records found: 7
NVIDIA's ThinkAct framework introduces a dual-system approach combining vision-language reasoning with reinforced visual latent planning, significantly improving robot manipulation and planning in complex environments.
RoboBrain 2.0 from BAAI integrates vision and language understanding to advance embodied AI in robotics, offering scalable models and superior reasoning for complex tasks.
Embodied AI agents leverage world models to perceive and act in real or virtual environments, enhancing their autonomy and human-like interaction across various industries.
PEVA is a new AI model that predicts egocentric video frames conditioned on detailed full-body motion, improving visual anticipation in embodied systems.
EmbodiedGen is an open-source framework that generates scalable, physically accurate 3D environments tailored for embodied AI simulations, bridging the gap between traditional 3D graphics and robotics-ready assets.
VeBrain introduces a unified multimodal AI framework that combines visual reasoning and robotic control, achieving superior performance in complex real-world robotic tasks.
Gemini Robotics combines cutting-edge AI reasoning with physical world interaction, enabling robots to perform complex tasks with precision and adaptability.