Open source model RoboBrain 2.0 will become foundation for humanoid robots
AI model RoboBrain 2.0 can now combine environment perception and robot control in 1 compact system. Specialists already call it the foundation for the future generation of humanoid robots.
RoboBrain supports planning, environment analysis and execution of actions in the real world. At the same time, the model contains only 7 billion parameters. Which makes it easy for integration into existing projects and robotic systems. All source code is available in an open repository on GitHub.
The technical architecture impresses with its capabilities. The system processes images, long video sequences and high-resolution visual data. At the same time, it excellently understands complex text instructions. Visual information passes through a special encoder and projector. And text turns into a unified token stream. Then the decoder performs reasoning, builds plans and determines spatial coordinates.
With such development pace, it’s quite realistic that by 2027 we’ll see mass production of advanced human-like robots.
Autor: AIvengo
For 5 years I have been working with machine learning and artificial intelligence. And this field never ceases to amaze, inspire and interest me.
Tinder launched double dates: AI assembles teams of 4 peopleTinder app launched a double date function that allows users to team up with friends to find pairs. Now you can invite up to 3 friends and together browse profiles of other so-called teams. That have at least 1 match in individual preferences.
New benchmark showed AI failure in Olympic programming tasksA new benchmark LiveCodeBench Pro for evaluating artificial intelligence programming capabilities has appeared. Link in description. It includes the most difficult and fresh tasks from popular competitions. International Olympiad in Informatics and World Programming Championship. Tasks were marked by winners and prize-winners of these competitions themselves.
Data up to 2022 became "pre-nuclear steel" for AI trainingArtificial intelligence, intended to become the locomotive of technological progress, is beginning to slow down its own development. According to The Register, generative models have filled the internet with so much synthetic content that this creates a real technological dead end.
