AI Briefing#vla-model
The latest AI and developer news about #vla-model, with the original source and a short summary.
The latest AI and developer news about #vla-model, with the original source and a short summary.
Google unveiled 'Gemini Robotics ER 2,' which supports robots' high-level reasoning and real-time tasks.
OpenBMB has released an open-source Embodied AI model series for robot manipulation and tracking.
This post covers the concept and key technical directions of Robot Foundation Models (RFM), robots that perform tasks by directly interacting within physical environments.
We look at the two core technical directions of Robot Foundation Models (RFM), which go beyond LLMs in virtual worlds to interact with the physical environment.
NVIDIA and Hugging Face are collaborating to integrate Isaac GR00T 1.7 and Isaac Teleop into LeRobot, increasing accessibility for robot development.
Qwen-RobotManip is a VLA foundation model with outstanding generality, trained on 38,100 hours of large-scale data through data alignment techniques.
NVIDIA has unveiled new physical AI agentic technologies to accelerate autonomous driving, robotics, and vision AI research.
Qwen-VLA is a general-purpose VLA model that goes beyond visual understanding to perform continuous robot actions and trajectory prediction.
NVIDIA has unveiled an integrated AI-powered workflow and the Isaac platform that support everything from simulation to real-world robot deployment.
NVIDIA has revealed how to build AI agents that operate in physical environments using DGX Spark and Reachy Mini.
Hugging Face's LeRobot v0.4.0 has been released, introducing large-scale dataset support and new VLA models.
SmolVLA, an open-source 450M-scale robotics VLA model that can run on consumer hardware, has been released.
Hugging Face is building a community-driven LeRobot dataset ecosystem to secure generalization for robots.
Physical Intelligence's general-purpose robot control model π0 has been integrated into Hugging Face LeRobot.