Articles Tagged “Vision Language Action”
6 articles found
NVIDIA Alpamayo 2 Super Ships an Open 34B AV Model
NVIDIA released Alpamayo 2 Super for commercial use — a 34B open reasoning model for robotaxis with 360-degree perception and a permissive OpenMDW license.
Gemini Robotics 2 Gives Humanoids Whole-Body Control
Google DeepMind's Gemini Robotics 2 landed July 30 with whole-body humanoid control, multi-robot teamwork, and up to 89.6% gripper accuracy.
NVIDIA GR00T 1.7 Opens Humanoid Robotics to Everyone
NVIDIA and Hugging Face brought Isaac GR00T 1.7 to LeRobot on July 7, connecting 3M robotics developers with 16M AI builders on one open stack.
Open-Source Robotics Leaps Forward: NVIDIA and Hugging Face Join LeRobot
NVIDIA and Hugging Face bring open humanoid models and data tools to the LeRobot library, opening vision-language-action robotics to every lab.
Qwen-Robot Suite Brings Open Embodied AI to Manipulation, World Modeling, and Navigation
Alibaba's Qwen team released three open embodied-AI models for robot manipulation, video world modeling, and vision-language navigation, with public weights and code.
Figure 03 Humanoid Robot Sorts 249,560 Packages in a 200-Hour Run
The Figure 03 humanoid robot ran 200 hours nonstop, sorting nearly 250,000 packages with zero hardware failures, powered by autonomous Helix-02 vision-language-action AI.