Ars Technica

Google’s RT-2 AI model brings us one step closer to WALL-E

On Friday, Google DeepMind announced Robotic Transformer 2 (RT-2), a “first-of-its-kind” vision-language-action (VLA) model that uses data scraped from the Internet to enable better robotic control ...
Ars Technica

Google’s PaLM-E is a generalist robot brain that takes commands

On Monday, a group of AI researchers from Google and the Technical University of Berlin unveiled PaLM-E, a multimodal embodied visual-language model (VLM) with 562 billion parameters that integrates ...
Mena FN

Altumview Launched First Fall Detection Solution Powered By Large Vision-Language AI Model (VLM)

The latest upgrade to AltumView's Sentinare sensor can eliminate false alarms, and solve a long-standing challenge for the senior care industry. VANCOUVER, BC, CANADA, April 16, 2025 /EINPresswire / - ...
GIGAZINE

NVIDIA significantly updates virtual world building tools for robot development and releases visual language model (VLM) to allow robots to recognize the world

Omniverse, a virtual world creation platform that is useful for developing robots, self-driving cars, and more. A new update to Omniverse has been announced to coincide with the international computer ...
VietNamNet

CMC’s Vietnamese AI model ranks Top 12 globally in document understanding

AI transformation is accelerating across Vietnam, with OCR technology playing a key role in digitalizing documents. Photo: Illustration CMC’s research team has announced that its AI model, CATI-VLM, ...