A rigorously controlled study finds that adding smoothness regularization and chunk-aware auxiliary supervision to a compact ...

Figure AI has unveiled HELIX, a pioneering Vision-Language-Action (VLA) model that integrates vision, language comprehension, and action execution into a single neural network. This innovation allows ...

Learn what Vision-Language Models (VLMs) are, how they work, and why they're changing computer vision, multimodal AI, and ...

Intelligent dual-arm robot launched by HD Hyundai Robotics at FIX 2026 runs on an in-house proprietary VLA AI model rather ...

Kyutai’s REKI is a 2.4B vision-language-action model trained on public data, scoring 90.4 on LIBERO-Plus with built-in memory ...

Foundation models have made great advances in robotics, enabling the creation of vision-language-action (VLA) models that generalize to objects, scenes, and tasks beyond their training data. However, ...

What if a robot could not only see and understand the world around it but also respond to your commands with the precision and adaptability of a human? Imagine instructing a humanoid robot to “set the ...

In the previous article, "The Big Picture of Physical AI," we broke down physical AI in the narrow sense into three areas: ...

Eka Robotics may be the first robotic arm that is actually good at picking a wide range of objects up, and it is so smooth ...

Hugging Face Inc. today open-sourced SmolVLM-256M, a new vision language model with the lowest parameter count in its category. The algorithm’s small footprint allows it to run on devices such as ...