To be useful in more dynamic and less structured environments, robots need artificial intelligence trained on a variety of sensory inputs. Microsoft Corp. today announced Rho-alpha, or ρα, the first ...

Abstract: In this paper, for manipulating flexible objects, e.g., connecting a grounding wire with the power line, in live-maintaining of power substations, we propose an action-level vision-language ...

Vision-language-action models (VLAs) trained on large-scale robotic datasets have demonstrated strong performance on manipulation tasks, including bimanual tasks. However, because most public datasets ...

At CES 2026, Nvidia launched Alpamayo, a new family of open source AI models, simulation tools, and datasets for training physical robots and vehicles that are designed to help autonomous vehicles ...

Instructions for cuda 12.8 (Nvidia 50-- series cards): To get started with loading and running OpenVLA models for inference, we provide a lightweight interface that leverages HuggingFace transformers ...

Safely achieving end-to-end autonomous driving is the cornerstone of Level 4 autonomy and the primary reason it hasn’t been widely adopted. The main difference between Level 3 and Level 4 is the ...

VITRA is a novel approach for pretraining Vision-Language-Action (VLA) models for robotic manipulation using large-scale, unscripted, real-world videos of human hand activities. Treating human hand as ...

NVIDIA is attempting to solve the “black box” problem of self-driving cars by open-sourcing the cognitive architecture behind them. At the NeurIPS conference today, the company released Alpamayo-R1, a ...

Nvidia announced new infrastructure and AI models on Monday as it works to build the backbone technology for physical AI, including robots and autonomous vehicles that can perceive and interact with ...