MF, an  XML-based data format developed by the 3MF Consortium, has officially become an ISO standard: ISO/IEC 25422:2025.

Many industrial products—from car bumpers to aerospace panels and medical implants—owe their performance to lightweight, ...

UKAEA 3D prints fusion energy components using Freemelt's eMELT E-PBF machine and Nikon SLM Solutions' SLM280.

Helix is Figure’s advanced Vision-Language-Action (VLA) model, designed to give humanoid robots a deeper understanding of the ...

Captum is a model interpretability and understanding library for PyTorch. Captum means comprehension in Latin and contains general purpose implementations of integrated gradients, saliency maps, ...

3D model-based gaze estimation methods are widely explored because of their good accuracy and ability to handle free head movement. Traditional methods with complex hardware systems (Eg. infrared ...

To address this limitation, this letter proposes 3D-RM Diffusion (3D-RadioDiff), which incorporates the altitude of Autonomous aerial vehicles (AAVs) and environmental topology as key conditioning ...

GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models Zhangyang Qi 1,2*, Zhixiong Zhang 2*, Ye Fang 2, Jiaqi Wang 2 , Hengshuang Zhao 1 * Equation Contribution, Corresponding Authors ...

Several groups hope to develop artificial-intelligence models that can predict how cells behave.

3D-printed tumor models mimic human tissue to improve surgical imaging research by Ashlyn Grotegut, Texas Tech University edited by Sadie Harley, reviewed by Andrew Zinin Editors' notes ...

If models get better at navigating human emotions, those manipulations could become more effective — but much of the issue comes down to the fundamental biases of model training.

Google DeepMind has released a new language model called Gemini Robotics On-Device that can run tasks locally on robots without an internet connection.