IEEE

Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation

Abstract: In robotic, task goals can be conveyed through various modalities, such as language, goal images, and goal videos. However, natural language can be ambiguous, while images or videos may ...
9to5Mac

Apple’s new AI model recreates 3D objects with realistic lighting effects from a single image

Apple researchers have created an AI model that reconstructs a 3D object from a single image, while keeping reflections, highlights, and other effects consistent across different viewing angles. Here ...
IEEE

Data-Centric and Model-Centric Enhancements for Urban Object Re-Identification

Abstract: In this study we propose an enhanced urban object reidentification pipeline based on the Bag-of-Tricks (BoT) framework. We introduce a variety of contributions at different levels, including ...
GitHub

Angular library for the WebMCP (Web Model Context Protocol) browser API. Expose your Angular application as an AI-agent-ready tool provider using idiomatic Angular patterns.

WebMCP is a W3C Community Group standard that allows web pages to expose structured JavaScript tools to AI agents and assistive technologies via navigator.modelContext. Think of it as turning a ...