Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent ...

Explore the Prusa Research Core One Open Source project. Download, modify, and reuse CAD files for innovative 3D printing solutions.

Turn photos into 3D with Meta's SAM 3D, using SAM 2 masks and Gaussian splatting, so you can build assets quickly for ...

Abstract: For open-vocabulary indoor three-dimensional (3D) object detection (OVI3DOD), there is a gap between the image and the point cloud for indoor scenes, especially on distant objects. However, ...

The model, called SHARP, can reconstruct a photorealistic 3D scene from a single image in under a second. Here are some examples.

What if creating high-quality 3D models no longer required expensive software, specialized hardware, or years of expertise? Enter Meta’s SAM 3D, an open source AI tool that promises to provide ...

Who’s interested in a brand new, from-scratch boundary representation (BREP) kernel? How about one that has no topological naming problem, a web-native parametric CAD front end to play with, ...

French AI startup Mistral unveiled its next generation of Mistral models called Mistral 3. The Microsoft (MSFT)-backed company said Mistral 3 includes three state-of-the-art small, dense models (14B, ...

DeepSeek has made widely available its Math-V2 model, which was open-sourced on developer platforms Hugging Face and GitHub, under a permissive licence that allows users to repurpose the model. Held ...

Russian hackers exploit Blender’s Auto Run feature to deliver StealC infostealer via .blend files Malware deployed through CGTrader assets, pulling payloads from Cloudflare Workers domains StealC ...

The China-based AI lab DeepSeek has released a new open-weight model, DeepSeekMath-V2. The model, as per the AI lab, demonstrates strong theorem-proving capabilities in mathematics and achieved ...

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, which is essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely ...