[CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.

RynnBrain: Open Embodied Foundation Models

Streaming speech recognition running natively and in the browser. A pure Rust implementation of Mistral's Voxtral Mini 4B Realtime model using the Burn ML framework.

A LLM trained only on data from certain time periods to reduce modern bias

Synthetic data for computer vision. An open source toolkit using Blender and Python.

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Official inference framework for 1-bit LLMs

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Grandmaster-Level Chess Without Search

Box64 - Linux Userspace x86_64 Emulator with a twist, targeted at ARM64, RV64 and LoongArch Linux devices

CUDA accelerated rasterization of gaussian splatting

[3DV'25] 3D Reconstruction with Spatial Memory

CUDA accelerated rasterization of gaussian splatting

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small langua…

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Simple MPL-2.0-licensed C++ geometry processing library.

Python bindings for xatlas

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

Instant neural graphics primitives: lightning fast NeRF and more

Mesh parameterization / UV unwrapping library

The official PyTorch implementation of Google's Gemma models

lightweight, standalone C++ inference engine for Google's Gemma models.

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Bringing the 3D geospatial ecosystem to Unity

Bringing the 3D geospatial ecosystem to Omniverse

Bringing the 3D geospatial ecosystem to Unreal Engine