Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

CUDA accelerated rasterization of gaussian splatting

An open-source framework for training large multimodal models.

Grounding Image Matching in 3D with MASt3R

Audio Large Language Models

Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]

[ICCV 2025] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE

Densely Captioned Images (DCI) dataset repository.

Official implementation of "DGD: Dynamic 3D Gaussians Distillation".

This repository contains an implementation of Shamir's Secret Sharing algorithm tailored for image files.

[gsplat backend] Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

A secure and private voting system based on the Shamir Secret Sharing algorithm.

Local Checkers Game in python, rendered using pygame