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.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
Repository Index
47,133 repositories indexed
1–24 of 67 · Most stars
Code and documentation to train Stanford's Alpaca models, and generate the data.
- deep-learning
- instruction-following
- language-model
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Instant neural graphics primitives: lightning fast NeRF and more
🦉 Data Versioning and ML Experiments
- data-science
- machine-learning
- reproducibility
- data-version-control
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
- 3d
- 3d-generation
- image-to-3d
- text-to-3d
COLMAP - Structure-from-Motion and Multi-View Stereo
- structure-from-motion
- multi-view-stereo
- reconstruction
- geometry
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
A collaboration friendly studio for NeRFs
Refine high-quality datasets and visual AI models
Fast and Accurate ML in 3 Lines of Code
Hackable and optimized Transformers building blocks, supporting a composable construction.
Build, Manage and Deploy AI/ML Systems
- machine-learning
- model-management
- ai
- ml
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
- cookiecutter-data-science
- cookiecutter
- cookiecutter-template
- data-science
Infrastructure for continually self‑improving agents
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
- python
- machine-learning
- infrastructure
- reproducible-research
Visual localization made easy with hloc
- deep-learning
- visual-localization
- feature-matching
- image-retrieval
Artificial Intelligence Infrastructure-as-Code Generator.
3D Computer Vision Framework
- computer-vision
- 3d-reconstruction
- photogrammetry
- structure-from-motion
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
- pytorch
- protein-structure
- alphafold2
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.
- 3d-reconstruction
- depth-prediction
- feature-matching
- global-features
Accelerated deep learning R&D