DeepSeek-OCR
DeepSeek-OCR is an open-source optical character recognition (OCR) and document-understanding system released by DeepSeek on 20 October 2025 that pioneers a contexts optical compression paradigm: it encodes…
Open Source AI
Explore Open Source AI through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Computer Vision
Articles that also belong to these categories. Counts cover all of Open Source AI.
All articles (444)Large Language Models (165)AI Models (120)Developer Tools (109)Chinese AI (77)AI Agents (53)AI Companies (42)Mixture of Experts (40)AI Infrastructure (37)Multimodal AI (28)NVIDIA (28)Robotics (28)Machine Learning (25)AI Code Generation (23)Natural Language Processing (23)AI Tools & Products (18)Generative AI (18)Meta AI (17)Small Language Models (16)Data & Datasets (15)Video Generation (13)Computer Vision (12)Diffusion Models (12)Image Generation (12)Information Retrieval (12)Google (11)Reasoning Models (11)AI Research (10)Artificial Intelligence (10)AI Hardware (9)AI Inference (9)Microsoft (9)Research Organizations (9)Speech & Audio AI (9)Embodied AI (8)Google DeepMind (8)MLOps (7)Training & Optimization (7)AI for Science (6)Reinforcement Learning (6)Robot Hardware (6)Deep Learning (5)Drug Discovery (5)OpenAI (5)Voice AI (5)AI Benchmarks (4)AI Safety (4)Healthcare AI (4)Model Evaluation (4)Algorithms (3)Conversational AI (3)AI Ethics (2)Agentic Commerce (2)Anthropic (2)Enterprise AI (2)Humanoid Robots (2)Interpretability (2)Mathematics (2)Model Architecture (2)Neural Networks (2)People (2)Physical AI (2)Programming Languages (2)Software Development (2)Transformer Models (2)AI Incidents & Controversies (1)AI Policy (1)AI Policy & Regulation (1)Data Science (1)Music & Audio Generation (1)Quantum Computing (1)Robotics Companies (1)World Models (1)
Showing 1-12 of 12 articles
Detectron2
Detectron2 is an open-source software library for object detection and image segmentation, built on PyTorch and developed by Facebook AI Research (FAIR), the research group now part of Meta AI.
Donut (Model)
Donut (Document understanding transformer) is an OCR-free visual document understanding model introduced by researchers at NAVER CLOVA in the paper "OCR-free Document Understanding Transformer," first posted…
OpenGVLab
OpenGVLab is the open-source organization and project hub for general-vision and multimodal foundation models run by the General Vision group at Shanghai AI Laboratory.
OpenPose
OpenPose is an open-source library for real-time multi-person 2D pose estimation that detects body, foot, hand, and facial keypoints in images and video.
Rerun (rerun.io)
Rerun is an open-source multimodal data stack and visualization system built for robotics, computer vision, and other forms of physical AI.
Sand.ai
Sand.ai is an artificial-intelligence company that develops video-generation models, research software, and commercial creation tools.
V-JEPA
V-JEPA (Video Joint Embedding Predictive Architecture) is a self-supervised video model from Meta AI that learns by predicting masked regions of a video in an abstract latent representation space rather than…
V-JEPA 2
V-JEPA 2 (Video Joint Embedding Predictive Architecture 2) is an open-source video world model released by Meta AI on June 11, 2025 that learns to understand, predict, and plan in the physical world by…
Wan 2.1-VACE
Wan 2.1-VACE (also written Wan2.1-VACE) is an open-weights video creation and editing model released by Alibaba's Tongyi Lab on May 14, 2025 .
YOLOv8
YOLOv8 is a family of one-stage computer vision models released by Ultralytics on January 10, 2023.
olmOCR
olmOCR is an open toolkit and vision-language model from the Allen Institute for AI (Ai2) that turns PDFs and document images into clean, structured plain text and Markdown.