機械学習 · GitHub

優れた自己教師あり手法を集めた厳選リスト

Any3R: Feedforward 3D Reconstruction from Any Camera Type — pinhole, fisheye beyond 180°, 360° panoramas, or any mix, in one forward pass

• One model for every central camera. Thirteen camera models are built in (pinhole, Brown–Conrady, Kannala–Brandt, equidistant, equisolid, stereographic, FOV, MEI, double sphere, EUCM, cylindrical, equirectangular and equirectangular windows), and any other central camera works through its ray field.
• Mixed cameras in one scene. Views from different cameras, with different sizes and fields of view, are reconstructed together into one consistent point cloud.

Updated weekly — until humanity achieves AI4AI. 965 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.

Kedroは、本番環境で利用できるデータサイエンスのためのツールボックスです。ソフトウェアエンジニアリングのベストプラクティスを活用し、再現性、保守性、モジュール性に優れたデータエンジニアリングおよびデータサイエンスのパイプラインを構築できます。

• Project Template - A standard, modifiable and easy-to-use project template based on Cookiecutter Data Science.
• Data Catalog - A series of lightweight data connectors used to save and load data across many different file formats and file systems, including local and network file systems, cloud object stores, and HDFS. The Data Catalog also includes data and model versioning for file-based systems.

Diagrams for visualizing neural network architecture

日本語テキストのためのOCRです。主に日本の漫画を対象としています。

YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

Span-level grounding verification for RAG, code, and tool-grounded AI outputs.

• Returns exact character spans instead of only an answer-level clean/flagged verdict.
• Supports RAG prose, multilingual QA, code-agent answers, and developer-tool output.

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

Open source neural network chess engine with GPU acceleration and broad hardware support.

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

• Python, Command Line, and Docker support
• Built for high performance including multi-GPU and multi-node support

LimiX：汎用知能のための構造化データモデリング能力を解き放つ https://arxiv.org/abs/2609.17488

Vector (and Scalar) Quantization, in Pytorch

A library for scientific machine learning and physics-informed learning

• enables the user code to be compact, resembling closely the mathematical formulation.
• 5 types of boundary conditions (BCs): Dirichlet, Neumann, Robin, periodic, and a general BC, which can be defined on an arbitrary domain or on a point set; and approximate distance functions for hard constraints.

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

BERTとc-TF-IDFを活用して、解釈しやすいトピックを作成します。

Open source tools for computational pathology - Nature BME

A Task-Based Workflow Orchestration Engine

• Task orchestration with Cron-style scheduling and dependency-aware DAGs via the Gust DSL.
• YAML and Shell DAG support for orchestrating shell commands and scripts.