Apprentissage automatique · GitHub

Une liste sélectionnée d'excellentes méthodes d'apprentissage auto-supervisé

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.

:octocat: Machine Learning for Cyber Security

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 est une boîte à outils pour la data science prête pour la production. Il s’appuie sur les bonnes pratiques du génie logiciel pour vous aider à créer des pipelines de data engineering et de data science reproductibles, maintenables et modulaires.

• 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

Outil de reconnaissance optique de caractères (OCR) pour les textes en japonais, principalement destiné aux mangas japonais.

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

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 : libérer les capacités de modélisation des données structurées pour une intelligence généraliste 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. 🔥 🔥 🔥

S’appuie sur BERT et c-TF-IDF pour créer des sujets faciles à interpréter.

Open source tools for computational pathology - Nature BME