G

generative-ai

Generative AI platform that offers you a complete and secure ecosystem, designed to be accessible by all your teams.

🔎 Type @brave in browser address bar to get results from Brave AI

🤖 AI chat & search summaries in Google Search, powered by the latest LLMs

🛒 AI chat & product/category summaries in Amazon shopping, powered by the latest LLMs

Official implementations of "Latent Diffusion Models for Attribute-Preserving Image Anonymization" and "Harnessing Foundation Models for Image Anonymization".

Type @deepseek in browser address bar to get answers from DeepSeek AI

🔎 Type @perplexity in browser omnibox to get results from Perplexity AI

🔎 Type @you in browser address bar to get results from You.com AI

🔎 Type @phind in browser address bar to get results from Phind AI

Lien vers le site : https://class-code.gitlab.io/iagenerative/

Le parcours IAGenerative est un parcours de ressources éducatives en ligne pour expérimenter, questionner et se questionner autour des IA et surtout des IA génératives. Ces ressources ont pour vocation d’explorer le fonctionnement des IA, leurs enjeux et leurs limitations ainsi que leurs usages professionnels. Ces ressources sont destinées à un public d'enseignants, de formateurs, d'éducateurs, de médiateurs ou d'animateurs, mais aussi plus largement au grand public pour toute personne intéressée de découvrir ou de se perfectionner autour des IA génératives.

AI Code Reviewer for GitLab CI — An automated, LLM-powered code-review system that runs inside GitLab CI on every Merge Request. The reviewer analyzes changed files using Azure OpenAI, detects bugs, code smells, risky patterns, and quality issues, and generates structured HTML/JSON reports stored in CI artifacts.

All review logic is contained inside the ci/ folder, and the .gitlab-ci.yml pipeline securely fetches only the MR target branch to perform the analysis. No external servers or deployments required — the entire review happens within GitLab CI.

[2025] Autonomous Claude Code plugin with pattern learning and skill auto-selection. Features 27 specialized agents across 4 collaborative groups, quality control automation, and intelligent task execution without human approval at each step.

Comparação entre Vision Transformers e Métodos Clássicos de Visão Computacional na Segmentação de Exsudatos Lipídicos em Imagens de Retinopatia Diabética. Trabalho de Conclusão de Curso para obtenção de título de bacharel em Engenharia Elétrica na Universidade Federal do Ceará.