Top Finds

Advanced data science project: multi-language-sentiment-engine

🤖 Analyze and fix code issues automatically with InfCode, an intelligent Code Agent System achieving a 79.4% solution rate using LLMs.

The Local AI Auditor for Manufacturing. Built on Goose & MCP. Zero Hallucination Deterministic Logic Gates.

✨ Colorful animated ASCII banners in your terminal — powered by pyfiglet & rich 🖤

My Bachelor's Thesis: Reviewing the Consistency of Semantical Capabilities of Large Language Models. For documentation see [https://github.com/Fabbernat/Thesis-paper]

Hybrid query-optimization framework for black-box adversarial attacks that dynamically switches from untargeted exploration to targeted exploitation

AI-powered ticket triage system using LLM extraction + embedding search FastAPI backend • Dockerized • Production ready

🏥 Elevate radiology with LuminaMed-AI, generating clear reports for doctors and patients using advanced multi-agent AI technology.

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

A lightweight PyTorch framework for building, training, and documenting deep neural network experiments.

Multi-user AI collaboration workspace with role-based action gating

ML model lifecycle platform - registration, versioning, deployment strategies (blue/green, canary), Flask API, JSON persistence

🔍 Analyze CUDA matrix multiplication performance and power consumption on NVIDIA Jetson Orin Nano across multiple implementations and settings.

🔍 Analyze financial data seamlessly with the AutoGen Financial Analysis System, offering risk assessment and quantitative insights through a multi-Agent framework.

Accelerate autoregressive image generation with Locality-aware Parallel Decoding (LPD). Explore our code and models on GitHub! 🚀🌟

Teacher-forced confidence as a false-belief sensor for language models.

🎤 Control your world with Jarvis, a voice-activated AI assistant that simplifies tasks and enhances productivity.

🤖 Build adaptable AI agents with skill-based systems, enabling efficient context management and seamless integration across any framework.

Web crawler para sitios de documentación — convierte páginas a Markdown limpio usando Playwright, markdownify y Ollama (local) u OpenRouter/OpenCode (cloud)

Data Science project - python-ml-pipeline-complete

Accelerate LLM inference by running speculative decoding in parallel, improving speed without sacrificing exactness or output quality.

🧠 Enhance AI conversations with Cognio, a persistent memory server that retains context and enables meaningful semantic search across sessions.

🔍 Evaluate LLM performance in creative writing tasks, focusing on content generation and response quality across varied prompts and difficulty levels.

🛠 Build and customize LLaMA models easily with LLaMA-Factory, streamlining the training and deployment of large language models.

Personal news intelligence — aggregate AI content from curated sources, score with LLM, serve your own dashboard