Skip to content
View karimluna's full-sized avatar
5 followers · 13 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report karimluna

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
karimluna/README.md

Hi👋, I am Karim Luna

Motivation

I work on control, optimization, and approximation of dynamic systems, for example in the study of how resource-constrained units can cooperate toward goals none of them could reach alone. My current interest frontiers are approximation of dynamical systems, world models, and multi-agent control.

Pinned Loading

  1. imprimer imprimer Public

    A platform that reduces prompt engineering effort and improves LLM output control using feedback🔁, reinforcement learning and constraint retention

    Python

  2. mpc-and-rl-for-a-battery-thermal-system-management mpc-and-rl-for-a-battery-thermal-system-management Public

    (Thesis). The application of Model Predictive Control (MPC) and Reinforcement Learning (RL) to Battery Thermal Management System of an Electrical Vehicle (EV) with a Ion-Lithuim battery

    Python 9 2

  3. tiny-grpo tiny-grpo Public

    Tiny GRPO in Go: a minimal reinforcement learning load balancer that learns real-time traffic routing with just 16 parameters and no critic

    Go

  4. madus madus Public

    🐿Madus: A production-ready multi-agent framework that understands text, figures, and tables in complex PDFs to answer natural language questions

    Python 1

  5. automated-optical-inspection automated-optical-inspection Public

    Automated inspection in a microservice for metal detection failure using Go, React and Python for high inference latency

    Python

  6. langchain-ai/langgraph langchain-ai/langgraph Public

    Build resilient agents.

    Python 44.2k 7.6k