Name: Mikołaj Pacek
Type: User
Bio: 🚀 ML graduate with NeurIPS-accepted research (LongLLama), specializing in Generative AI, LLMs, RL, CV, TTS, and ML for Robotics. Let's innovate together! 🔍
Mikołaj Pacek's Projects
An attempt of detecting adversarial attacks with GANs.
Interface for autonomous control of a Tello drone. It implements various computer vision techniques and allows for creating missions for a drone.
Neptune + Mrunner on GCP tutorial
Lecture notes for 'Interpretable Machine Learning' at UoW. Summer semester 2020/2021
My programming C-like language interpreter. Its additional feature is counter which allows for counting how many times a variable was accessed.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.
Set of tools for creating learning curriculums for reinforcement learning agents. So far I focused on fighting games like Mortal Kombat and Street Fighter.
Solver for Sokoban (a grid-world logical game) written in Prolog. It is basically a DFS.
Zadanie na IPP
Interface for autonomous control of a robot. It is based on computer vision (mainly aruco markers). There are two missions implemented.
XAI Stories 2.0. eXplainable Artificial Intelligence for Retail Analytics - case studies