Alexy Skoutnev Alexyskoutnev

🌙

Building AI

Achievements

alexyskoutnev /README.md

Project	⭐ Stars	Stack / Notes
TWIN – Writes the game it plays: World Model For ARC-AGI-3 (Ph.D)	Stars	LLM agents · World models
MOEvo – Pareto-evolving coding-agent harnesses on multi-objectives (Ph.D)	Stars	Evolution
Loan Processing System – Bank statement parser & loan decision engine	Stars	React · LLM · Banking
builD-chatGpT – Making a LLM funny from scratch (WIP)	Stars	Python · PyTorch
SecurityGPT – AI red-team assistant	Stars	LLM · PyTorch
QTOS – Quadruped trajectory optimization (Ph.D.)	Stars	Python · C++ · Docker
PRELUDE – Robust perception for legged robots (Ph.D.)	Stars	PyTorch · C++ · CV

TWIN-ARC-AGI-3 TWIN-ARC-AGI-3 Public

TWIN: Test Time World Model Inference

Python 7
Quadruped-Trajectory-Optimization-Stack Quadruped-Trajectory-Optimization-Stack Public

Quadruped Trajectory Optimization Stack (QTOS) is an optimization framework for legged locomotion that autonomously generates full-body trajectory plans across challenging terrains.

Python 28 7
Awesome-Research Awesome-Research Public

An curated compilation of research papers spanning Deep Learning, Machine Learning, Reinforcement Learning, and Robotics that I have personally read and highly recommend

3
research-skills research-skills Public

Ten Claude Code skills for writing an ML paper, abstract to rebuttal. Recipes, axioms, and mechanical checklists reverse-engineered from papers that got in.

Python 1