JD Kim

FixMatch-pytorch. Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"

MPL-pytorch. Unofficial PyTorch implementation of "Meta Pseudo Labels"

rl_pytorch. Deep Reinforcement Learning Algorithms Implementation in PyTorch

gym-tictactoe-zero. Tic Tac Toe with Alpha Zero method - My first work

UDA-pytorch. An unofficial PyTorch implementation of Unsupervised Data Augmentation

mcts-omok. Omok using MCTS (UCT, PUCT)

custom-claude-code. Python

codex-system-prompts. Unofficial mirror of OpenAI Codex prompt strings — version-tracked, fragment-level. Modeled on Piebald's claude-code-system-prompts.

kabang-knowledge. KakaoBank public-document corpus and manual tau3-style banking knowledge tasks.

oh-my-claude-code. Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.