MaximeVandegar/Papers-in-100-Lines-of-Code resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2865 stars · 255 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A curated collection of 63+ machine learning research papers implemented from scratch in roughly 100 lines of Python/PyTorch each. It serves as an educational resource for understanding core algorithms like GANs, VAEs, diffusion models, NeRF, and deep reinforcement learning.

Use cases

• learn how GANs work by reading minimal code
• understand diffusion models implementation from scratch
• study deep Q-learning for Atari in a small codebase
• implement NeRF in a few lines of PyTorch
• find concise reference implementations of classic ML papers
• teach deep learning concepts with minimal examples

When to choose

• you want to understand the core math of a paper without framework overhead
• you need a compact reference implementation for study or teaching
• you are learning PyTorch through real research code

When to avoid

• you need production-ready, optimized, or feature-complete implementations
• you need maintained libraries with APIs and documentation
• you need scalable training pipelines for large datasets

Facets

learning-resource · maturity active

deep-learning machine-learning reinforcement-learning llm-training deep-learning machine-learning education tutorials artificial-intelligence python papers pytorch educational minimal-implementations generative-models diffusion-models gans nerf reinforcement-learning meta-learning

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MaximeVandegar/Papers-in-100-Lines-of-Code")