I read research papers and rewrite them the way I wish they had been explained to me: intuition first, pictures where they help, and code you can actually run.
The current project is a growing library of diffusion model papers — from the 2020 paper that started it all to the systems behind today’s image and video generators.
The 2020 paper that started the diffusion era. Wreck an image with noise, teach a network to guess the noise, then run the wrecking process backwards. Explained with pictures, almost no maths, and code you can run.
Paper Attention Is All You Need The problem Explain the problem using your own words. Main idea Describe the important concepts, diagrams, and equations. Python implementation import numpy as np def softmax(values): exp_values = np.exp(values - np.max(values)) return exp_values / exp_values.sum() print(softmax(np.array([1.0, 2.0, 3.0]))) What I learned Summarize the practical lessons and link to your complete GitHub project.