Reading Notes

Notes and summaries from reading ML/AI papers (and some blog posts). All credit to the content in the papers and blog posts goes to the original authors.

Building Diffusion Model's theory from ground up

ICLR Diffusion explained blogpost

3 min read · December 24, 2025

2025 · distillation
Weight-sparse transformers have interpretable circuits

Leo Gao OpenAI sparse circuits

6 min read · December 07, 2025

2025 · distillation
Between the Bars: Gradient-based Jailbreaks are Bugs that induce Features

Gradient Based Jailbreaking

2 min read · December 07, 2025

2025 · distillation
Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents

Breakpoint

1 min read · December 07, 2025

2025 · distillation
Fluid Language Model Benchmarking

Fluid model benchmarking

3 min read · December 06, 2025

2025 · distillation