Skip to content
All tags

#diffusion-models

2 posts
learningguideReading Berkeley CS189 Introduction to Machine Learning

(Optional) Guide: InfoNCE for Biology, Diffusion Theory, LLM Fine-Tuning + Kaggle | Berkeley CS189 Assignment 5

HW5 is the only Spring 2026 assignment marked optional, due 5/11, the same day as the final. The written part has three pieces: derive InfoNCE gradients and the trade-off in the number of negatives, using scRNA-seq as the setting; prove the optimal denoiser is a conditional expectation and derive the continuity equation; generalize flow matching's straight-line path to arbitrary interpolations. The notebook is a full LLM fine-tuning pipeline: Qwen2.5-0.5B-Instruct is fixed, MMLU machine_learning is converted to chat format, TRL's SFTTrainer does full fine-tuning, accuracy on CS189 exam questions is compared before and after, and predictions on a 169-question test set go to Kaggle, all while guarding against catastrophic forgetting. An official hw5-sol.pdf is provided, covering the written part only.

#berkeley#cs189#course-guide#self-supervised-learning#diffusion-models#fine-tuning#homework
aideep-diveReading Stanford CS230 Deep Learning

Adversarial Robustness and Generative Models: It's Not Nonlinearity, It's Linearity | Stanford CS230 Lecture 4

Researchers initially assumed neural networks are easy to fool because they're nonlinear. That was wrong — Goodfellow's 2014 paper argues the primary cause is their linear nature, and high dimensionality lets every tiny perturbation compound. The second half covers generative models: GANs' three pathologies, and why diffusion sidesteps two of them by adding noise and learning to remove it.

#adversarial-attack#prompt-injection#gan#diffusion-models#stanford-cs230