Mason Wang

Notes Index

• DDPM Math

• DDPM Noise Schedules

• DDPM - Reparametrization

• Diffusion Models - UDL Notes

• Gradients - UDL

• Initialization - UDL

• MLP Interpretation - UDL

• Measuring Performance - UDL

• Optimization - UDL

• VAEs - UDL

• Advances in Computer Vision

• Image Formation

• Language Modeling from Scratch

• Linear Image Processing

• Actor Critic

• Approximate Nearest Neighbors

• Approximation Theorem

• Autoencoders

• Autograd

• Backpropagation

• Batchnorm

• Bayes

• Bias Variance Tradeoff

• Biased vs Unbiased Estimates

• Byte Pair Encoding

• Clip Plus GAN

• CNNs

• Chain Rule

• Classifier Free Guidance

• Conditional Independence

• Constrastive Learning

• Convolution

• Covariance

• Cross Entropy

• Denoising Autoencoder

• Diffusion Best Practices

• Discrete Fourier Transform

• Distributed Training

• Double Descent

• Downsampling and Stretching

• Downsampling and Stretching

• Eigenvalues

• Encoder-Decoder Transformers

• Energy-Based Generative Model

• Entropy

• Evolution Strategies

• Fine Tuning

• Fourier Dualities

• Functions

• Gated Activations

• Gaussian Splatting

• Generalization

• Geometric Deep Learning

• Gradients

• Group Theory

• Gumbel Softmax

• Infinitesimals

• Information Theory

• Jensens Inequality

• KL-Divergence

• LLMs

• LSTM

• Large Scale Deep Learning

• Linear Classifiers

• Linked Lists

• Loss Functions

• Masked Image Modeling

• Min-hash

• Mixed Precision

• Momentum, RMSProp, Adam

• Mutual Information

• Neural Scaling Laws

• Normalization

• PAC Bayes

• PCA

• PQMF

• Pink Frequency Profiles

• Pocketed Activation

• Policy Gradient

• Positional Encodings

• Precision and Recall

• Product Quantization

• RLHF

• Random Variables and Probability Distributions

• Rate Distortion Theory

• Real Analysis

• Reconstruction based learning

• Representation Learning

• Running Covariance Algorithms

• SVM

• Similarity-Based Methods

• Speech to Speech Models

• Training

• Transformers

• Transpose Convolution

• UNet

• Uniform Width Sampling

• Wiener Process

• ‘1/f noise’ in music and speech

• Adaptive Preference Aggregation

• AlphaGo

• BERT

• CLIP

• Concept Activation Vectors

• DAC

• DDIM

• Direct Preference Optimization

• DiT

• DiffWave

• Diffusion Models Beat GANs on Image Synthesis

• Diffusion Forcing

• Edify - Image

• Elucidated Diffusion Models

• FLAM: Frame-Wise Language-Audio Modeling

• Fast R-CNN

• Few-Shot Preference-Based RL

• Free Transformer

• Generalized Advantage Estimation

• History Guidance

• HuBERT

• LoRA

• MIDI-DDSP

• Mask-RCNN

• Multi-Source Diffusion Models

• MultiDiffusion

• ODISE

• PixelVAE

• R-CNN

• RLOO

• Re-Bottleneck

• SDEdit

• SIGLIP

• Stemphonic

• Universal Audio Synthesizer Control with Normalizing Flows

• VAR

• W2V-Bert

• WordPiece

• wav2vec

• A Brief Introduction To Information

• A Recipe for Training Neural Networks

• Generative Modeling Using SDEs

• Score-Based Generative Models

• An Interpretation of KL Divergence

• How to write a good paper

• ICML Best Practices

• Julius Advice

• Einsum

• File Systems

• Git

• Hydra

• Lightning

• PyTorch

• Python

• Slurm

• Wandb

• Webdataset