Lily H. Zhang

An R package to generate fake data given an existing dataset

No description provided.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

T5Patches is a set of tools for fast and targeted editing of generative language models built with T5X.

Reference implementation for DPO (Direct Preference Optimization)

Train transformer language models with preference data.

A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

No description provided.

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

High-quality implementations of standard and SOTA methods on a variety of tasks.

Pytorch implementations of generative models: VQVAE2, AIR, DRAW, InfoGAN, DCGAN, SSVAE

The implementation of "Learning Deep Transformer Models for Machine Translation"

DenseNet implementation in Keras

Code for the paper, "Distribution Augmentation for Generative Modeling", ICML 2020.

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

DomainBed is a suite to test domain generalization algorithms

Manifold-learning flows (ℳ-flows)

Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

Google Research

Pytorch implementation of β-VAE

Tensorflow implementation for prodLDA and NVLDA.

Playing Atari Breakout with Q-learning

Analyzing food price data collected from on-the-ground contributors.

A quick analysis on legislation proposed in previous sessions in Maryland and California.

Predicting the status of wells across Tanzania

A Khan Academy Project-based Interview Question