Winnie Xu's Projects
A reository for various configuration files
Original 2048 Android Implementation
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
ATM Machine
Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"
Blog site
Citizen Science App
Pytorch implementation of COIN, a framework for compression with implicit neural representations 🌸
Lab Exercises and Assignments
Hardware Programming Labs and Projects
Berkeley CS285 Deep RL assignments exploring theory and implementations of model free algorithms.
A tool that processes language data in real time and applies the expectation maximization algorithm to infer medical diagnoses based on symptoms.
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
Configs, setups, etc
Official Pytorch and JAX implementation of "Efficient-VDVAE: Less is more"
Google Foo-Bar Challenge
Go library and CLIs for working with container registries
Google Research
A toolkit for developing and comparing reinforcement learning algorithms.
[WIP] OpenAI Gym Environment for Multi-Agent Learning
A library with extensible implementations of DPO, KTO, PPO, and other human-aware loss functions (HALOs).
Multi-player Hangman console game with server connection infrastructure
Automatic skeletal muscle fibre masking, segmentation, and analysis with ImageJ integration for confocal microscopy image formats.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
An app that runs a generative model for employing personalized solutions based on irregularly sampled habitual usage data to quitting vaping.
Lanczos Network, Graph Neural Networks, Deep Graph Convolutional Networks, Deep Learning on Graph Structured Data, QM8 Quantum Chemistry Benchmark, ICLR 2019
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Models and examples built with TensorFlow
OccuBOT is a python-based web app implementing human and facial recognition with OpenCV, developed at Hack the North 2017