Tom B Brown's repositories
rl-teacher
Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
imagenet-stubs
A teeny tiny set of ImageNet-like images for testing pipelines
robustness
Corruption and Perturbation Robustness
unrestricted-adversarial-examples
Contest Proposal and infrastructure for the Unrestricted Adversarial Examples Challenge
ai-and-efficiency
Submissions for AI and Efficiency SOTA's
robust-features-code
Code for "There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits)"
worldmodels.github.io
World Models
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
finetune-transformer-lm
Code and model for the paper "Improving Language Understanding by Generative Pre-Training"
parallel-trpo
A parallel version of Trust Region Policy Optimization
pytorch-openai-transformer-lm
A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
watchdog
Python library and shell utilities to monitor filesystem events.
xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.