Steven H. Wang

realtime, confidence-varying trajectory prediction for "Probabilistically Safe Robot Planning with Confidence-Based Human Predictions". RSS '18

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

output village coordinates

LLMs from scratch

CUAD (NeurIPS 2021)

Universal Basic Chat

No description.

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Transformer related optimization, including BERT, GPT

Dataset for NAACL 2021 paper: "QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization"

⚡ Building applications with LLMs through composability ⚡

Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

No description.

Tensorflow 2 implementation of Causal-BERT

Virtual Adversarial Training (VAT) techniques in PyTorch

No description.

No description.

No description.

No description.

No description.

Level up Roam with power user features. Automation, keyboard nav, dictionary, live preview and more.

Demonstrating the new automatic package recursion facility in sphinx.ext.autosummary version 3.1

Tooling

PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.

No description.

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

My restic backup solution using Backblaze B2 storage, systemd timers (or cron) and email notifications on failure.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

CHAI's imitation repo + benchmarking against SB GAIL

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

Neural MMO - A Massively Multiagent Game Environment

building off of pomonam/NoisyNaturalGradient.

TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC"

📈 TensorFlow + Matplotlib as TF ops

VGG16 models for CIFAR-10 and CIFAR-100 using Keras

ROS wrapper for pedestrian prediction.

An implementation of KFAC for TensorFlow

Pytorch Implementation of paper "Noisy Natural Gradient as Variational Inference"

No description.

variants of Inverse Reinforcement Learning

the TCPdump network dissector

No description.

No description.