Open-Sora: Democratizing Efficient Video Production for All

Dateset Reset Policy Optimization

Aligning LLM Agents by Learning Latent Preference from User Edits

Benchmarking the Spectrum of Agent Capabilities

This is our own implementation of 'Layer Selective Rank Reduction'

A benchmark for evaluating learning agents based on just language feedback

INTeractive learning via REPresentatIon Discovery

Simple and easily configurable grid world environments for reinforcement learning

A Python package to assess and improve fairness of machine learning models.

Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

The repository contains an ongoing collection of tweets IDs associated with the novel coronavirus COVID-19 (SARS-CoV-2), which commenced on January 28, 2020.

Reinforcement Learning via Latent State Decoding

Navigation data used for Chen and Mooney 2011 and Artzi and Zettlemoyer 2013 (including cleaned up oracle data)

Dynamic Robot Instruction Following

Some hard problems for reinforcement learning.

Connect a ROS-enabled robot to Unity

Code for NAACL 2018 paper "Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information"

Code for SLT 2016 paper on Grapheme-to-Phoneme conversion using attention based encoder-decoder models

(OLD REPO) Line-by-line profiling for Python - Current repo ->

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

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research