haotang1995

self-repair

[ICLR 2024]: Is Self-Repair a Silver Bullet for Code Generation?

sketch-frontend

predicators

Learning for effective and efficient bilevel planning

gym-minigrid

gym-sokoban

Sokoban environment for OpenAI Gym

rl-starter-files

RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code

rl-baselines3-zoo

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

ARC-AGI

The Abstraction and Reasoning Corpus

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

teaching_arithmetic

LAWT

Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)

egos-2000

Envision a future where every student can read all the code of a teaching operating system.

guidance

A guidance language for controlling large language models.

codellama

Inference code for CodeLlama models

mxeval

BetterChatGPT

An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)

openai-python

The official Python library for the OpenAI API

nltk

NLTK Source

python-git-info

A simple project to get information from the git repository of your project

program-synthesis-guided-RL

popgym

Partially Observable Process Gym

Diffusion-LM

Diffusion-LM

AStarNet

Official implementation of A* Networks

TextWorld

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

ChainCoder

📜 [ICML 2023] "Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation", Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, Kevin Wang, Yihan Xi, Dejia Xu, Zhangyang Wang

reflexion

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

awesome-discrete-diffusion-models

A curated list for awesome discrete diffusion models resources.

smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

CodeT