Stars
Python programs, usually short, of considerable difficulty, to perfect particular skills.
Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELS
Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"
Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"
Automatic architecture search and hyperparameter optimization for PyTorch
[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
Actually Robust Training - Tool Inspired by Andrej Karpathy "Recipe for training neural networks". It allows you to decompose your Deep Learning pipeline into modular and insightful "Steps". Additi…
Benchmarking the Spectrum of Agent Capabilities
Simplifying reinforcement learning for complex game environments
A list of awesome and popular robot learning environments
Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Fast and memory-efficient exact attention
Gradient descent is cool and all, but what if we could delete it?
a simple and scalable agent for training adaptive policies with sequence-based RL
Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch
A Python-embedded modeling language for convex optimization problems.
A collection of 1000+ survey papers on Natural Language Processing (NLP) and Machine Learning (ML).
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKT…
Awesome resources on normalizing flows.
Continual Reinforcement Learning in 3D Non-stationary Environments
A Survey on multimodal learning research.
Python code for "Probabilistic Machine learning" book by Kevin Murphy
Code for visualizing the loss landscape of neural nets