Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow

Janus-Series: Unified Multimodal Understanding and Generation Models

The dataset for drone based detection and tracking is released, including both image/video, and annotations.

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Tutorial for Multi-UAV (Quadcopters) simulation in Gazebo and Ardupilot.

Documentation of the ETHZ gazebo_motor_model for simulation of propeller-driven aircraft

A pluginlib-based C++ library that interfaces with several vehicle SDK's

Material for lectures on Diffusion models at IE university

A Gradio web UI for Large Language Models with support for multiple inference backends.

Minimal implementation of Vision Transformers (ViT)

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

You like pytorch? You like micrograd? You love tinygrad! ❤️

basic implementation of leader follower system for crazyflies

Flying Swarms of Crazyflie Quadrotors in ROS 2

The Fastest Deep Reinforcement Learning Library

The main firmware for the Crazyflie Nano Quadcopter, Crazyflie Bolt Quadcopter and Roadrunner Positioning Tag.

Python library to communicate with Crazyflie

Training transferable end-to-end quadrotor control policies on a laptop in 18 seconds.

Reference implementation for DPO (Direct Preference Optimization)

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Offline RLHF codebase implementation for "Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback" (ICLR2024)

A curated list of reinforcement learning with human feedback resources (continually updated)

Nvidia TAO (Train, Adapt, Optimize) with STM32Cube.AI Developer Cloud

Implementation of several Generative Adversarial Networks in JAX / Flax

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Lightweight, useful implementation of conformal prediction on real data.

Voxel Airplanes WebGL 3D demo

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Source code for the book Real-Time C++, by Christopher Kormanyos