Stars
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…
A unified framework for 3D content generation.
Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.
A library that uses hardware acceleration to load sequences of video frames to facilitate machine learning training
[NeurIPS 2024] Official implementation of paper "Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers"
Implementation of Classifier Free Guidance in Pytorch, with emphasis on text conditioning, and flexibility to include multiple text embedding models
A C# library to interface with the Game State Integration found in Counter-Strike 2.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Gymnasium extension for DarkSouls III, Elden Ring, and other Souls games
Reinforcement Learning Algorithms Tutorial (Python) from scratch (Mar 2021)
PyTorch Discounted Cumsum with Autograd (CPU + CUDA)
This repository contains code for fine-tuning the LLama3 8b model using Alpaca prompts to generate Java codes. The code is based on a Google Colab notebook.
This allows you to record keyboard and mouse input, and play it back using pynput.
[CVPR2024] NARUTO: Neural Active Reconstruction
Several simple examples for popular neural network toolkits calling custom CUDA operators.
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
Hands-On Machine Learning with C++, published by Packt
[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection