A latent text-to-image diffusion model

Google Research

Neural Networks: Zero to Hero

Kolmogorov Arnold Networks

PyTorch code and models for the DINOv2 self-supervised learning method.

Tutorials, assignments, and competitions for MIT Deep Learning related courses.

Reference PyTorch implementation and models for DINOv3

Using Low-rank adaptation to quickly fine-tune diffusion models.

NYU Deep Learning Spring 2020

Taming Transformers for High-Resolution Image Synthesis

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

A small package to create visualizations of PyTorch execution graphs

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

pytorch implementation of openpose including Hand and Body Pose Estimation.

🎨 Semantic segmentation models, datasets and losses implemented in PyTorch.

A pedagogical implementation of Autograd

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learna…

VQVAEs, GumbelSoftmaxes and friends

pytorch version of spatial transformer networks

Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models

Dataset to assess the disentanglement properties of unsupervised learning methods

Nvidia GEAR Lab's initiative to solve the robotics data problem using world models

Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)

Pytorch Tutorial, Pytorch with Google Colab, Pytorch Implementations: CNN, RNN, DCGAN, Transfer Learning, Chatbot, Pytorch Sample Codes

Revisions and implementations of modern Convolutional Neural Networks architectures in TensorFlow and Keras

Pretrained bag-of-local-features neural networks

Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"

ISMIR 2020 Tutorial for Metric Learning in MIR