Financial Model Engineering — Python code compiles to live Excel formulas

ai42z is an innovative framework designed to transform Large Language Models (LLMs) into autonomous, self-learning AI agents. The framework stands out by enabling AI agents to build and maintain a …

The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web

Enable AI models for video production in the browser

Fully open reproduction of DeepSeek-R1

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

Master programming by recreating your favorite technologies from scratch.

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework

OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones su…

9th Place Solution of Kaggle Global Wheat Detection

WIP: Roadmap to becoming a machine learning engineer in 2020

Freezing generator for pseudo image translation

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

ECCV2020 paper "Whole-Body Human Pose Estimation in the Wild"

Learning to Transfer Texture from Clothing Images to 3D Humans, CVPR 2020

System design patterns for machine learning

A dataset of 15 million CAD sketches with geometric constraint graphs.

Pytorch library for fast transformer implementations

[CVPR2020] Adversarial Latent Autoencoders

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

The fastai book, published as Jupyter Notebooks

L5Kit - https://woven.toyota

A guideline for building practical production-level deep learning systems to be deployed in real world applications.

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

ML and DL related contests, competitions and conference challenges.

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

A collection of loss functions for medical image segmentation