🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
TranslatedRepo for BenCao [original name: HuaTuo (华驼)], Instruction-tuning Large Language Models with Chinese Medical Knowledge.
Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
This package contains the original 2012 AlexNet code.
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
- gat
- graph-attention-networks
- attention-mechanism
- self-attention
A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
Open-source AI video style cloning for 2D animation. Give it a reference video or YouTube link; Claude Code or Codex agents rebuild its pacing, shots and transitions as a new original animation.
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
The original code from the DeepMind article + my tweaks
Repository containing common 3D test models in original format with original source if known and obj mesh
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
Open-source AI video replacement workflow by TEIN. Combine depth maps, SAM segmentation, face meshes, and audio processing to replace characters and objects with Seedance. Includes a local web UI to prepare inputs, review masks, preview generations, and export with original audio.
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.
- resnet
- resnet20
- resnet32
- resnet44
Whisper command line client compatible with original OpenAI client based on CTranslate2.
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
A Vulkan reimplementation of NVIDIA's DLSS 5 Neural Rendering network, bit-exact against the original.
Translate EPUB books using Large Language Models while preserving the original text. The translated content is displayed side-by-side with the original, creating bilingual books perfect for language learning and cross-reference reading.
Collection of useful machine learning codes and snippets (originally intended for my personal use)
Java API for Natural Language Generation. Originally developed by Ehud Reiter at the University of Aberdeen’s Department of Computing Science and co-founder of Arria NLG. This git repo is the official SimpleNLG version.
- simplenlg
- natural-language-generation
- nlg
- realiser
The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.
GRU4Rec is the original Theano implementation of the algorithm in "Session-based Recommendations with Recurrent Neural Networks" paper, published at ICLR 2016 and its follow-up "Recurrent Neural Networks with Top-k Gains for Session-based Recommendations". The code is optimized for execution on the GPU.