Phil Wang

Working with Attention. It's all we need

Ecosystems: Python, PyTorch, Crystal, Cuda

Projects

NWT-pytorch

Implementation of NWT, audio-to-video generation, in Pytorch

Python - Released: 09 Jun 2021 - 87

anymal-belief-state-encoder-decoder-pytorch

Implementation of the Belief State Encoder / Decoder in the new breakthrough robotics paper from ETH Zürich

Python - Released: 26 Jan 2022 - 62

g-mlp-gpt

GPT, but made only out of MLPs

Python - Released: 20 May 2021 - 86

uformer-pytorch

Implementation of Uformer, Attention-based Unet, in Pytorch

Python - Released: 17 Jun 2021 - 93

hamburger-pytorch

Pytorch implementation of the hamburger module from the ICLR 2021 paper "Is Attention Better Than Matrix Decomposition"

Python - Released: 11 Nov 2020 - 98

firefly-torch

Exploration into the Firefly algorithm in Pytorch

Python - Released: 08 Sep 2024 - 34

marge-pytorch

Implementation of Marge, Pre-training via Paraphrasing, in Pytorch

Python - Released: 24 Aug 2020 - 75

memory-compressed-attention

Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"

Python - Released: 25 Jul 2020 - 71

geometric-vector-perceptron

Implementation of Geometric Vector Perceptron, a simple circuit for 3d rotation equivariance for learning over large biomolecules, in Pytorch. Idea proposed and accepted at ICLR 2021

Python - Released: 13 Jan 2021 - 72

n-grammer-pytorch

Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch

Python - Released: 28 Nov 2021 - 72

ponder-transformer

Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper

Python - Released: 25 Aug 2021 - 78

complex-valued-transformer

Implementation of the transformer proposed in "Building Blocks for a Complex-Valued Transformer Architecture"

Python - Released: 06 Oct 2023 - 57

HTM-pytorch

Implementation of Hierarchical Transformer Memory (HTM) for Pytorch

Python - Released: 14 Sep 2021 - 72

mogrifier

Usable implementation of Mogrifier, a circuit for enhancing LSTMs and potentially other networks, from Deepmind

Python - Released: 05 Jul 2020 - 15

isab-pytorch

An implementation of (Induced) Set Attention Block, from the Set Transformers paper

Python - Released: 26 Oct 2020 - 53

JEPA-pytorch

Implementation of JEPA, Yann LeCun's vision of how AGI would be built, in Pytorch

Python - Released: 21 Aug 2022 - 90

mlp-gpt-jax

A GPT, made only of MLPs, in Jax

Python - Released: 21 May 2021 - 55

ddpm-ipa-protein-generation

Implementation of the DDPM + IPA (invariant point attention) for protein generation, as outlined in the paper "Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models"

Python - Released: 31 May 2022 - 86

pause-transformer

Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount of time on any token

Python - Released: 18 Oct 2023 - 42

omninet-pytorch

Implementation of OmniNet, Omnidirectional Representations from Transformers, in Pytorch

Python - Released: 02 Mar 2021 - 53

multistream-transformers

Implementation of Multistream Transformers in Pytorch

Python - Released: 29 Jul 2021 - 54

molecule-attention-transformer

Pytorch reimplementation of Molecule Attention Transformer, which uses a transformer to tackle the graph-like structure of molecules

Python - Released: 30 Nov 2020 - 58

rela-transformer

Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012

Python - Released: 10 Jan 2022 - 49

cross-transformers-pytorch

Implementation of Cross Transformer for spatially-aware few-shot transfer, in Pytorch

Python - Released: 11 Dec 2020 - 51

compositional-attention-pytorch

Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process with disentangled search and retrieval head aggregation, in Pytorch

Python - Released: 09 May 2022 - 50