Repositories

lucidrains repositories

402 supported repositories

Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch

Last commit Jan 6, 2021

 (25 stars) (3 forks) (0 indexed issues) (0 open good first issues)

Implementation of ETSformer, state of the art time-series Transformer, in Pytorch

Last commit Aug 26, 2023

 (154 stars) (16 forks) (0 indexed issues) (0 open good first issues)

Implementation of E(n)-Transformer, which incorporates attention mechanisms into Welling's E(n)-Equivariant Graph Neural Network

Last commit Jun 2, 2024

 (226 stars) (31 forks) (0 indexed issues) (0 open good first issues)

Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.

Last commit Apr 21, 2025

 (17 stars) (0 forks) (0 indexed issues) (0 open good first issues)

Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"

Last commit Sep 26, 2023

 (372 stars) (25 forks) (0 indexed issues) (0 open good first issues)

Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch

Last commit Jan 21, 2025

 (25 stars) (0 forks) (0 indexed issues) (0 open good first issues)

Exploration into the proposed architecture from Sapient Intelligence of Singapore 🇸🇬

Last commit Aug 18, 2025

 (75 stars) (8 forks) (0 indexed issues) (0 open good first issues)

Implementation of HS-TasNet, "Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet"

Last commit Apr 23, 2026

 (103 stars) (14 forks) (0 indexed issues) (0 open good first issues)

Implementation of Hierarchical Transformer Memory (HTM) for Pytorch

Last commit Sep 15, 2021

 (76 stars) (6 forks) (0 indexed issues) (0 open good first issues)

Implementation of the Hierarchical Latent Action Model, proposed by Hanjung Kim et al. of Yonsei University

Last commit May 6, 2026

 (16 stars) (0 forks) (0 indexed issues) (0 open good first issues)

Implementation of Humanoid Standing Up, from the paper "Learning Humanoid Standing-up Control across Diverse Postures" out of Shanghai, in Pytorch

Last commit May 3, 2025

 (46 stars) (5 forks) (0 indexed issues) (0 open good first issues)

Implementation of the Hybrid Perception Block and Dual-Pruned Self-Attention block from the ITTR paper for Image to Image Translation using Transformers

Last commit Apr 2, 2022

 (35 stars) (8 forks) (0 indexed issues) (0 open good first issues)

Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch

Last commit Nov 25, 2024

 (55 stars) (2 forks) (1 indexed issue) (1 open good first issue)

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

Last commit Dec 27, 2024

 (654 stars) (55 forks) (0 indexed issues) (0 open good first issues)

Pytorch implementation of MIMO, Controllable Character Video Synthesis with Spatial Decomposed Modeling, from Alibaba Intelligence Group

Last commit Sep 30, 2024

 (135 stars) (7 forks) (0 indexed issues) (0 open good first issues)

Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch

Last commit Oct 10, 2023

 (104 stars) (4 forks) (0 indexed issues) (0 open good first issues)

Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena

Last commit Aug 26, 2023

 (207 stars) (11 forks) (0 indexed issues) (0 open good first issues)

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

Last commit Mar 17, 2022

 (92 stars) (8 forks) (0 indexed issues) (0 open good first issues)

Nim is a statically typed compiled systems programming language. It combines successful concepts from mature languages like Python, Ada and Modula. Its design focuses on efficiency, expressiveness, and elegance (in that order of priority).

Last commit Dec 21, 2022

 (3 stars) (0 forks) (0 indexed issues) (0 open good first issues)

Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind

Last commit Nov 1, 2025

 (136 stars) (7 forks) (0 indexed issues) (0 open good first issues)