lucidrains repositories

Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch

Last commit Aug 4, 2021

Causal Attention with Lookahead Keys

Last commit Sep 26, 2025

Config files for my GitHub profile.

No recent commit data

Last commit Sep 13, 2025

Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch

Last commit Jul 26, 2024

Implementation of LVSM, SOTA Large View Synthesis with Minimal 3d Inductive Bias, from Adobe Research

Last commit Feb 24, 2025

Implementation of MagViT2 Tokenizer in Pytorch

Last commit Jan 12, 2025

Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

Last commit May 3, 2024

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

Last commit Jan 14, 2021

Implementation of the proposed MaskBit from Bytedance AI

Last commit Nov 12, 2024

Implementation of MedSegDiff in Pytorch - SOTA medical segmentation using DDPM and filtering of features in fourier space

Last commit Dec 3, 2023

A repository to house some personal attempts to beat some state-of-the-art for medical datasets

Last commit Nov 20, 2023

PyTorch Framework for Developing Memory Efficient Deep Invertible Networks

Last commit Jan 19, 2020

Implementation of Memformer, a Memory-augmented Transformer, in Pytorch

Last commit Nov 13, 2020

A simple numpy memmap replay buffer for RL and personal use-cases

Last commit May 23, 2026

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

Last commit Jul 17, 2023

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

Last commit Apr 10, 2023

My explorations into editing the knowledge and memories of an attention network

Last commit Dec 8, 2022

Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

Last commit Jul 18, 2023

A variant of Transformer-XL where the memory is updated not with a queue, but with attention

Last commit Jul 31, 2020