Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network
(52 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Repositories
lucidrains repositories
lucidrains/g-mlp-gptPython
GPT, but made only out of MLPs
(89 stars) (9 forks) (0 indexed issues) (0 open good first issues)
lucidrains/g-mlp-pytorchPython
Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch
(431 stars) (58 forks) (0 indexed issues) (0 open good first issues)
lucidrains/gaia2-pytorchPython
Implementation of the world model architecture for self driving out of Wayve
(61 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch
(101 stars) (4 forks) (0 indexed issues) (0 open good first issues)
Implementation of GateLoop Transformer in Pytorch and Jax
(92 stars) (10 forks) (0 indexed issues) (0 open good first issues)
Toy genetic algorithm in Pytorch
(56 stars) (4 forks) (0 indexed issues) (0 open good first issues)
Implementation of a framework for Genie2 in Pytorch
(157 stars) (13 forks) (0 indexed issues) (0 open good first issues)
Implementation of GenMimic, "From Generated Human Videos to Physically Plausible Robot Trajectories"
(18 stars) (0 forks) (0 indexed issues) (0 open good first issues)
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
(77 stars) (13 forks) (0 indexed issues) (0 open good first issues)
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs
(1,941 stars) (107 forks) (0 indexed issues) (0 open good first issues)
A Pytorch implementation of Global Self-Attention Network, a fully-attention backbone for vision tasks
(94 stars) (7 forks) (0 indexed issues) (0 open good first issues)
lucidrains/glom-pytorchPython
An attempt at the implementation of Glom, Geoffrey Hinton's new idea that integrates concepts from neural fields, top-down-bottom-up processing, and attention (consensus between columns), for emergent part-whole heirarchies from data
(196 stars) (27 forks) (0 indexed issues) (0 open good first issues)
Unofficial implementation of GotenNet, new SOTA 3d equivariant transformer, in Pytorch
(67 stars) (3 forks) (0 indexed issues) (0 open good first issues)
A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch
(130 stars) (4 forks) (0 indexed issues) (0 open good first issues)
Implementation of Graph Transformer in Pytorch, for potential use in replicating Alphafold2
(238 stars) (19 forks) (0 indexed issues) (0 open good first issues)
Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
(104 stars) (9 forks) (0 indexed issues) (0 open good first issues)
Implementation of the dynamic chunking mechanism in H-net by Hwang et al. of Carnegie Mellon
(79 stars) (2 forks) (0 indexed issues) (0 open good first issues)
Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning
(166 stars) (22 forks) (0 indexed issues) (0 open good first issues)
Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones
(199 stars) (20 forks) (0 indexed issues) (0 open good first issues)