Beast code in Giters

Csordás Róbert's repositories

MobilECG-II

Open source ECG holter

Language:C384 74 8

OnyxNoteRenderer

Tool for rendering note PDFs from Onyx Note backup file.

Language:PythonBSD-3-Clause81 8 10

moe_attention

Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"

Language:PythonMIT79 7 2

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

Language:PythonMIT66 10

modules

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

Language:PythonBSD-3-Clause4302

arch-efiboot

Boot EFISTUB linux kernels on UEFI systems not supporting kernel command line

Language:Shell40 6 4

moeut

Language:PythonMIT3400

moe

Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"

Language:PythonMIT33 1 1

ndr

The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".

Language:PythonMIT32 10

linear_layer_as_attention

The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention".

Language:Python15 2 3

moe_layer

sigma-MoE layer

Language:PythonMIT9 20

ctlpp

Codebase for our EMNLP 2022 paper "CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations"

Language:Python6 10