The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Repository Index
105,102 visible repositories in the index
49–58 of 58 · Most stars
TensorFlow Implementation of "Show, Attend and Tell"
- tensorflow
- image-captioning
- show-attend-and-tell
- attention-mechanism
The repository host gives no description.
TranslatedA tiny Transformer built from scratch in PyTorch, with an English-to-Chinese translation demo | A small Transformer implemented from scratch with PyTorch, with an English-to-Chinese translation demo, to help understand how the model works
- attention-mechanism
- deep-learning
- educational
- from-scratch
Peax is a tool for interactive visual pattern search and exploration in epigenomic data based on unsupervised representation learning with autoencoders
- epigenomics
- pattern-search
- data-visualization
- interactive-machine-learning
Tools for drawing 2d and 3d interactive visualizations using Jupyter proxy widgets
Agentic LLM CTF to test prompt injection attacks and preventions
Deciphering cell-cell communication from spatially resolved transcriptomic data at single-cell resolution with subgraph-based attentional graph neural network
Attempt at reproducing a SGNN's projection layer, but with word n-grams instead of skip-grams. Paper and more: http://aclweb.org/anthology/D18-1105
A coding exercise: let's convert dirty machine learning code into clean code using a Pipeline - which is the Pipe and Filter Design Pattern applied to Machine Learning.