A beautiful, simple, clean, and responsive Jekyll theme for academics

Refine high-quality datasets and visual AI models

This repository contains demos I made with the Transformers library by HuggingFace.

Yet Another Neural Machine Translation Toolkit

Synthesize image datasets of documents in natural scenes with Python+Blender3D

LightSeq: A High Performance Library for Sequence Processing and Generation

Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

Prefix-Tuning: Optimizing Continuous Prompts for Generation

A synthetic data generator for text recognition

CUAD (NeurIPS 2021)

Make drawing and labeling bounding boxes a piece of cake

Differential Privacy Preservation in Deep Learning under Model Attacks

A simplified implemention of Faster R-CNN that replicate performance from origin paper

A PyTorch reimplementation of bottom-up-attention models

A small React app to monitor ARK funds daily transactions

An implementation of the Splitting and Merging table recognition method.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

⚡ Hugo Blox: Markdown sites in minutes. Academic/resume/lab/portfolio for AI researchers & startups. Premium templates. Deploy to GitHub Pages now in 1-click 👇

The accompanying code for "Injecting Numerical Reasoning Skills into Language Models" (Mor Geva*, Ankit Gupta* and Jonathan Berant, ACL 2020).

Attributing predictions made by the Inception network using the Integrated Gradients method

Code for paper Hierarchical Transformers for Multi-Document Summarization in ACL2019

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Pytorch library for fast transformer implementations

Reformer, the efficient Transformer, in Pytorch

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

This repository focus on Image Captioning & Video Captioning & Seq-to-Seq Learning & NLP

Exploring Self-attention for Image Recognition, CVPR2020.

[arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis