An open source framework for research in Embodied-AI from AI2.
-
Updated
Sep 11, 2024 - Python
An open source framework for research in Embodied-AI from AI2.
Using pre trained word embeddings (Fasttext, Word2Vec)
PyTorch code for EMNLP 2020 paper "X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers"
A simple toolbox for your school Chromebook.
ARCADE198 Dataset from the ACL 2018 MRQA Workshop
An extension to check if VPN is active in the system, built for MIT AI2 and other App Inventor based distributions.
staging post for Thunkable Extensions Directory
❓❔In this project a BERT-based model is build, which returns “an answer”, given a user question and a passage which includes the answer of the question. For this question answering task, SQuAD 2.0 dataset is used.
An MIT AI2 extension that allows developers to show media style notifications for their media applications.
Knight é um jogo para Aparelhos Android, feito na plataforma MIT App Inventor.
This project is about developing a document retrieval system to return titles of scientific papers containing the answer to a given user question. Two different sentence embedding approaches have been implemented and compared.
Repo for the FormulasV extension
A AI2 Extension to wrap the Metadata Retriever class.
Routing and tracking with MIT App Inventor in Blockly (educational)
AI2 extension for parsing json strings.
Add a description, image, and links to the ai2 topic page so that developers can more easily learn about it.
To associate your repository with the ai2 topic, visit your repo's landing page and select "manage topics."