COMPASS
This repository contains the PyTorch implementation of the COMPASS model proposed in our paper: COMPASS: Contrastive Multimodal Pretraining for Autonomous Systems. COMPASS aims to build general purpose representations for autonomous systems from multimodal observations. Given multimodal signals of spatial and temporal modalities M_s and M_m, respectively. COMPASS learns two factorized latent spaces, i.e., a motion pattern space O_m and a current state space O_s, using multimodal correspondence as the self-supervisory signal.
Hippocorpus
To examine the cognitive processes of remembering and imagining and their traces in language, we introduce Hippocorpus, a dataset of 6,854 English diary-like short stories about recalled and imagined events.
Carbon Insight
A platform to display the carbon neutralization information for researchers, decision-makers, and other participants in the community.
Accera
Open-source cross-platform compiler for compute-intensive loops used in AI algorithms, from Microsoft Research.
Poultry Barn Mapping
A repository for training models from high-resolution aerial imagery and a dataset of predicted poultry barns across the United States.
Solar Farms Mapping
The Solar Farms Mapping release is an artificial intelligence dataset for solar energy locations in India – a spatially explicit machine learning model to map utility-scale solar projects across India using freely available satellite imagery.
FLUTE
FLUTE (Federated Learning Utilities for Testing and Experimentation) is a platform for conducting high-performance federated learning simulations.
FastSeq
FastSeq provides efficient implementation of popular sequence models (e.g. Bart, ProphetNet) for text generation, summarization, translation tasks etc. It automatically optimizes inference speed based on popular NLP toolkits (e.g. FairSeq and HuggingFace-Transformers) without accuracy loss.
FS-Mol
FS-Mol is A Few-Shot Learning Dataset of Molecules, containing molecular compounds with measurements of activity against a variety of protein targets. The dataset is presented with a model evaluation benchmark which aims to drive few-shot learning research in the domain of molecules and graph-structured data.

