An accelerator to help organizations build Trusted Research Environments on Azure.
Обновлено 2024-11-19 15:42:37 +03:00
Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.
Обновлено 2024-11-13 06:41:06 +03:00
This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.
Обновлено 2024-10-27 15:51:02 +03:00
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
Обновлено 2024-10-23 20:40:41 +03:00
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Обновлено 2024-10-18 13:31:05 +03:00
Security Research from the Microsoft Security Response Center (MSRC)
Обновлено 2024-08-09 02:25:26 +03:00
A research project for natural language generation, containing the official implementations by MSRA NLC team.
Обновлено 2024-07-25 14:27:07 +03:00
This repository contains code and datasets related to entity/knowledge papers from the VERT (Versatile Entity Recognition & disambiguation Toolkit) project, by the Knowledge Computing group at Microsoft Research Asia (MSRA).
Обновлено 2024-03-16 09:53:11 +03:00
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
Обновлено 2024-02-23 11:45:58 +03:00
A Dataset of Python Challenges for AI Research
Обновлено 2023-12-21 00:10:56 +03:00
Multiple paper open-source codes of the Microsoft Research Asia DKI group
Обновлено 2023-11-10 05:14:43 +03:00
Repository containing information about Unity Labs research past and current.
Обновлено 2023-10-10 22:49:49 +03:00
A framework for drone racing research, built on Microsoft AirSim.
Обновлено 2023-08-15 00:51:00 +03:00
Research code of ICCV 2021 paper "Mesh Graphormer"
Обновлено 2023-07-07 01:06:33 +03:00
Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"
Обновлено 2023-07-07 01:02:19 +03:00
Research code accompanying paper on predicting the probability of a positive SARS-CoV-2 test, using OMOP common data model.
Обновлено 2023-07-07 01:01:33 +03:00
Transformer-based machine reading comprehension in combination with Azure Cognitive Search
Обновлено 2023-06-13 00:29:56 +03:00
A dual learning toolkit developed by Microsoft Research
Обновлено 2023-06-12 22:32:21 +03:00
Automatically extracting keyphrases that are salient to the document meanings is an essential step to semantic document understanding. An effective keyphrase extraction (KPE) system can benefit a wide range of natural language processing and information retrieval tasks. Recent neural methods formulate the task as a document-to-keyphrase sequence-to-sequence task. These seq2seq learning models have shown promising results compared to previous KPE systems The recent progress in neural KPE is mostly observed in documents originating from the scientific domain. In real-world scenarios, most potential applications of KPE deal with diverse documents originating from sparse sources. These documents are unlikely to include the structure, prose and be as well written as scientific papers. They often include a much diverse document structure and reside in various domains whose contents target much wider audiences than scientists. To encourage the research community to develop a powerful neural model with key phrase extraction on open domains we have created OpenKP: a dataset of over 150,000 documents with the most relevant keyphrases generated by expert annotation.
Обновлено 2023-06-12 21:21:58 +03:00
Truly Conversational Search is the next logic step in the journey to generate intelligent and useful AI. To understand what this may mean, researchers have voiced a continuous desire to study how people currently converse with search engines. Traditionally, the desire to produce such a comprehensive dataset has been limited because those who have this data (Search Engines) have a responsibility to their users to maintain their privacy and cannot share the data publicly in a way that upholds the trusts users have in the Search Engines. Given these two powerful forces we believe we have a dataset and paradigm that meets both sets of needs: A artificial public dataset that approximates the true data and an ability to evaluate model performance on the real user behavior. What this means is we released a public dataset which is generated by creating artificial sessions using embedding similarity and will test on the original data. To say this again: we are not releasing any private user data but are releasing what we believe to be a good representation of true user interactions.
Обновлено 2023-06-12 21:21:58 +03:00
Record-and-replay tools are indispensable for quality assurance of mobile applications. However, by conducting an empirical study of various existing tools in industrial settings, researchers have concluded that no existing tools under evaluation are sufficient for industrial applications. In this project, we present a record-and-replay tool called SARA towards bridging the gap and targeting a wide adoption.
Обновлено 2023-06-12 21:21:33 +03:00
TOML-annotated C header file format for packaging binary files, from Microsoft Research
Обновлено 2023-05-09 19:08:05 +03:00
This research project implements a real-time object detection and pose estimation method as described in the paper, Tekin et al. "Real-Time Seamless Single Shot 6D Object Pose Prediction", CVPR 2018. (https://arxiv.org/abs/1711.08848).
Обновлено 2022-11-28 22:11:09 +03:00
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.
Обновлено 2022-01-06 19:18:51 +03:00
This project aims to predict the probability of leprosy using skin lesion images and clinical data (as compared to the diagnosis of dermatologists). This model is provided for research and development use only. The model is not intended for use in clinical decision-making or for any other clinical use and the performance of model for clinical use has not been established.
Обновлено 2021-06-30 03:06:06 +03:00
Research simulation toolkit for federated learning
Обновлено 2020-11-07 20:47:34 +03:00
CANOSP-2019 internship project meta-repo for Private Federated Learning research project
Обновлено 2020-05-01 02:53:07 +03:00
DEPRECATED - Preliminary work ahead of Web crawl research (list generation, precrawl, analysis)
Обновлено 2019-12-14 21:24:00 +03:00