Synthesis and Machine Learning for Heterogeneous Extraction
In this project, we present a way to combine techniques from the program synthesis and machine learning communities to extract structured information from heterogeneous data. Such problems arise in several situations such as extracting attributes…
Project Jigsaw
Large Language Models meet Program Synthesis Note: This research project has reached its conclusion. These pages are maintained for reference and archival purposes. Large pre-trained language models such as GPT-3, Codex, and Google’s language model…
AI Tooling and MLOps
In recent years, artificial intelligence (AI), including machine learning (ML) and deep learning (DL), has been widely adopted in many application domains, such as computer vision, speech recognition, natural language processing, and gaming. However, developers…
COVID19-CT segmentation
This project provides code to train semantic segmentation models for pulmonary lesions segmentation from Computer Tomography (CT) scans. Furthermore, we present a multitask model for joint segmentation of different classes of pulmonary lesions present in…
2022微软亚洲研究院人工智能与系统专题讨论——软硬件优化专场
在深度学习时代,人工智能进化的速度已经超过了摩尔定律。高效的AI系统,包括全栈算法、软件框架、编译和硬件加速,是保持AI高速发展的关键保障之一。微软亚洲研究院人工智能与系统专题讨论系列旨在联合学界和业界的专家学者,促进人工智能与系统领域多样的学术交流,营造更加开放的研究氛围,并推动人工智能与系统领域学术研究与发展。 研讨会筹委会 徐宁仪 上海交通大…
Shanghai AI/ML Group
The Shanghai AI/ML Group from MSRA Shanghai focuses on research areas related to machine learning and its application. For machine learning research, we are interested to fundamental deep learning techniques including neural network architecture design,…
Plenary Talk: From mathematics to data science and back
Plenary Talk: From mathematics to data science and back by Terry Lyons of the University of Oxford. Learn more about the 2021 MSR Asia Theory Workshop: https://cm-edgetun.pages.dev/en-us/research/event/2021-msr-asia-theory-workshop/
Talk: Recent results on stochastic 3D Navier-Stokes equations
Talk: Recent results on stochastic 3D Navier-Stokes equations by Xiangchan Zhu of Chinese Academy of Sciences. Learn more about the 2021 MSR Asia Theory Workshop: https://cm-edgetun.pages.dev/en-us/research/event/2021-msr-asia-theory-workshop/
Talk: The implicit bias of optimization algorithms in deep learning
Talk: The implicit bias of optimization algorithms in deep learning by Qi Meng of Microsoft Research Asia. Learn more about the 2021 MSR Asia Theory Workshop: https://cm-edgetun.pages.dev/en-us/research/event/2021-msr-asia-theory-workshop/
Talk: Causal inference, observational studies, and the 2021 Nobel Prize in Economics
Talk: Causal inference, observational studies, and the 2021 Nobel Prize in Economics by Wang Miao of Peking University. Learn more about the 2021 MSR Asia Theory Workshop: https://cm-edgetun.pages.dev/en-us/research/event/2021-msr-asia-theory-workshop/