Microsoft Research

Physics-based groundwater – surface water modeling at continental scale Aquanty, which is a research spin off from the University of Waterloo, is at the forefront of developing state-of-the-art

Out of thin air: Direct Air Capture of carbon dioxide to walk our carbon footprint backwards It is likely that to avert temperature increases greater than 1.5C society will need negative emission

Recorded on November 17, 2021 Speaker: Dr. André Brock, Associate Professor of Media Studies at Georgia Institute of Technology Where does Blackness manifest in Western technoculture?

Recorded on October 27, 2021 Speaker: Dr.

Watch the condensed version: youtu.be/JS5H-Usiphg Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered

The increased availability and maturity of head-mounted and wearable devices opens up opportunities for remote communication and collaboration.

LITMUS: Linguistically Inspired Training and testing of MUltilingual Systems LITMUS Predictor provides support for simulating performance in ~100 languages given training observations of the

On June 9 at the Spring 2021 Machine Learning, AI & Data Science Conference, we featured an interview and Q&A with Jenny Sabin, the Cornell-based artist who created the Ada installation currently

Meet some of 2021 global PhD Fellowship recipients from around the world. See more at microsoft.com/en-us/research/video/microsoft-research-2021-global-phd-fellowship-recipients

On an 8,000-acre family farm in Eastern Washington, Microsoft Research helps deploy precision agriculture, putting AI and powerful data analysis tools in the hands of an eighth-generation farmer

Here at Microsoft Research in Cambridge, we truly aspire to transform the world through deep research. Watch the video to find out more about our culture, ambition and research themes.

Episode 010 | September 28, 2021 Artificial intelligence, Machine Learning, Deep Learning, and Deep Neural Networks are today critical to the success of many industries.

The Ultimate Flexible Workstation?

HapticBots introduces a novel encountered-type haptic approach for Virtual Reality (VR) based on multiple tabletop-size shape-changing robots.

X-Rings is a novel hand-mounted 360-degree shape display for Virtual Reality that renders objects in 3D and responds to user-applied touch and grasping force.

Microsoft Sponsor Session at ICCV 2021 featuring speakers: Han Hu, Principal Researcher, Microsoft Research Asia Li Dong, Senior Researcher, Microsoft Research Asia

In this talk I will present my current and future work towards enabling safe real-world autonomy.

Recorded on September 22, 2021 Speaker: Dr.

We demonstrate that it is possible to perform face-related computer vision in the wild using synthetic data alone.

Pre-trained representations are becoming crucial for many NLP and perception tasks.

In this talk, I will introduce our recent work about ViLD, a training method via Vision and Language knowledge Distillation.

In this talk, I am going to cover three of our recent explorations on pre-training.

The goal of Computer Vision, as coined by Marr, is to develop algorithms to answer What are Where at When from visual appearance.

Any dataset has bias, as the data collection will be intervened by human bias and affected by the nature’s biased law.

Advances in deep learning keep producing impressive results at the junction of computer vision and natural language processing.

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image.

As humans, we parse language and visual scenes -- often together -- into a rich understanding of what is going on in the world.

Remarkable progress has been made at the intersection of vision and language.

Deep learning has brought tremendous progress to visual recognition, thanks to big labeled data and fast compute.

Multi-modal data provides an exciting opportunity to train grounded generative models that synthesize images consistent with real world phenomena.