Latest news
View all-
April 27, 2021ARA funds nearly twice as many awards as in previous year; 101 award recipients represent 59 universities in 13 countries.
-
April 26, 2021New method identifies which causal factors contribute most to observed changes in probability distributions.
-
April 23, 2021To mark the occasion, Amazon Science showcases some of the top-selling artificial-intelligence books, and passages from each book that Kindle customers have highlighted most frequently.
-
-
May 3 - 7, 2021
-
June 6 - 11, 2021
-
April 22, 2021The Middle Mile team manages complexity and scale in making routing decisions across the company’s expansive transportation network.
-
April 22, 2021Cloud access to the CMIP6 dataset will enable climate scientists and researchers to study future climate conditions more easily.
-
April 21, 2021Polito is one of the featured speakers at the first virtual Amazon Web Services Machine Learning Summit on June 2.
-
April 19, 2021In a pilot study, an automated code checker found about 100 possible errors, 80% of which turned out to require correction.
Recent publications
View all-
2021 Annual Learning for Dynamics & Control Conference2021How can we learn a dynamical system to make forecasts, when some variables are unobserved? For instance, in COVID-19, we want to forecast the number of infected and death cases but we do not know the count of susceptible and exposed people. While mechanics compartment models are widely-used in epidemic modeling, data-driven models are emerging for disease forecasting. As a case study, we compare these two
-
ICLR 2021 RobustML Workshop2021Controllable text generation is one of the most important yet challenging tasks in natural language processing (NLP). Prior methods relying on disentangled representations or language models suffer from limited controllability due to biases or spurious correlations in the data. To remedy this, we present a causal framework for controllable text generation. Our method allows control over one or more attributes
-
2021Named Entity Recognition (NER) remains difficult in real-world settings; current challenges include short texts (low context), emerging entities, and complex entities (e.g. movie names). Gazetteer features can help, but results have been mixed due to challenges with adding extra features, and a lack of realistic evaluation data. It has been shown that including gazetteer features can cause models to overuse
-
NAACL 2021 Workshop on Multimodal Artificial Intelligence2021Explainable deep learning models are advantageous in many situations. Prior work mostly provide unimodal explanations through posthoc approaches not part of the original system design. Explanation mechanisms also ignore useful textual information present in images. In this paper, we propose MTXNet, an end-to-end trainable multimodal architecture to generate multimodal explanations, which focuses on the
-
NAACL 2021 Third Workshop on Privacy in Natural Language Processing2021Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. When the noise is small in magnitude, these mechanisms are susceptible to reconstruction of the original sensitive text. This is because the nearest neighbor to the noised input is likely to be the original input. To mitigate this
![View from space of a connected network around planet Earth representing the Internet of Things.](https://webcf.waybackmachine.org/web/20210427232920im_/https://assets.amazon.science/dims4/default/29c19bf/2147483647/strip/true/crop/1014x877+4+346/resize/326x282!/quality/90/?url=http%3A%2F%2Famazon-topics-brightspot.s3.amazonaws.com%2Fscience%2F20%2Fc4%2Fc36de9f643dab18e2f27ea071590%2Famazon-science-newsletter-project-kuiper.jpg)
Research areas
Hear from Amazon scientists, watch interviews and panels, and more.
Up next
![Meet our scientists](https://webcf.waybackmachine.org/web/20210427232920im_/https://assets.amazon.science/dims4/default/7bb2b11/2147483647/strip/true/crop/480x269+0+46/resize/143x80!/quality/90/?url=https%3A%2F%2Fi.ytimg.com%2Fvi%2FBAVNj91mAC4%2Fhqdefault.jpg)
Meet our scientists
![Yoelle Maarek, Alexa Shopping vice president of research and science](https://webcf.waybackmachine.org/web/20210427232920im_/https://assets.amazon.science/dims4/default/97c6810/2147483647/strip/true/crop/480x269+0+46/resize/143x80!/quality/90/?url=https%3A%2F%2Fi.ytimg.com%2Fvi%2FPGYmKVn-HNA%2Fhqdefault.jpg)
Yoelle Maarek, Alexa Shopping vice president of research and science
![CVPR Panel - Computer vision: A look at the past, present, and future](https://webcf.waybackmachine.org/web/20210427232920im_/https://assets.amazon.science/dims4/default/5486f2f/2147483647/strip/true/crop/480x269+0+46/resize/143x80!/quality/90/?url=https%3A%2F%2Fi.ytimg.com%2Fvi%2FgNWqK__U23U%2Fhqdefault.jpg)
CVPR Panel - Computer vision: A look at the past, present, and future
![Women in Tech coffee talk at VLDB 2020 | Amazon Science](https://webcf.waybackmachine.org/web/20210427232920im_/https://assets.amazon.science/dims4/default/a7e2c6f/2147483647/strip/true/crop/480x269+0+46/resize/143x80!/quality/90/?url=https%3A%2F%2Fi.ytimg.com%2Fvi%2FcnzOkeD7InM%2Fhqdefault.jpg)
Women in Tech coffee talk at VLDB 2020 | Amazon Science
![Swami Sivasubramanian keynote outtake from Amazon AWS re:Invent 2020](https://webcf.waybackmachine.org/web/20210427232920im_/https://assets.amazon.science/dims4/default/dfcf42b/2147483647/strip/true/crop/480x269+0+46/resize/143x80!/quality/90/?url=https%3A%2F%2Fi.ytimg.com%2Fvi%2FPPYgcbw2NEM%2Fhqdefault.jpg)
Swami Sivasubramanian keynote outtake from Amazon AWS re:Invent 2020
Meet our scientists
Five scientists from across the company describe what they love about working at Amazon, and the type of customer-obsessed science and innovation they're responsible for in their role.
Working at Amazon
View all-
April 13, 2021Their doctoral degrees help these product managers bridge the gap between business and science.
-
March 30, 2021Learn how Bill Smart wants to simplify the ways that robots and people work together — and why waiting on a date one night changed his career path.
Academic engagements
Learn more-
March 22, 2021Amazon Lab126 and the Center for Risk and Reliability will study how devices are accidentally damaged — and how to help ensure they survive more of those incidents.
-
March 18, 2021Next week the spring 2021 call for proposals open for the Amazon Research Awards, related to two research areas: Alexa Fairness in AI, and AWS Automated Reasoning. Deadline for submissions is April 23, 2021.