

-
September 20, 2023Leveraging large language models will make interactions with Alexa more natural and engaging.
-
September 15, 2023Novel “cuboid attention” helps transformers handle large-scale multidimensional data, while diffusion models enable probabilistic prediction.
-
September 14, 2023In a keynote address, the Amazon International vice president will discuss recommendations in directed graphs, training models whose target labels change, and using prediction uncertainty to improve model performance.
-
-
October 2 - 6, 2023
-
October 15 - 18, 2023
-
September 19, 2023The new Fulfillment by Amazon system empowers sellers to have more transparency and control over their capacity within Amazon’s fullfilment network by applying market-based principles.
-
August 28, 2023AWS service enables machine learning innovation on a robust foundation.
-
August 24, 2023Registrations for the third edition of the ML Summer School closed on Sept. 6.
-
August 16, 2023Startup Pixieray is working on a breakthrough in vision correction.
-
2023Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve
-
2023Video amodal segmentation is a particularly challenging task in computer vision, which requires to deduce the full shape of an object from the visible parts of it. Recently, some studies have achieved promising performance by using motion flow to integrate information across frames under a self-supervised setting. However, motion flow has a clear limitation by the two factors of moving cameras and object
-
2023Amodal object segmentation is a challenging task that involves segmenting both visible and occluded parts of an object. In this paper, we propose a novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addresses this problem by progressively modeling the amodal segmentation. C2F-Seg initially reduces the learning space from the pixel-level image space to the vector-quantized latent space. This
-
ECAI 2023 Workshop on Perspectivist Approaches to NLP2023In the framework of perspectivism, analyzing how people perceive pragmatic phenomena, like irony, is relevant for deeply understanding the different points of view, and for creating more robust perspective-aware models. This paper presents a linguistic analysis of irony perception in 11 perspectivist models. Each model is trained on annotations by crowd-sourcing workers different in gender, age, and nationalities
-
IJCNLP-AACL 20232023Modern virtual assistants are trained to classify customer requests into a taxonomy of predesigned intents. Requests that fall outside of this taxonomy, however, are often unhandled and need to be clustered to define new experiences. Recently, state-of-the-art results in intent clustering were achieved by training a neural network with a latent structured prediction loss. Unfortunately, though, this new
-
September 21, 2023The submission period opens September 21 and closes on November 1.
-
September 12, 2023GauchoChat wins $250,000 first place prize in overall competition; Chirpy Cardinal earns $250,000 for first place in scientific innovation category.
-
September 07, 2023Awardees have access to Amazon public datasets, along with AWS AI/ML services and tools to perform cutting-edge research in generative AI.
Working at Amazon
View allMeet the people driving the innovation essential to being the world’s most customer-centric company.
View all
-
August 29, 2023Chamsi Hssaine and Hanzhang Qin, the inaugural postdoctoral scientists with the Supply Chain Optimization Technologies team, share what they learned from Amazon scientists.
-
August 24, 2023From the urgent challenge of "machine unlearning" to overcoming the problem of critical learning periods in deep neural networks, Alessandro Achille is tackling fundamental issues on behalf of Amazon customers.
-
August 21, 2023How Linghui Luo's research helps ensure code is checked and ready to deploy.