Customer-obsessed science
-
May 17, 2024A novel loss function and a way to aggregate multimodal input data are key to dramatic improvements on some test data.
-
May 10, 2024Using large language models to discern commonsense relationships can improve performance on downstream tasks by as much as 60%.
-
April 30, 2024Using causal random forests and Bayesian structural time series to extrapolate from sparse data ensures that customers get the most useful information as soon as possible.
-
-
May 20 - 25, 2024
-
June 9 - 14, 2024
-
June 16 - 21, 2024
-
March 18, 2024
Tokenizing time series data and treating it like a language enables a model whose zero-shot performance matches or exceeds that of purpose-built models. Update: Amazon scientists how now released the training code for Chronos, which is available on GitHub.
-
AISTATS 20242024Crowdsourced machine learning on competition platforms such as Kaggle is a popular and often effective method for generating accurate models. Typically, teams vie for the most accurate model, as measured by overall error on a holdout set, and it is common towards the end of such competitions for teams at the top of the leaderboard to ensemble or average their models outside the platform mechanism to get
-
*SEM 20242024Abstract Meaning Representation (AMR) is a semantic formalism that captures the core meaning of an utterance. There has been substantial work developing AMR corpora in English and more recently across languages, though the limited size of existing datasets and the cost of collecting more annotations are prohibitive. With both engineering and scientific questions in mind, we introduce MASSIVE-AMR, a dataset
-
ICML 20242024In large language model training, input documents are typically concatenated together and then split into sequences of equal length to avoid padding tokens. Despite its efficiency, the concatenation approach compromises data integrity—it inevitably breaks many documents into incomplete pieces, leading to excessive truncations that hinder the model from learning to compose logically coherent and factually
News and features
-
April 26, 2024Awardees, who represent 51 universities in 15 countries, have access to Amazon public datasets, along with AWS AI/ML services and tools.
-
April 09, 2024How the team behind Echo Frames delivered longer battery life and improved sound quality inside the slim form factor of a pair of eyeglasses.
-
March 21, 2024The principal economist and his team address unique challenges using techniques at the intersection of microeconomics, statistics, and machine learning.