Customer-obsessed science
-
September 19, 2024“Agentic workflows” that use multiple, fine-tuned smaller LLMs — rather than one large one — can improve efficiency.
-
September 16, 2024A position paper presented at ACL proposes a framework for more-accurate human evaluation of LLMs.
-
September 10, 2024Automated reasoning and optimizations specific to CPU microarchitectures improve both performance and assurance of correct implementation.
-
-
September 29 - October 4, 2024
-
November 12 - 16, 2024
-
September 25, 2024
Now open until November 6, Amazon Research Awards will be seeking proposals in the following research areas: AI for Information Security, Automated Reasoning, AWS AI, AWS Cryptography, and Sustainability.
-
TQC 20242024Given a linear system of equations Ax = b, quantum linear system solvers (QLSSs) approximately prepare a quantum state |x⟩ for which the amplitudes are proportional to the solution vector x. Asymp-totically optimal QLSSs have query complexity O(κ log(1/ε)), where κ is the condition number of A, and ε is the approximation error. However, runtime guarantees for existing optimal and near-optimal QLSSs do not
-
ICPR 20242024This paper improves upon existing data pruning methods for image classification by introducing a novel pruning metric and pruning procedure based on importance sampling. The proposed pruning metric explicitly accounts for data separability, data integrity, and model uncertainty, while the sampling procedure is adaptive to the pruning ratio and considers both intra-class and inter-class separation to further
-
JSM 20242024SHAP (SHapley Additive exPlanations) is widely used in machine learning model explanations nowadays, especially for complex and black-box models (deep learning models, ensemble models). SHAP assigns a feature contribution to every record. Users can check each individual record feature contribution or use the mean absolute SHAP values over the entire dataset as the SHAP feature importance. But it’s not uncommon
-
AutoML 20242024Abstract We introduce TabRepo, a new dataset of tabular model evaluations and predictions. TabRepo contains the predictions and metrics of 1310 models evaluated on 200 classification and regression datasets. We illustrate the benefit of our dataset in multiple ways. First, we show that it allows to perform analysis such as comparing Hyperparameter Optimization against current AutoML systems while also considering
-
2024We present a novel end-to-end algorithm (PoCo) for the indoor RGB-D place recognition task, aimed at identifying the most likely match for a given query frame within a reference database. The task presents inherent challenges attributed to the constrained field of view and limited range of perception sensors. We propose a new network architecture, which generalizes the recent Context of Clusters (CoCs)
Resources
-
We look for talent from around the world for applied scientists, data scientists, economists, research scientists, scholars, academics, PhDs, and interns.
-
We collaborate with leading academic organizations to drive innovation and to ensure that research is creating solutions whose benefits are shared broadly.
-
Learn more about the awards and recognitions that Amazon researches from around the world have been honored with during their tenure.