Customer-obsessed science
-
![At left is a neural network, labeled "pre-edit model", each of whose input nodes receives a single token from the string "<CLS> The high minded dismissal [SEP] A dismissal of a higher mind". The output of the model is the prediction "Contradict". Encodings from the network pass to a block labeled "SaLEM", in which gradients for each input token are calculated and the most-salient layer identified. The outputs of the block are edits to the layer weights. At right is another version of the neural network at left, labeled "post-edit model". Here, the output is "Entailed" rather than "Contradict".](data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZlcnNpb249IjEuMSIgaGVpZ2h0PSIzMDBweCIgd2lkdGg9IjUzNXB4Ij48L3N2Zz4=)
March 25, 2024Automated method that uses gradients to identify salient layers prevents regression on previously seen data. -
March 18, 2024Tokenizing time series data and treating it like a language enables a model whose zero-shot performance matches or exceeds that of purpose-built models.
-
March 14, 2024Diffusion modeling within the representational space of a variational autoencoder enables state-of-the-art results.
-
March 07, 2024DocFormerV2 makes sense of documents using local features, outperforming much bigger models.
![At left is a neural network, labeled "pre-edit model", each of whose input nodes receives a single token from the string "<CLS> The high minded dismissal [SEP] A dismissal of a higher mind". The output of the model is the prediction "Contradict". Encodings from the network pass to a block labeled "SaLEM", in which gradients for each input token are calculated and the most-salient layer identified. The outputs of the block are edits to the layer weights. At right is another version of the neural network at left, labeled "post-edit model". Here, the output is "Entailed" rather than "Contradict".](https://assets.amazon.science/dims4/default/7114eff/2147483647/strip/true/crop/4000x2243+0+0/resize/535x300!/quality/90/?url=http%3A%2F%2Famazon-topics-brightspot.s3.amazonaws.com%2Fscience%2Ffc%2F84%2F2aa85e0645d9b139cedded97c66b%2Fsalem-architecture.png)
February 15, 2024
In addition to its practical implications, recent work on “meaning representations” could shed light on some old philosophical questions.
-
CLeaR 20242024Identifying root causes for unexpected or undesirable behavior in complex systems is a prevalent challenge. This issue becomes especially crucial in modern cloud applications that employ numerous microservices. Although the machine learning and systems research communities have proposed various techniques to tackle this problem, there is currently a lack of standardized datasets for quantitative benchmarking
-
CVPR 20242024In the realm of geospatial analysis, the diversity of remote sensors, encompassing both optical and microwave technologies, offers a wealth of distinct observational capabilities. Recognizing this, we present msGFM, a multisensor geospatial foundation model that effectively unifies data from four key sensor modalities. This integration spans an expansive dataset of two million multisensor images. msGFM
-
AAAI 20242024The selection of the assumed effect size (AES) critically determines the duration of an experiment, and hence its accuracy and efficiency. Traditionally, experimenters determine AES based on domain knowledge. However, this method becomes impractical for online experimentation services managing numerous experiments, and a more automated approach is hence of great demand. We initiate the study of data-driven
-
March 21, 2024The principal economist and his team address unique challenges using techniques at the intersection of microeconomics, statistics, and machine learning.
-
March 13, 2024Amazon Health Services' Sunita Mishra and Columbia University’s Katrina Armstrong discuss technology's potential role in medical settings.
-
February 14, 2024Derek Chibuzor utilized his SURE experience to gain "exposure to an aerospace research project in a professional research environment."
