Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
ICLR 20232023Like many other machine learning applications, neural machine translation (NMT) benefits from over-parameterized deep neural models. However, these models have been observed to be brittle: NMT model predictions are sensitive to small input changes and can show significant variation across re-training or incremental model updates. This work studies a frequently used method in NMT, pseudo-label training (
-
CVPR 20232023In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input
-
PAKDD 20232023Dense embedding-based semantic matching is widely used in e-commerce product search to address the shortcomings of lexical matching such as sensitivity to spelling variants. The recent advances in BERT-like language model encoders, have however, not found their way to realtime search due to the strict inference latency requirement imposed on e-commerce websites. While bi-encoder BERT architectures enable
-
AAAI 2023 Workshop on Knowledge Augmented Methods for NLP2023The abundance of benchmark datasets supports the recent trend of increased attention given to Question Answering (QA) tasks. However, most of them lack a diverse selection of QA types and more challenging questions. In this work, we present StoryQA, a new task and dataset addressing diverse QA problems for both in-context and out-of-context questions. Additionally, we developed QA models based on large
-
PPoPP 20232023Jointly utilizing multiple GPUs to train graph neural networks (GNNs) is crucial for handling large graphs and achieving high efficiency. However, we find that existing systems suffer from high communication costs and low GPU utilization due to improper data layout and training procedures. Thus, we propose a system dubbed Distributed Sampling and Pipelining (DSP) for multi-GPU GNN training. DSP adopts a
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all