Advancing the state of the art

It has been shown that learning audiovisual features can lead to improved speech recognition performance over audio-only features, especially for noisy speech. However, in many common applications, the visual features are partially or entirely missing, e.g.~the speaker might move off screen. Multi-modal models need to be robust: missing video frames should not degrade the performance of an...

The ability to accurately estimate job runtime properties allows a scheduler to effectively schedule jobs. State-of-theart online cluster job schedulers use history-based learning, which uses past job execution information to estimate the runtime properties of newly arrived jobs. However, with fast-paced development in cluster technology (in both hardware and software) and changing user inputs,...

Differentially private algorithms for common metric aggregation tasks, such as clustering or averaging, often have limited practicality due to their complexity or to the large number of data points that is required for accurate results. We propose a simple and practical tool $\mathsf{FriendlyCore}$ that takes a set of points $\cD$ from an unrestricted (pseudo) metric space as input. When $\cD$...

Differentially private algorithms for common metric aggregation tasks, such as clustering or averaging, often have limited practicality due to their complexity or to the large number of data points that is required for accurate results. We propose a simple and practical tool $\mathsf{FriendlyCore}$ that takes a set of points $\cD$ from an unrestricted (pseudo) metric space as input. When $\cD$...

We present a decade of evolution and production experience with Jupiter datacenter network fabrics. In this period Jupiter has delivered 5x higher speed and capacity, 30% reduction in capex, 41% reduction in power, incremental deployment and technology refresh all while serving live production traffic. A key enabler for these improvements is evolving Jupiter from a Clos to a direct-connect...

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to direct future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-...

Neural Radiance Fields (NeRF) have emerged as a powerful representation for the task of novel view synthesis due to their simplicity and state-of-the-art performance. Though NeRF can produce photorealistic renderings of unseen viewpoints when many input views are available, its performance drops significantly when this number is reduced. We observe that the majority of artifacts in sparse input...

Although convolutional neural networks (CNNs) achieve state-of-the-art in image classification, recent works address their unreliable predictions due to their excessive dependence on biased training data. Existing unbiased modeling postulates that the bias in the dataset is obvious to know, but it is actually unsuited for image datasets including countless sensory attributes. To mitigate this...

The multi-stage cascaded architecture has been adopted by many search engines for efficient and effective retrieval. This architecture consists of a stack of retrieval and reranking models in which efficient retrieval models are followed by effective (neural) learning to rank models. The optimization of these learning to rank models is loosely connected to the early stage retrieval models. In...