Related papers: Scaling TensorFlow to 300 million predictions per …

Recent years, many applications have been driven advances by the use of Machine Learning (ML). Nowadays, it is common to see industrial-strength machine learning jobs that involve millions of model parameters, terabytes of training data,…

Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and…

Traffic signal control is an emerging application scenario for reinforcement learning. Besides being as an important problem that affects people's daily life in commuting, traffic signal control poses its unique challenges for reinforcement…

Machine-learning models, which are known to accurately predict patterns from large datasets, are crucial in decision making. Consequently, counterfactual explanations-methods explaining predictions by introducing input perturbations-have…

Software Engineering, as a discipline, has matured over the past 5+ decades. The modern world heavily depends on it, so the increased maturity of Software Engineering was an eventuality. Practices like testing and reliable technologies help…

This paper proposes a topic modeling method that scales linearly to billions of documents. We make three core contributions: i) we present a topic modeling method, Tensor Latent Dirichlet Allocation (TLDA), that has identifiable and…

WarpFlow is a fast, interactive data querying and processing system with a focus on petabyte-scale spatiotemporal datasets and Tesseract queries. With the rapid growth in smartphones and mobile navigation services, we now have an…

Foundation models (FMs) have emerged as a promising approach for time series forecasting. While effective, FMs typically remain fixed during deployment due to the high computational costs of learning them online. Consequently, deployed FMs…

Channel turbulence is a formidable obstacle for free-space optical (FSO) communication. Anticipation of turbulence levels is highly important for mitigating disruptions but has not been demonstrated without dedicated, auxiliary hardware. We…

Option pricing is a significant problem for option risk management and trading. In this article, we utilize a framework to present financial data from different sources. The data is processed and represented in a form of 2D tensors in three…

Personalization in Federated Learning (FL) aims to modify a collaboratively trained global model according to each client. Current approaches to personalization in FL are at a coarse granularity, i.e. all the input instances of a client use…

Recent Transformer-based large language models (LLMs) demonstrate in-context learning ability to perform various functions based solely on the provided context, without updating model parameters. To fully utilize the in-context capabilities…

Video inpainting tasks have seen significant improvements in recent years with the rise of deep neural networks and, in particular, vision transformers. Although these models show promising reconstruction quality and temporal consistency,…

Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of…

We propose a novel framework in high-dimensional factor models to simultaneously analyse multiple tensor time series, each with potentially different tensor orders and dimensionality. The connection between different tensor time series is…

This paper explores the potential for leveraging Large Language Models (LLM) in the realm of online advertising systems. We introduce a general framework for LLM advertisement, consisting of modification, bidding, prediction, and auction…

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Temporal coherence is a valuable source of information in the context of optical flow estimation. However, finding a suitable motion model to leverage this information is a non-trivial task. In this paper we propose an unsupervised online…

Large Language Models (LLMs) have pushed the frontier of artificial intelligence but are comprised of hundreds of billions of parameters and operations. For faster inference latency, LLMs are deployed on multiple hardware accelerators…

Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved for continuous modalities, including…