Related papers: Assessing Resource-Performance Trade-off of Natura…

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the…

Developing interpretable machine learning models has become an increasingly important issue. One way in which data scientists have been able to develop interpretable models has been to use dimension reduction techniques. In this paper, we…

This article analyzes the use of Large Language Models (LLMs) as support for the conceptual modeling of relational databases through the automatic generation of Entity-Relationship (ER) diagrams from natural language requirements. The…

Attribution maps for semantic segmentation are almost always judged by visual plausibility. Yet looking convincing does not guarantee that the highlighted pixels actually drive the model's prediction, nor that attribution credit stays…

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET…

In recent years, we have witnessed a dramatic shift towards techniques driven by neural networks for a variety of NLP tasks. Undoubtedly, neural language models (NLMs) have reduced perplexity by impressive amounts. This progress, however,…

Pre-trained language models (PLMs) show impressive performance in various downstream NLP tasks. However, pre-training large language models demands substantial memory and training compute. Furthermore, due to the substantial resources…

Although Large Language Models (LLMs) have made significant progress in code generation, they still struggle with code generation tasks in specific scenarios. These scenarios usually necessitate the adaptation of LLMs to fulfill specific…

Large language models (LLMs) are increasingly used in applications forming multi-request workflows like document summarization, search-based copilots, and multi-agent programming. While these workflows unlock richer functionality, they also…

Many complex problems, such as natural language processing or visual object detection, are solved using deep learning. However, efficient training of complex deep convolutional neural networks for large data sets is computationally…

We propose a new approach towards determining the distribution of mechanical and acoustic wave energy in complex built-up structures. The technique interpolates between standard Statistical Energy Analysis (SEA) and full ray tracing…

Deep learning, as a highly efficient method for metasurface inverse design, commonly use simulation data to train deep neural networks (DNNs) that can map desired functionalities to proper metasurface designs. However, the assumptions and…

We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation operators across peer nodes communicating with non-blocking…

Training deep learning models on mobile devices recently becomes possible, because of increasing computation power on mobile hardware and the advantages of enabling high user experiences. Most of the existing work on machine learning at…

Conventional online surveys provide limited personalization, often resulting in low engagement and superficial responses. Although AI survey chatbots improve convenience, most are still reactive: they rely on fixed dialogue trees or static…

Word embedding (WE) techniques are advanced textual semantic representation models oriented from the natural language processing (NLP) area. Inspired by their effectiveness in facilitating various NLP tasks, more and more researchers…

Interactions with virtual assistants typically start with a trigger phrase followed by a command. In this work, we explore the possibility of making these interactions more natural by eliminating the need for a trigger phrase. Our goal is…

During the past sixty years, a lot of effort has been made regarding the productive efficiency. Such endeavours provided an extensive bibliography on this subject, culminating in two main methods, named the Stochastic Frontier Analysis…

Benchmarking the performance of complex systems such as rail networks, renewable generation assets and national economies is central to transport planning, regulation and macroeconomic analysis. Classical frontier methods, notably Data…

Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence…