Related papers: On Improving Deep Learning Trace Analysis with Sys…

In deep neural networks, better results can often be obtained by increasing the complexity of previously developed basic models. However, it is unclear whether there is a way to boost performance by decreasing the complexity of such models.…

We study the problem of event extraction from text data, which requires both detecting target event types and their arguments. Typically, both the event detection and argument detection subtasks are formulated as supervised sequence…

Decay Replay Mining is a deep learning method that utilizes process model notations to predict the next event. However, this method does not intertwine the neural network with the structure of the process model to its full extent. This…

Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. To understand this gap, we synthesize cognitive…

Locks have been widely used as an effective synchronization mechanism among processes and threads. However, we observe that a large number of false inter-thread dependencies (i.e., unnecessary lock contentions) exist during the program…

This work presents a novel means for understanding learning dynamics and scaling relations in neural networks. We show that certain measures on the spectrum of the empirical neural tangent kernel, specifically entropy and trace, yield…

Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…

Retrieval-Augmented Generation (RAG) delivers substantial value in knowledge-intensive applications. However, its generated responses often lack transparent reasoning paths that trace back to source evidence from retrieved documents. This…

Event linking connects event mentions in text with relevant nodes in a knowledge base (KB). Prior research in event linking has mainly borrowed methods from entity linking, overlooking the distinct features of events. Compared to the…

We apply a fast kernel method for mask-based single-channel speech enhancement. Specifically, our method solves a kernel regression problem associated to a non-smooth kernel function (exponential power kernel) with a highly efficient…

Multi-task learning has recently become a very active field in deep learning research. In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks…

In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To exploit both…

The analysis of sequences (e.g., protein, DNA, and SMILES string) is essential for disease diagnosis, biomaterial engineering, genetic engineering, and drug discovery domains. Conventional analytical methods focus on transforming sequences…

We introduce a similarity function on formulae of signal temporal logic (STL). It comes in the form of a kernel function, well known in machine learning as a conceptually and computationally efficient tool. The corresponding kernel trick…

With the rise of machine learning, there is a great deal of interest in treating programs as data to be fed to learning algorithms. However, programs do not start off in a form that is immediately amenable to most off-the-shelf learning…

Graph neural networks (GNNs) have become a powerful tool for processing graph-structured data but still face challenges in effectively aggregating and propagating information between layers, which limits their performance. We tackle this…

Human activity recognition (HAR) in smart homes remains challenging because many daily activities exhibit similar local sensor patterns, while minimally intrusive sensing provides sparse and ambiguous observations. As a result, methods…

Named entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive…

Learning representations of nodes in a low dimensional space is a crucial task with numerous interesting applications in network analysis, including link prediction, node classification, and visualization. Two popular approaches for this…

Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can…