Related papers: Sequencelib: A Computational Platform for Formaliz…

The integration of Artificial Intelligence (AI) into automation systems has the potential to enhance efficiency and to address currently unsolved existing technical challenges. However, the industry-wide adoption of AI is hindered by the…

As artificial intelligence (AI) gains greater adoption in a wide variety of applications, it has immense potential to contribute to mathematical discovery, by guiding conjecture generation, constructing counterexamples, assisting in…

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks…

In today's data-driven world, the proliferation of publicly available information raises security concerns due to the information leakage (IL) problem. IL involves unintentionally exposing sensitive information to unauthorized parties via…

Data representation remains a fundamental challenge in machine learning, particularly when adapting sequence-based architectures like Transformers and Large Language Models (LLMs) for structured tabular data. Existing methods often fail to…

OpenSesame is a program for generating tabular equations of state (EOS), with capabilities for multiphase EOS construction. In this tutorial, we provide an overview of how to run OpenSesame to construct a multiphase EOS. We discuss some…

Sequential structure is a key feature of multiple domains of natural cognition and behavior, such as language, movement and decision-making. Likewise, it is also a central property of tasks to which we would like to apply artificial…

Formal theorem-proving benchmarks enable mechanically verifiable evaluation of mathematical reasoning in large language models. However, existing benchmarks mainly focus on Olympiad-style problems and algebraic domains, leaving…

We introduce HONEY; a new specialized programming language designed to facilitate the processing of multivariate, asynchronous and non-uniformly sampled symbolic and scalar time sequences. When compiled, a Honey program is transformed into…

In this paper, we make the first attempt to understand and test potential computation efficiency robustness in state-of-the-art LLMs. By analyzing the working mechanism and implementation of 20,543 public-accessible LLMs, we observe a…

SentenceMIM is a probabilistic auto-encoder for language data, trained with Mutual Information Machine (MIM) learning to provide a fixed length representation of variable length language observations (i.e., similar to VAE). Previous…

Customization of processor architectures through Instruction Set Extensions (ISEs) is an effective way to meet the growing performance demands of embedded applications. A high-quality ISE generation approach needs to obtain results close to…

The increasing demand for large language model (LLM) serving has necessitated significant advancements in the optimization and profiling of LLM inference systems. As these models become integral to a wide range of applications, the need for…

The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE).…

Extracting tables from documents is a crucial task in any document conversion pipeline. Recently, transformer-based models have demonstrated that table-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence…

First-principles electronic structure calculations are very widely used thanks to the many successful software packages available. Their traditional coding paradigm is monolithic, i.e., regardless of how modular its internal structure may…

Lecture slide element detection and retrieval are key problems in slide understanding. Training effective models for these tasks often depends on extensive manual annotation. However, annotating large volumes of lecture slides for…

Recent advances in large language models show strong promise for formal reasoning. However, most LLM-based theorem provers have long been constrained by the need for expert-written formal statements as inputs, limiting their applicability…

It is well-established that large, diverse datasets play a pivotal role in the performance of modern AI systems for text and image modalities. However, there are no datasets for tabular data of comparable size and diversity to those…

SQL is central to enterprise data engineering, yet generating fully correct SQL code in a single attempt remains difficult, even for experienced developers and advanced text-to-SQL LLMs, often requiring multiple debugging iterations. We…