Related papers: Expression Templates Revisited: A Performance Anal…

Large Language Models (LLMs) have emerged as a promising alternative to traditional static program analysis methods, such as symbolic execution, offering the ability to reason over code directly without relying on theorem provers or SMT…

Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel…

Since the advent of Large Language Models a few years ago, they have often been considered the de facto solution for many AI problems. However, in addition to the many deficiencies of LLMs that prevent them from broad industry adoption,…

From the discovery that the template system of C++ forms a Turing complete language in 1994, a programming technique called Template Metaprogramming has emerged that allows for the creation of faster, more generic and better code. Here, we…

Constructing Extract-Load-Transform (ELT) pipelines is a labor-intensive data engineering task and a high-impact target for AI automation. On ELT-Bench, the first benchmark for end-to-end ELT pipeline construction, AI agents initially…

Current approaches to question answering rely on pre-trained language models (PLMs) like RoBERTa. This work challenges the existing question-answer encoding convention and explores finer representations. We begin with testing various…

Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique. Despite this progress, their reasoning is often constrained by their intrinsic understanding, lacking…

The traditional abstract domain framework for imperative programs suffers from several shortcomings; in particular it does not allow precise symbolic abstractions. To solve these problems, we propose a new abstract interpretation framework,…

Transformers have revolutionized the machine learning landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being…

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…

Automatically generating formal specifications including loop invariants, preconditions, and postconditions for legacy code is critical for program understanding, reuse and verification. However, the inherent complexity of control and data…

One of the key requirements for the Lattice QCD Application Development as part of the US Exascale Computing Project is performance portability across multiple architectures. Using the Grid C++ expression template as a starting point, we…

Large language models (LLMs) have revolutionized natural language processing with their exceptional understanding, synthesizing, and reasoning capabilities. However, deploying LLMs on resource-constrained edge devices presents significant…

The task of inferring logical formulas from examples has garnered significant attention as a means to assist engineers in creating formal specifications used in the design, synthesis, and verification of computing systems. Among various…

Large, self-supervised transformer-based language representation models have recently received significant amounts of attention, and have produced state-of-the-art results across a variety of tasks simply by scaling up pre-training on…

Code generation models can benefit data scientists' productivity by automatically generating code from context and text descriptions. An important measure of the modeling progress is whether a model can generate code that can correctly…

Empathetic conversation is a crucial characteristic in daily conversations between individuals. Nowadays, Large Language models (LLMs) have shown outstanding performance in generating empathetic responses. Knowledge bases like COMET can…

Control planes of cloud frameworks trade off between scheduling granularity and performance. Centralized systems schedule at task granularity, but only schedule a few thousand tasks per second. Distributed systems schedule hundreds of…

Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…