Related papers: LEGO-Compiler: Enhancing Neural Compilation Throug…

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…

Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large Language Models (LLMs) have shown promise in automating…

Large Language Models (LLMs) have demonstrated remarkable capabilities in solving various tasks, yet they often struggle with comprehensively addressing complex and vague problems. Existing approaches, including multi-agent LLM systems,…

Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods using language models have demonstrated promising results,…

Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable,…

Large Language Models have demonstrated a remarkable capability in natural language and program generation and software development. However, the source code generated by the LLMs does not always meet quality requirements and may fail to…

Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering. Existing deep-learning approaches model code…

This study explores the capabilities of multimodal large language models (LLMs) in handling challenging multistep tasks that integrate language and vision, focusing on model steerability, composability, and the application of long-term…

The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated texts. They serve as scalable and economical evaluators, but the question of how reliable these evaluators are has emerged as…

Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precise object state detection are required. In this work, we…

Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to lower-level programming languages, such as assembly. We propose a synthetic data generation method named C-ing Clearly,…

We introduce a novel paradigm in compiler optimization powered by Large Language Models with compiler feedback to optimize the code size of LLVM assembly. The model takes unoptimized LLVM IR as input and produces optimized IR, the best…

Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software…

Combinatorial optimization (CO) is essential for improving efficiency and performance in engineering applications. As complexity increases with larger problem sizes and more intricate dependencies, identifying the optimal solution become…

Large Language Models (LLMs) have become extremely potent instruments with exceptional capacities for comprehending and producing human-like text in a wide range of applications. However, the increasing size and complexity of LLMs present…

Intermediate Representations (IRs) play a critical role in compiler design and program analysis, yet their comprehension by Large Language Models (LLMs) remains underexplored. In this paper, we present an explorative empirical study…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models (LLMs) for code translation. However, existing LLMs only…

Compilation is an important process in developing configurable systems, such as Linux. However, identifying compilation errors in configurable systems is not straightforward because traditional compilers are not variability-aware. Previous…

Since their inception, programming languages have trended towards greater readability and lower barriers for programmers. Following this trend, natural language can be a promising type of programming language that provides great flexibility…