Related papers: Idioms: Neural Decompilation With Joint Code and T…

We study idiom-based visual puns--images that align an idiom's literal and figurative meanings--and present an iterative framework that coordinates a large language model (LLM), a text-to-image model (T2IM), and a multimodal LLM (MLLM) for…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, due to the lack of domain-specific knowledge, they may not be optimal in completing code that requires intensive domain knowledge for example…

Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating and analyzing counterfactual scenarios, researchers can assess the adaptability and…

Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this.…

The recovery of types from stripped binaries is a key to exact decompilation, yet its practical realization suffers. For composite structures in particular, both layout and semantic fidelity are required to enable end-to-end reconstruction.…

In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrated by Large Language…

LLMs show strong performance in code generation, but their outputs lack correctness guarantees. Sample-based uncertainty estimators address this by generating multiple candidate programs and measuring their disagreement. However, existing…

Enhancing the mathematical reasoning of large language models (LLMs) demands high-quality training data, yet conventional methods face critical challenges in scalability, cost, and data reliability. To address these limitations, we propose…

Maintaining legacy software requires many software and systems engineering hours. Assembly code programs, which demand low-level control over the computer machine state and have no variable names, are particularly difficult for humans to…

In an era of exponential scientific growth, identifying novel research ideas is crucial and challenging in academia. Despite potential, the lack of an appropriate benchmark dataset hinders the research of novelty detection. More…

Ontologies are useful for automatic machine processing of domain knowledge as they represent it in a structured format. Yet, constructing ontologies requires substantial manual effort. To automate part of this process, large language models…

Analyzing third-party software such as malware or firmware is a crucial task for security analysts. Although various approaches for automatic analysis exist and are the subject of ongoing research, analysts often have to resort to manual…

Resolving semantic ambiguity has long been recognised as a central challenge in the field of Machine Translation. Recent work on benchmarking translation performance on ambiguous sentences has exposed the limitations of conventional Neural…

Code-documentation inconsistencies are common and undesirable: they can lead to developer misunderstandings and software defects. This paper introduces DocPrism, a multi-language, code-documentation inconsistency detection tool. DocPrism…

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

Image explanation has been one of the key research interests in the Deep Learning field. Throughout the years, several approaches have been adopted to explain an input image fed by the user. From detecting an object in a given image to…

Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of large language models (LLMs) beyond standalone benchmarks like…