Related papers: CODEFUSE-DEBENCH: An Empirical Study on Readabilit…
Existing document OCR largely targets plain text or Markdown, discarding the structural and executable properties that make LaTeX essential for scientific publishing. We study page-level reconstruction of scientific PDFs into compilable…
The deployment of Large Language Models (LLMs) for code debugging (e.g., C and Python) is widespread, benefiting from their ability to understand and interpret intricate concepts. However, in the semiconductor industry, utilising LLMs to…
As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and…
While third-party libraries are extensively reused to enhance productivity during software development, they can also introduce potential security risks such as vulnerability propagation. Software composition analysis, proposed to identify…
Locally repairable codes (LRCs) were originally introduced to enable efficient recovery from erasures in distributed storage systems by accessing only a small number of other symbols. While their structural properties-such as bounds and…
Programs are bloated. Our study shows that only 5% of libc is used on average across the Ubuntu Desktop environment (2016 programs); the heaviest user, vlc media player, only needed 18%. In this paper: (1) We present a debloating framework…
The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…
This paper uses the reconstruction-computation-quantization (RCQ) paradigm to decode low-density parity-check (LDPC) codes. RCQ facilitates dynamic non-uniform quantization to achieve good frame error rate (FER) performance with very low…
The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark…
Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparisons among them. Moreover, their evaluations are mostly based…
Disassembly is a challenging task, particularly for obfuscated executables containing junk bytes, which is designed to induce disassembly errors. Existing solutions rely on heuristics or leverage machine learning techniques, but only…
Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code…
Decomposition is a fundamental skill in algorithmic programming, requiring learners to break down complex problems into smaller, manageable parts. However, current self-study methods, such as browsing reference solutions or using LLM…
Binary neural networks have great resource and computing efficiency, while suffer from long training procedure and non-negligible accuracy drops, when comparing to the full-precision counterparts. In this paper, we propose the composite…
Debugging consumes a substantial portion of the software development lifecycle, yet the effectiveness of Large Language Models(LLMs) in this task is not well understood. Competitive programming offers a rich benchmark for such evaluation,…
As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the…
Reverse engineering tools remain monolithic and imperative compared to the advancement of modern compiler architectures: analyses are tied to a single mutable representation, making them difficult to extend or refine, and forcing premature…
The evaluation of code-generating Large Language Models (LLMs) is fundamentally constrained by two intertwined challenges: a reliance on static, easily contaminated problem sources and the use of superficial, low-rigor testing. This paper…
Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations,…
Mathematical reasoning requires abstracting symbolic rules from visual patterns -- inferring the infinite from the finite. We investigate whether multimodal AI systems possess this capability through FractalBench, a benchmark evaluating…