Related papers: FastCode: Fast and Cost-Efficient Code Understandi…

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while…

Large Language Models (LLMs) have recently emerged as capable coding assistants that operate over large codebases through either agentic exploration or full-context generation. Existing benchmarks capture a broad range of coding…

Mining textual patterns in news, tweets, papers, and many other kinds of text corpora has been an active theme in text mining and NLP research. Previous studies adopt a dependency parsing-based pattern discovery approach. However, the…

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, repository-level code generation presents unique challenges, particularly due to the need to utilize information spread across…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

The understanding of large-scale scientific software poses significant challenges due to its diverse codebase, extensive code length, and target computing architectures. The emergence of generative AI, specifically large language models…

Software clones are beneficial to detect security gaps and software maintenance in one programming language or across multiple languages. The existing work on source clone detection performs well but in a single programming language.…

Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various sparse attention…

Root cause analysis in a large-scale production environment is challenging due to the complexity of services running across global data centers. Due to the distributed nature of a large-scale system, the various hardware, software, and…

Large language model (LLM) routers improve the efficiency of multi-model systems by directing each query to the most appropriate model while leveraging the diverse strengths of heterogeneous LLMs. Most existing approaches frame routing as a…

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the…

This paper proposes Fulcrum network codes, a network coding framework that achieves three seemingly conflicting objectives: (i) to reduce the coding coefficient overhead to almost n bits per packet in a generation of n packets; (ii) to…

As text and code resources have expanded, large-scale pre-trained models have shown promising capabilities in code generation tasks, typically employing supervised fine-tuning with problem statement-program pairs. However, increasing model…

Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads…

Modern language models (LMs) have been successfully employed in source code generation and understanding, leading to a significant increase in research focused on learning-based code intelligence, such as automated bug repair, and test case…

The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit…

Code writing is repetitive and predictable, inspiring us to develop various code intelligence techniques. This survey focuses on code search, that is, to retrieve code that matches a given query by effectively capturing the semantic…

Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation.…

Despite recent advances, Large Language Models (LLMs) still generate vulnerable code. Retrieval-Augmented Generation (RAG) has the potential to enhance LLMs for secure code generation by incorporating external security knowledge. However,…

Code search aims to retrieve semantically relevant code snippets for natural language queries. While pre-trained language models (PLMs) have shown remarkable performance in this task, they struggle in cross-domain scenarios, often requiring…