Related papers: Beyond Function-Level Search: Repository-Aware Dua…

Source code search plays an important role in software development, e.g. for exploratory development or opportunistic reuse of existing code from a code base. Often, exploration of different implementations with the same functionality is…

Despite recent advances in inversion and instruction-based image editing, existing approaches primarily excel at editing single, prominent objects but significantly struggle when applied to complex scenes containing multiple entities. To…

Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evaluate code agents in such authentic, workflow-driven scenarios.…

Analog circuit design relies heavily on reusing existing intellectual property (IP), yet searching across heterogeneous representations such as SPICE netlists, schematics, and functional descriptions remains challenging. Existing methods…

We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contrastive training by splitting source code randomly into…

Code retrieval is allowing software engineers to search codes through a natural language query, which relies on both natural language processing and software engineering techniques. There have been several attempts on code retrieval from…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

In this paper, we propose the CodeRetriever model, which learns the function-level code semantic representations through large-scale code-text contrastive pre-training. We adopt two contrastive learning schemes in CodeRetriever: unimodal…

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

Recent advances in large language models (LLMs) have significantly improved automated code generation. While existing approaches have achieved strong performance at the function and file levels, real-world software engineering requires…

Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description. Existing REC benchmarks primarily evaluate perceptual capabilities and lack interpretable scoring…

While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate…

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative…

Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection…

Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a…

Evaluation of repository-aware software engineering systems is often confounded by synthetic task design, prompt leakage, and temporal contamination between repository knowledge and future code changes. We present a time-consistent…

The ability to reason is one of the most fundamental capabilities of large language models (LLMs), enabling a wide range of downstream tasks through sophisticated problem-solving. A critical aspect of this is code reasoning, which involves…

In models to generate program source code from natural language, representing this code in a tree structure has been a common approach. However, existing methods often fail to generate complex code correctly due to a lack of ability to…

Repository-level code completion remains challenging for large language models (LLMs) due to cross-file dependencies and limited context windows. Prior work addresses this challenge using Retrieval-Augmented Generation (RAG) frameworks…