Search

Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into popular intelligent IDEs like JetBrains and Cursor. Current benchmarks for evaluating models' code comprehension capabilities primarily focus on code generation or completion, often neglecting QA, which is a crucial aspect of understanding code. Existing code QA benchmarks are derived from code comments with predefined patterns (e.g., CodeQA) or focus on specific domains, such as education (e.g., CS1QA). These benchmarks fail to capture the real-world complexity of software engineering and user requirements for understanding code repositories. To address this gap, we introduce CoReQA, a benchmark for Code Repository-level question answering, constructed from GitHub issues and comments from 176 popular repositories across four programming languages. Since questions and answers may include both natural language and code snippets, traditional evaluation metrics such as BLEU are inadequate for assessing repository-level QA performance. Thus, we provide an LLM-as-a-judge framework to evaluate QA performance from five aspects. Based on CoReQA, we evaluate the performance of three baselines, including two short-context models using generic retrieval strategies and one long-context model that utilizes the entire repository context. Evaluation results show that state-of-the-art proprietary and long-context models struggle to address repository-level questions effectively. Our analysis highlights the limitations of language models in assisting developers in understanding repositories and suggests future directions for improving repository comprehension systems through effective context retrieval methodologies., Comment: 12 pages, 7 figures, 8 tables

The Go programming language has gained significant traction for developing software, especially in various infrastructure systems. Nonetheless, concurrency bugs have become a prevalent issue within Go, presenting a unique challenge due to the language's dual concurrency mechanisms-communicating sequential processes and shared memory. Detecting concurrency bugs and accurately classifying program executions as pass or fail presents an immense challenge, even for domain experts. We conducted a survey with expert developers at Bytedance that confirmed this challenge. Our work seeks to address the test oracle problem for Go programs, to automatically classify test executions as pass or fail. This problem has not been investigated in the literature for Go programs owing to its distinctive programming model. Our approach involves collecting both passing and failing execution traces from various subject Go programs. We capture a comprehensive array of execution events using the native Go execution tracer. Subsequently, we preprocess and encode these traces before training a transformer-based neural network to effectively classify the traces as either passing or failing. The evaluation of our approach encompasses 8 subject programs sourced from the GoBench repository. These subject programs are routinely used as benchmarks in an industry setting. Encouragingly, our test oracle, Go-Oracle, demonstrates high accuracies even when operating with a limited dataset, showcasing the efficacy and potential of our methodology. Developers at Bytedance strongly agreed that they would use the Go-Oracle tool over the current practice of manual inspections to classify tests for Go programs as pass or fail.

We present an analysis of the structure, kinematics, and chemo-dynamical properties of the Milky Way bulge using data from OGLE, APOGEE, and Gaia. Firstly, we identified 2,156 ab-type RR Lyrae stars (RRabs) from OGLE-IV, then through their apocenters derived from orbital integration, we distinguished three populations: the central bulge RRabs, the inner bulge RRabs and halo interlopers. Inner bulge RRabs kinematically align with the Galactic bar, while central bulge RRabs show slower rotation with lower velocity dispersion, which do not trace the bar. Higher velocity dispersion stars were identified as halo interlopers. Then, orbital analysis of 28,188 APOGEE Red Clump and Red Giant Branch stars revealed kinematic properties consistent with RRabs, and chemical abundance distribution displayed a bimodal stellar density pattern, suggesting complex star evolution histories and also slightly different star formation histories for the inner bulge and central bulge. The differences in the density distribution on the $|\mathrm{Z}|_{\text{max}}$-eccentricity plane for the central bulge, inner bulge, and halo regions are clearly detected. Finally, the chemodynamical analysis of 301,485 Gaia DR3 red giants without orbital integration indicated that metal-rich bulge stars form a bar-like structure, while metal-poor bulge stars are dominated by velocity dispersion. It is found that the classification of bulge stars based on orbital parameters, rather than solely on metallicity, provides a more accurate population separation. Our results also support that secular evolution of the Galactic disk is the primary origin of the bulge, and boxy/peanut (B-P) bulge population might be more dominant than X-shape bulge population., Comment: 24 pages, 20 figures

Inconsistent responses of X-ray detector elements lead to stripe artifacts in the sinogram data, which manifest as ring artifacts in the reconstructed CT images, severely degrading image quality. This paper proposes a method for correcting stripe artifacts in the sinogram data. The proposed method leverages implicit neural representation (INR) to correct defective pixel response values using implicit continuous functions and simultaneously learns stripe features in the angular direction of the sinogram data. These two components are combined within an optimization constraint framework, achieving unsupervised iterative correction of stripe artifacts in the projection domain. Experimental results demonstrate that the proposed method significantly outperforms current state-of-the-art techniques in removing ring artifacts while maintaining the clarity of CT images., Comment: 10 pages, 11 figures

With the growing reliance on automated code completion tools in software development, the need for robust evaluation benchmarks has become critical. However, existing benchmarks focus more on code generation tasks in function and class level and provide rich text description to prompt the model. By contrast, such descriptive prompt is commonly unavailable in real development and code completion can occur in wider range of situations such as in the middle of a function or a code block. These limitations makes the evaluation poorly align with the practical scenarios of code completion tools. In this paper, we propose RepoMasterEval, a novel benchmark for evaluating code completion models constructed from real-world Python and TypeScript repositories. Each benchmark datum is generated by masking a code snippet (ground truth) from one source code file with existing test suites. To improve test accuracy of model generated code, we employ mutation testing to measure the effectiveness of the test cases and we manually crafted new test cases for those test suites with low mutation score. Our empirical evaluation on 6 state-of-the-art models shows that test argumentation is critical in improving the accuracy of the benchmark and RepoMasterEval is able to report difference in model performance in real-world scenarios. The deployment of RepoMasterEval in a collaborated company for one month also revealed that the benchmark is useful to give accurate feedback during model training and the score is in high correlation with the model's performance in practice. Based on our findings, we call for the software engineering community to build more LLM benchmarks tailored for code generation tools taking the practical and complex development environment into consideration.

Recent years have seen the development of LLM-based code generation. Compared to generating code in a software project, incremental code edits are empirically observed to be more frequent. The emerging code editing approaches usually formulate the problem as generating an edit based on known relevant prior edits and context. However, practical code edits can be more complicated. First, an editing session can include multiple (ir)relevant edits to the code under edit. Second, the inference of the subsequent edits is non-trivial as the scope of its ripple effect can be the whole project. In this work, we propose CoEdPilot, an LLM-driven solution to recommend code edits by discriminating the relevant edits, exploring their interactive natures, and estimating its ripple effect in the project. Specifically, CoEdPilot orchestrates multiple neural transformers to identify what and how to edit in the project regarding both edit location and edit content. When a user accomplishes an edit with an optional editing description, a Subsequent Edit Analysis first reports the most relevant files in the project with what types of edits (e.g., keep, insert, and replace) can happen for each line of their code. Next, an Edit-content Generator generates concrete edit options for the lines of code, regarding its relevant prior changes reported by an Edit-dependency Analyzer. Lastly, both the Subsequent Edit Analysis and the Edit-content Generator capture relevant prior edits as feedback to readjust their recommendations. We train our models by collecting over 180K commits from 471 open-source projects in 5 programming languages. Our extensive experiments show that CoEdPilot can well predict the edits (i.e., predicting edit location with an accuracy of 70.8%-85.3%, and the edit content with an exact match rate of 41.8% and BLEU4 score of 60.7)..., Comment: 13 pages, 7 figures

Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development, marked by frequent library updates. This gap significantly limits LLMs' deployment in realistic settings. In this paper, we propose two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM). In conjunction, we introduce VersiCode, a comprehensive Python dataset specifically designed to evaluate LLMs on these two tasks, together with a novel evaluation metric, Critical Diff Check (CDC@1), which assesses code generation against evolving API requirements. We conduct an extensive evaluation on VersiCode, which reveals that version-controllable code generation is indeed a significant challenge, even for GPT-4o and other strong frontier models. We believe the novel tasks, dataset, and metric open up a new, important research direction that will further enhance LLMs' real-world applicability. The code and resources can be found at https://github.com/wutong8023/VersiCode.

In spectral CT reconstruction, the basis materials decomposition involves solving a large-scale nonlinear system of integral equations, which is highly ill-posed mathematically. This paper proposes a model that parameterizes the attenuation coefficients of the object using a neural field representation, thereby avoiding the complex calculations of pixel-driven projection coefficient matrices during the discretization process of line integrals. It introduces a lightweight discretization method for line integrals based on a ray-driven neural field, enhancing the accuracy of the integral approximation during the discretization process. The basis materials are represented as continuous vector-valued implicit functions to establish a neural field parameterization model for the basis materials. The auto-differentiation framework of deep learning is then used to solve the implicit continuous function of the neural base-material fields. This method is not limited by the spatial resolution of reconstructed images, and the network has compact and regular properties. Experimental validation shows that our method performs exceptionally well in addressing the spectral CT reconstruction. Additionally, it fulfils the requirements for the generation of high-resolution reconstruction images., Comment: 14 pages,16 figures

Wireless communication is rapidly evolving, and future wireless communications (6G and beyond) will be more heterogeneous, multi-layered, and complex, which poses challenges to traditional communications. Adaptive technologies in traditional communication systems respond to environmental changes by modifying system parameters and structures on their own and are not flexible and agile enough to satisfy requirements in future communications. To tackle these challenges, we propose a novel self-evolving communication framework, which consists of three layers: data layer, information layer, and knowledge layer. The first two layers allow communication systems to sense environments, fuse data, and generate a knowledge base for the knowledge layer. When dealing with a variety of application scenarios and environments, the generated knowledge is subsequently fed back to the first two layers for communication in practical application scenarios to obtain self-evolving ability and enhance the robustness of the system. In this paper, we first highlight the limitations of current adaptive communication systems and the need for intelligence, automation, and self-evolution in future wireless communications. We overview the development of self-evolving technologies and conceive the concept of self-evolving communications with its hypothetical architecture. To demonstrate the power of self-evolving modules, we compare the performances of a communication system with and without evolution. We then provide some potential techniques that enable self-evolving communications and challenges in implementing them.

Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities. However, existing benchmarks predominantly focused on simplified or isolated aspects of coding, such as single-file code generation or repository issue debugging, falling short of measuring the full spectrum of challenges raised by real-world programming activities. In this case study, we explore the performance of LLMs across the entire software development lifecycle with DevEval, encompassing stages including software design, environment setup, implementation, acceptance testing, and unit testing. DevEval features four programming languages, multiple domains, high-quality data collection, and carefully designed and verified metrics for each task. Empirical studies show that current LLMs, including GPT-4, fail to solve the challenges presented within DevEval. Our findings offer actionable insights for the future development of LLMs toward real-world programming applications., Comment: Our data and code are available at https://github.com/open-compass/DevEval

Topotactic reduction utilizing metal hydrides as reagents emerges as an effective approach to achieve exceptionally low oxidization states of metal ions and unconventional coordination networks. This method opens avenues to the development of entirely new functional materials, with one notable example being the infinite-layer nickelate superconductors. However, the reduction effect on the atomic reconstruction and electronic structures -- crucial for superconductivity -- remains largely unresolved. We design two sets of control Nd$_{0.8}$Sr$_{0.2}$NiO$_2$ thin films and implement secondary ion mass spectroscopy to highlight the absence of reduction-induced hydrogen intercalation. X-ray absorption spectroscopy shows a significant linear dichroism with dominant Ni 3d$_{x2{-}y2}$ orbitals on superconducting samples, indicating a Ni single-band nature of infinite-layer nickelates. Consistent with the superconducting $T_c$, the Ni 3d orbitals asymmetry manifests a dome-like reduction duration dependence. Our results unveil the critical role of reduction in modulating the Ni-3d orbital polarization and its impact on the superconducting properties., Comment: Main: 21 pages, 4 figure - Supplementary: 7 pages, 5 figure

Simulating the cold $^{87}Rb$ atom with a three-level quantum system interacting with two orthogonal standing-wave fields, the localization within half-wavelength domain in the x-y plane is achieved by monitoring the probe absorption. Within the half-wavelength domain, the single absorption peak increases from 0.2 to 1.0 via the spontaneously generated coherence (SGC), while the diameters of the single absorption peaks are diminished by the increasing incoherent pumping field. Our scheme provides the flexible parameters manipulating manner for the localization of cold $^{87}Rb$ atom., Comment: 10 pages, 5 figures

The atom localization of a V-type atomic system is discussed by the detunings associated with the probe and the two orthogonal standing-wave fields, and by the spontaneously generated coherence (SGC). Within the half-wavelength domain in the 2-dimensional(2-D) plane, the atom localization depicted by the probe dual absorption peaks is achieved when the detunings are tuned. However, the dual peaks change into single-peak when the SGC arises. The single-peak 2-D localization demonstrated the advantage for atom localization achieved by the flexible manipulating parameters in our scheme., Comment: 0 pages, 6 figures

We present a novel, deep-learning based method -- dubbed Galactic-Seismology Substructures and Streams Hunter, or GS$^{3}$ Hunter for short, to search for substructures and streams in stellar kinematics data. GS$^{3}$ Hunter relies on a combined application of Siamese Neural Networks to transform the phase space information and the K-means algorithm for the clustering. As a validation test, we apply GS$^{3}$ Hunter to a subset of the Feedback in Realistic Environments (FIRE) cosmological simulations. The stellar streams and substructures thus identified are in good agreement with corresponding results reported earlier by the FIRE team. In the same vein, we apply our method to a subset of local halo stars from the Gaia Early Data Release 3 and GALAH DR3 datasets, and recover several, previously known dynamical groups, such as Thamnos 1+2, Hot Thick Disk, ED-1, L-RL3, Helmi 1+2, and Gaia-Sausage-Enceladus, Sequoia, VRM, Cronus, Nereus. Finally, we apply our method without fine-tuning to a subset of K-giant stars located in the inner halo region, obtained from the LAMOST Data Release 5 (DR5) dataset. We recover three, previously known structures (Sagittarius, Hercules-Aquila Cloud, and the Virgo Overdensity), but we also discover a number of new substructures. We anticipate that GS$^{3}$ Hunter will become a useful tool for the community dedicated to the search of stellar streams and structures in the Milky Way (MW) and the Local group, thus helping advance our understanding of the stellar inner and outer halos, and of the assembly and tidal stripping history in and around the MW., Comment: 41 pages, 34 figures, 3 tables. Accepted for Publication in the Astrophysical Journal