Repository-level code completion aims to generate code for unfinished code snippets within the context of a specified repository. Existing approaches mainly rely on retrievalaugmented generation strategies due to limitations in input sequence length. However, traditional lexical-based retrieval methods like BM25 struggle to capture code semantics, while model-based retrieval methods face challenges due to the lack of labeled data for training. Therefore, we propose RLCoder, a novel reinforcement learning framework, which can enable the retriever to learn to retrieve useful content for code completion without the need for labeled data. Specifically, we iteratively evaluate the usefulness of retrieved content based on the perplexity of the target code when provided with the retrieved content as additional context, and provide feedback to update the retriever parameters. This iterative process enables the retriever to learn from its successes and failures, gradually improving its ability to retrieve relevant and high-quality content. Considering that not all situations require information beyond code files and not all retrieved context is helpful for generation, we also introduce a stop signal mechanism, allowing the retriever to decide when to retrieve and which candidates to retain autonomously. Extensive experimental results demonstrate that RLCoder consistently outperforms state-of-the-art methods on CrossCodeEval and RepoEval, achieving 12.2% EM improvement over previous methods. Moreover, experiments show that our framework can generalize across different programming languages and further improve previous methods like RepoCoder. We provide the code and data at https://github.com/DeepSoftwareAnalytics/RLCoder.

To evaluate the repository-level code generation capabilities of Large Language Models (LLMs) in complex real-world software development scenarios, many evaluation methods have been developed. These methods typically leverage contextual code from the latest version of a project to assist LLMs in accurately generating the desired function. However, such evaluation methods fail to consider the dynamic evolution of software projects over time, which we refer to as evolution-ignored settings. This in turn results in inaccurate evaluation of LLMs' performance. In this paper, we conduct an empirical study to deeply understand LLMs' code generation performance within settings that reflect the evolution nature of software development. To achieve this, we first construct an evolution-aware repository-level code generation dataset, namely HumanEvo, equipped with an automated execution-based evaluation tool. Second, we manually categorize HumanEvo according to dependency levels to more comprehensively analyze the model's performance in generating functions with different dependency levels. Third, we conduct extensive experiments on HumanEvo with seven representative and diverse LLMs to verify the effectiveness of the proposed benchmark. We obtain several important findings through our experimental study. For example, we find that previous evolution-ignored evaluation methods result in inflated performance of LLMs, with performance overestimations ranging from 10.0% to 61.1% under different context acquisition methods, compared to the evolution-aware evaluation approach. Based on the findings, we give actionable suggestions for more realistic evaluation of LLMs on code generation. We also build a shared evolution-aware code generation toolbox to facilitate future research. The replication package including source code and datasets is anonymously available at https://github.Com/DeepSoftwareAnalytics/HumanEvo.

Code generation aims to automatically generate code snippets that meet given natural language requirements and plays an important role in software development. Although Code LLMs have shown excellent performance in this domain, their long generation time poses a signification limitation in practice use. In this paper, we first conduct an in-depth preliminary study with different Code LLMs on code generation task and identify a significant efficiency issue, i.e., continual generation of excess tokens. It harms the developer productivity and leads to huge computational wastes. To address it, we introduce CodeFast, an inference acceleration approach for Code LLMs on code generation. The key idea of CodeFast is to terminate the inference process in time when unnecessary excess tokens are detected. First, we propose an automatic data construction framework to obtain training data. Then, we train a unified lightweight model GenGuard applicable to multiple programming languages to predict whether to terminate inference at the current step. Finally, we enhance Code LLM with GenGuard to accelerate its inference in code generation task. We conduct extensive experiments with CodeFast on five representative Code LLMs across four widely used code generation datasets. Experimental results show that (1) CodeFast can significantly improve the inference speed of various Code LLMs in code generation, ranging form 34% to 452%, without compromising the quality of generated code. (2) CodeFast is stable across different parameter settings and can generalize to untrained datasets. Our code and data are available at https://github.com/DeepSoftwareAnalytics/CodeFast.

Estimating hospital mortality of patients is important in assisting clinicians to make decisions and hospital providers to allocate resources. This paper proposed a multi-task recurrent neural network with attention mechanisms to predict patients' hospital mortality, using reconstruction of patients' physiological time series as an auxiliary task. Experiments were conducted on a large public electronic health record database, i.e., MIMIC-III. Fifteen physiological measurements during the first 24 h of critical care were used to predict death before hospital discharge. Compared with the conventional simplified acute physiology score (SAPS-II), the proposed multi-task learning model achieved better sensitivity (0.503 ± 0.020 versus 0.365 ± 0.021), when predictions were made based on the same 24-h observation period. The multi-task learning model is recommended to be updated daily with at least a 6-h observation period, in order for it to perform similarly or better than the SAPS-II. In the future, the need for intervention can be considered as another task to further optimize the performance of the multi-task learning model.

Body sensors are now commonly used as ingestible, wearable and implantable devices for clinical diagnosis and continuous physiological monitoring. Nevertheless, they usually have limited resources. Recent advancements in technologies provide a possible solution to mitigate the resource limitation of these devices by connecting them with mobile devices and cloud services. To evaluate the feasibility of the cloud-enabled body sensor networks, this paper presents simulation results on testing the feasibility of 24-hour operating time and concurrent user support for the cloud-enabled applications.

Colorectal cancer (CRC) is a leading cause of cancer deaths worldwide. Although polypectomy at early stage reduces CRC incidence, 90% of the polyps are small and diminutive, where removal of them poses risks to patients that may outweigh the benefits. Correctly detecting and predicting polyp type during colonoscopy allows endoscopists to resect and discard the tissue without submitting it for histology, saving time, and costs. Nevertheless, human visual observation of early stage polyps varies. Therefore, this paper aims at developing a fully automatic algorithm to detect and classify hyperplastic and adenomatous colorectal polyps. Adenomatous polyps should be removed, whereas distal diminutive hyperplastic polyps are considered clinically insignificant and may be left in situ . A novel transfer learning application is proposed utilizing features learned from big nonmedical datasets with 1.4-2.5 million images using deep convolutional neural network. The endoscopic images we collected for experiment were taken under random lighting conditions, zooming and optical magnification, including 1104 endoscopic nonpolyp images taken under both white-light and narrowband imaging (NBI) endoscopy and 826 NBI endoscopic polyp images, of which 263 images were hyperplasia and 563 were adenoma as confirmed by histology. The proposed method identified polyp images from nonpolyp images in the beginning followed by predicting the polyp histology. When compared with visual inspection by endoscopists, the results of this study show that the proposed method has similar precision (87.3% versus 86.4%) but a higher recall rate (87.6% versus 77.0%) and a higher accuracy (85.9% versus 74.3%). In conclusion, automatic algorithms can assist endoscopists in identifying polyps that are adenomatous but have been incorrectly judged as hyperplasia and, therefore, enable timely resection of these polyps at an early stage before they develop into invasive cancer.

The recent emergence of indoor wireless communication applications, e.g. WLAN, requires cost effective channel measurement equipments. In this contribution, we present a detailed design of an indoor 2x2 MIMO channel measurement system of 2.4/5.8GHz, using FPGA, PC and some RFICs without any specific instruments. The semi-sequential scheme and sliding correlation method is used for MIMO channel measurement. The design of signal processing algorithms, FPGA firmware and graphical user interface is described.