Search

How to evaluate Large Language Models (LLMs) in code generation is an open question. Many benchmarks have been proposed but are inconsistent with practical software projects, e.g., unreal program distributions, insufficient dependencies, and small-scale project contexts. Thus, the capabilities of LLMs in practical projects are still unclear. In this paper, we propose a new benchmark named DevEval, aligned with Developers' experiences in practical projects. DevEval is collected through a rigorous pipeline, containing 2,690 samples from 119 practical projects and covering 10 domains. Compared to previous benchmarks, DevEval aligns to practical projects in multiple dimensions, e.g., real program distributions, sufficient dependencies, and enough-scale project contexts. We assess five popular LLMs on DevEval (e.g., gpt-4, gpt-3.5-turbo, CodeLLaMa, and StarCoder) and reveal their actual abilities in code generation. For instance, the highest Pass@1 of gpt-3.5-turbo only is 42 in our experiments. We also discuss the challenges and future directions of code generation in practical projects. We open-source DevEval and hope it can facilitate the development of code generation in practical projects., Comment: We are re-checking this benchmark and repeating related experiments. New versions of DevEval will be released later

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. To address the knowledge gap, we propose a new benchmark named DevEval, which has three advances. (1) DevEval aligns with real-world repositories in multiple dimensions, e.g., code distributions and dependency distributions. (2) DevEval is annotated by 13 developers and contains comprehensive annotations (e.g., requirements, original repositories, reference code, and reference dependencies). (3) DevEval comprises 1,874 testing samples from 117 repositories, covering 10 popular domains (e.g., Internet, Database). Based on DevEval, we propose repository-level code generation and evaluate 8 popular LLMs on DevEval (e.g., gpt-4, gpt-3.5, StarCoder 2, DeepSeek Coder, CodeLLaMa). Our experiments reveal these LLMs' coding abilities in real-world code repositories. For example, in our experiments, the highest Pass@1 of gpt-4-turbo is only 53.04%. We also analyze LLMs' failed cases and summarize their shortcomings. We hope DevEval can facilitate the development of LLMs in real code repositories. DevEval, prompts, and LLMs' predictions have been released., Comment: Accepted by the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024). arXiv admin note: substantial text overlap with arXiv:2404.00599, arXiv:2401.06401

Many eye diseases like Diabetic Macular Edema (DME), Age-related Macular Degeneration (AMD), and Glaucoma manifest in the retina, can cause irreversible blindness or severely impair the central version. The Optical Coherence Tomography (OCT), a 3D scan of the retina with high qualitative information about the retinal morphology, can be used to diagnose and monitor changes in the retinal anatomy. Many Deep Learning (DL) methods have shared the success of developing an automated tool to monitor pathological changes in the retina. However, the success of these methods depend mainly on large datasets. To address the challenge from very small and limited datasets, we proposed a DL architecture termed CoNet (Coherent Network) for joint segmentation of layers and fluids in retinal OCT images on very small datasets (less than a hundred training samples). The proposed model was evaluated on the publicly available Duke DME dataset consisting of 110 B-Scans from 10 patients suffering from DME. Experimental results show that the proposed model outperformed both the human experts' annotation and the current state-of-the-art architectures by a clear margin with a mean Dice Score of 88% when trained on 55 images without any data augmentation., Comment: Submitted to Bioimaging 2023

Retinal Optical Coherence Tomography (OCT), a noninvasive cross-sectional scan of the eye with qualitative 3D visualization of the retinal anatomy is use to study the retinal structure and the presence of pathogens. The advent of the retinal OCT has transformed ophthalmology and it is currently paramount for the diagnosis, monitoring and treatment of many eye pathogens including Macular Edema which impairs vision severely or Glaucoma that can cause irreversible blindness. However the quality of retinal OCT images varies among device manufacturers. Deep Learning methods have had their success in the medical image segmentation community but it is still not clear if the level of success can be generalised across OCT images collected from different device vendors. In this work we propose two variants of the nnUNet [8]. The standard nnUNet and an enhanced vision call nnUnet_RASPP (nnU-Net with residual and Atrous Spatial Pyramid Pooling) both of which are robust and generalise with consistent high performance across images from multiple device vendors. The algorithm was validated on the MICCAI 2017 RETOUCH challenge dataset [1] acquired from 3 device vendors across 3 medical centers from patients suffering from 2 retinal disease types. Experimental results show that our algorithms outperform the current state-of-the-arts algorithms by a clear margin for segmentation obtaining a mean Dice Score (DS) of 82.3% for the 3 retinal fluids scoring 84.0%, 80.0%, 83.0% for Intraretinal Fluid (IRF), Subretinal Fluid (SRF), and Pigment Epithelium Detachments (PED) respectively on the testing dataset. Also we obtained a perfect Area Under the Curve (AUC) score of 100% for the detection of the presence of fluid for all 3 fluid classes on the testing dataset., Comment: 25 pages, 14 figures and 5 tables

Recently, deep learning techniques have shown great success in automatic code generation. Inspired by the code reuse, some researchers propose copy-based approaches that can copy the content from similar code snippets to obtain better performance. Practically, human developers recognize the content in the similar code that is relevant to their needs, which can be viewed as a code sketch. The sketch is further edited to the desired code. However, existing copy-based approaches ignore the code sketches and tend to repeat the similar code without necessary modifications, which leads to generating wrong results. In this paper, we propose a sketch-based code generation approach named SkCoder to mimic developers' code reuse behavior. Given a natural language requirement, SkCoder retrieves a similar code snippet, extracts relevant parts as a code sketch, and edits the sketch into the desired code. Our motivations are that the extracted sketch provides a well-formed pattern for telling models "how to write". The post-editing further adds requirement-specific details to the sketch and outputs the complete code. We conduct experiments on two public datasets and a new dataset collected by this work. We compare our approach to 20 baselines using 5 widely used metrics. Experimental results show that (1) SkCoder can generate more correct programs, and outperforms the state-of-the-art - CodeT5-base by 30.30%, 35.39%, and 29.62% on three datasets. (2) Our approach is effective to multiple code generation models and improves them by up to 120.1% in Pass@1. (3) We investigate three plausible code sketches and discuss the importance of sketches. (4) We manually evaluate the generated code and prove the superiority of our SkCoder in three aspects., Comment: Accepted by the 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023)

Cancerous skin lesions are one of the most common malignancies detected in humans, and if not detected at an early stage, they can lead to death. Therefore, it is crucial to have access to accurate results early on to optimize the chances of survival. Unfortunately, accurate results are typically obtained by highly trained dermatologists, who may not be accessible to many people, particularly in low-income and middle-income countries. Artificial Intelligence (AI) appears to be a potential solution to this problem, as it has proven to provide equal or even better diagnoses than healthcare professionals. This project aims to address the issue by collecting state-of-the-art techniques for image classification from various fields and implementing them. Some of these techniques include mixup, presizing, and test-time augmentation, among others. Three architectures were used for the implementation: DenseNet121, VGG16 with batch normalization, and ResNet50. The models were designed with two main purposes. First, to classify images into seven categories, including melanocytic nevus, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses and intraepithelial carcinoma, vascular lesions, and dermatofibroma. Second, to classify images into benign or malignant. The models were trained using a dataset of 8012 images, and their performance was evaluated using 2003 images. It's worth noting that this model is trained end-to-end, directly from the image to the labels, without the need for handcrafted feature extraction.

Large Language Models (LLMs) (e.g., ChatGPT) have shown impressive performance in code generation. LLMs take prompts as inputs, and Chain-of-Thought (CoT) prompting is the state-of-the-art prompting technique. CoT prompting asks LLMs first to generate CoTs (i.e., intermediate natural language reasoning steps) and then output the code. However, CoT prompting is designed for natural language generation and has low accuracy in code generation. In this paper, we propose Structured CoTs (SCoTs) and present a novel prompting technique for code generation, named SCoT prompting. Our motivation is source code contains rich structural information and any code can be composed of three program structures (i.e., sequence, branch, and loop structures). Intuitively, structured intermediate reasoning steps make for structured source code. Thus, we ask LLMs to use program structures to build CoTs, obtaining SCoTs. Then, LLMs generate the final code based on SCoTs. Compared to CoT prompting, SCoT prompting explicitly constrains LLMs to think about how to solve requirements from the view of source code and further the performance of LLMs in code generation. We apply SCoT prompting to two LLMs (i.e., ChatGPT and Codex) and evaluate it on three benchmarks (i.e., HumanEval, MBPP, and MBCPP). (1) SCoT prompting outperforms the state-of-the-art baseline - CoT prompting by up to 13.79% in Pass@1. (2) Human evaluation shows human developers prefer programs from SCoT prompting. (3) SCoT prompting is robust to examples and achieves substantial improvements., Comment: arXiv admin note: text overlap with arXiv:2303.17780

Large Language Models (LLMs) have shown great success in code generation. LLMs take as the input a prompt and output the code. A key question is how to make prompts (i.e., Prompting Techniques). Existing prompting techniques are designed for natural language generation and have low accuracy in code generation. In this paper, we propose a new prompting technique named AceCoder. Our motivation is that code generation meets two unique challenges (i.e., requirement understanding and code implementation). AceCoder contains two novel mechanisms (i.e., guided code generation and example retrieval) to solve these challenges. (1) Guided code generation asks LLMs first to analyze requirements and output an intermediate preliminary (e.g., test cases). The preliminary is used to clarify requirements and tell LLMs "what to write". (2) Example retrieval selects similar programs as examples in prompts, which provide lots of relevant content (e.g., algorithms, APIs) and teach LLMs "how to write". We apply AceCoder to three LLMs (e.g., Codex) and evaluate it on three public benchmarks using the Pass@k. Results show that AceCoder can significantly improve the performance of LLMs on code generation. (1) In terms of Pass@1, AceCoder outperforms the state-of-the-art baseline by up to 56.4% in MBPP, 70.7% in MBJP, and 88.4% in MBJSP. (2) AceCoder is effective in LLMs with different sizes (i.e., 6B to 13B) and different languages (i.e., Python, Java, and JavaScript). (3) Human evaluation shows human developers prefer programs from AceCoder.

The morphology of retinal blood vessels can indicate various diseases in the human body, and researchers have been working on automatic scanning and segmentation of retinal images to aid diagnosis. This project compares the performance of four neural network architectures in segmenting retinal images, using a combined dataset from different databases, namely the UNet, DR-VNet, UNet-ResNet and UNet-VGG.

Radiation therapy is a primary and effective NasoPharyngeal Carcinoma (NPC) treatment strategy. The precise delineation of Gross Tumor Volumes (GTVs) and Organs-At-Risk (OARs) is crucial in radiation treatment, directly impacting patient prognosis. Previously, the delineation of GTVs and OARs was performed by experienced radiation oncologists. Recently, deep learning has achieved promising results in many medical image segmentation tasks. However, for NPC OARs and GTVs segmentation, few public datasets are available for model development and evaluation. To alleviate this problem, the SegRap2023 challenge was organized in conjunction with MICCAI2023 and presented a large-scale benchmark for OAR and GTV segmentation with 400 Computed Tomography (CT) scans from 200 NPC patients, each with a pair of pre-aligned non-contrast and contrast-enhanced CT scans. The challenge's goal was to segment 45 OARs and 2 GTVs from the paired CT scans. In this paper, we detail the challenge and analyze the solutions of all participants. The average Dice similarity coefficient scores for all submissions ranged from 76.68\% to 86.70\%, and 70.42\% to 73.44\% for OARs and GTVs, respectively. We conclude that the segmentation of large-size OARs is well-addressed, and more efforts are needed for GTVs and small-size or thin-structure OARs. The benchmark will remain publicly available here: https://segrap2023.grand-challenge.org, Comment: A challenge report of SegRap2023 (organized in conjunction with MICCAI2023)

Our study introduces a new image-to-video generator called FashionFlow to generate fashion videos. By utilising a diffusion model, we are able to create short videos from still fashion images. Our approach involves developing and connecting relevant components with the diffusion model, which results in the creation of high-fidelity videos that are aligned with the conditional image. The components include the use of pseudo-3D convolutional layers to generate videos efficiently. VAE and CLIP encoders capture vital characteristics from still images to condition the diffusion model at a global level. Our research demonstrates a successful synthesis of fashion videos featuring models posing from various angles, showcasing the fit and appearance of the garment. Our findings hold great promise for improving and enhancing the shopping experience for the online fashion industry.

Medical imaging plays a crucial role in modern healthcare by providing non-invasive visualisation of internal structures and abnormalities, enabling early disease detection, accurate diagnosis, and treatment planning. This study aims to explore the application of deep learning models, particularly focusing on the UNet architecture and its variants, in medical image segmentation. We seek to evaluate the performance of these models across various challenging medical image segmentation tasks, addressing issues such as image normalization, resizing, architecture choices, loss function design, and hyperparameter tuning. The findings reveal that the standard UNet, when extended with a deep network layer, is a proficient medical image segmentation model, while the Res-UNet and Attention Res-UNet architectures demonstrate smoother convergence and superior performance, particularly when handling fine image details. The study also addresses the challenge of high class imbalance through careful preprocessing and loss function definitions. We anticipate that the results of this study will provide useful insights for researchers seeking to apply these models to new medical imaging problems and offer guidance and best practices for their implementation.

Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects. Code summarization aims to generate natural language descriptions automatically for source code. Code summaries are highly structured and have repetitive patterns. Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code. However, the state-of-the-art approaches perform poorly on predicting the keywords, which leads to the generated summaries suffering a loss in informativeness. To alleviate this problem, this paper proposes a novel retrieve-and-edit approach named EditSum for code summarization. Specifically, EditSum first retrieves a similar code snippet from a pre-defined corpus and treats its summary as a prototype summary to learn the pattern. Then, EditSum edits the prototype automatically to combine the pattern in the prototype with the semantic information of input code. Our motivation is that the retrieved prototype provides a good start-point for post-generation because the summaries of similar code snippets often have the same pattern. The post-editing process further reuses the patternized words in the prototype and generates keywords based on the semantic information of input code. We conduct experiments on a large-scale Java corpus and experimental results demonstrate that EditSum outperforms the state-of-the-art approaches by a substantial margin. The human evaluation also proves the summaries generated by EditSum are more informative and useful. We also verify that EditSum performs well on predicting the patternized words and keywords., Comment: Accepted by the 36th IEEE/ACM International Conference on Automated Software Engineering (ASE 2021)

Modern Monte-Carlo-based rendering systems still suffer from the computational complexity involved in the generation of noise-free images, making it challenging to synthesize interactive previews. We present a framework suited for rendering such previews of static scenes using a caching technique that builds upon a linkless octree. Our approach allows for memory-efficient storage and constant-time lookup to cache diffuse illumination at multiple hitpoints along the traced paths. Non-diffuse surfaces are dealt with in a hybrid way in order to reconstruct view-dependent illumination while maintaining interactive frame rates. By evaluating the visual fidelity against ground truth sequences and by benchmarking, we show that our approach compares well to low-noise path-traced results, but with a greatly reduced computational complexity, allowing for interactive frame rates. This way, our caching technique provides a useful tool for global illumination previews and multi-view rendering., Comp Graphics & Visualisation

Code comment generation which aims to automatically generate natural language descriptions for source code, is a crucial task in the field of automatic software development. Traditional comment generation methods use manually-crafted templates or information retrieval (IR) techniques to generate summaries for source code. In recent years, neural network-based methods which leveraged acclaimed encoder-decoder deep learning framework to learn comment generation patterns from a large-scale parallel code corpus, have achieved impressive results. However, these emerging methods only take code-related information as input. Software reuse is common in the process of software development, meaning that comments of similar code snippets are helpful for comment generation. Inspired by the IR-based and template-based approaches, in this paper, we propose a neural comment generation approach where we use the existing comments of similar code snippets as exemplars to guide comment generation. Specifically, given a piece of code, we first use an IR technique to retrieve a similar code snippet and treat its comment as an exemplar. Then we design a novel seq2seq neural network that takes the given code, its AST, its similar code, and its exemplar as input, and leverages the information from the exemplar to assist in the target comment generation based on the semantic similarity between the source code and the similar code. We evaluate our approach on a large-scale Java corpus, which contains about 2M samples, and experimental results demonstrate that our model outperforms the state-of-the-art methods by a substantial margin., Comment: to be published in the 35th IEEE/ACM International Conference on Automated Software Engineering (ASE 2020) (ASE'20)

Modern Monte-Carlo-based rendering systems still suffer from the computational complexity involved in the generation of noise-free images, making it challenging to synthesize interactive previews. We present a framework suited for rendering such previews of static scenes using a caching technique that builds upon a linkless octree. Our approach allows for memory-efficient storage and constant-time lookup to cache diffuse illumination at multiple hitpoints along the traced paths. Non-diffuse surfaces are dealt with in a hybrid way in order to reconstruct view-dependent illumination while maintaining interactive frame rates. By evaluating the visual fidelity against ground truth sequences and by benchmarking, we show that our approach compares well to low-noise path-traced results, but with a greatly reduced computational complexity, allowing for interactive frame rates. This way, our caching technique provides a useful tool for global illumination previews and multi-view rendering.

This work presents the analysis of data recorded by an eye tracking device in the course of evaluating a foveated rendering approach for head-mounted displays (HMDs). Foveated rendering methods adapt the image synthesis process to the user’s gaze and exploiting the human visual system’s limitations to increase rendering performance. Especially, foveated rendering has great potential when certain requirements have to be fulfilled, like low-latency rendering to cope with high display refresh rates. This is crucial for virtual reality (VR), as a high level of immersion, which can only be achieved with high rendering performance and also helps to reduce nausea, is an important factor in this field. We put things in context by first providing basic information about our rendering system, followed by a description of the user study and the collected data. This data stems from fixation tasks that subjects had to perform while being shown fly-through sequences of virtual scenes on an HMD. These fixation tasks consisted of a combination of various scenes and fixation modes. Besides static fixation targets, moving tar- gets on randomized paths as well as a free focus mode were tested. Using this data, we estimate the precision of the utilized eye tracker and analyze the participants’ accuracy in focusing the displayed fixation targets. Here, we also take a look at eccentricity-dependent quality ratings. Comparing this information with the users’ quality ratings given for the displayed sequences then reveals an interesting connection between fixation modes, fixation accuracy and quality ratings.

Computational Intelligence in Process Modelling and Prediction, EMOPAC - Evolutionary Multi-Objective Optimization and Its Applications in Analog Circuit Design

In this paper, we discuss theoretical foundations and a practical realization of a real-time traffic sign detection, tracking and recognition system operating on board of a vehicle. In the proposed framework, a generic detector refinement procedure based

Storing and retrieving a quantum state of light on demand, without corrupting the information it carries, is an important challenge in the field of quantum information processing. Classical measurement and reconstruction strategies for storing light must

The ability to learn classification rules from data is important and useful in a range of applications. While many methods to facilitate this task have been proposed, few can derive classification rules that involve ranges (numerical intervals). In this paper, we consider how range-based classification rules may be derived from numerical data and propose a new method inspired by classification association rule mining. This method searches for associated ranges in a similar way to how associated itemsets are searched in categorical attributes in association rule mining, but uses class values to guide the search, so that only those ranges that are relevant to the derivation of classification rules are found. Our preliminary experiments demonstrate the effectiveness of our method.