Related papers: Input-Gen: Guided Generation of Stateful Inputs fo…
Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system design and optimization opportunities. The technology is…
A great part of software development involves conceptualizing or communicating the underlying procedures and logic that needs to be expressed in programs. One major difficulty of programming is turning concept into code, especially when…
Since the release of ChatGPT, generative models have achieved tremendous success and become the de facto approach for various NLP tasks. However, its application in the field of input methods remains under-explored. Many neural network…
In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…
Generative coding tools promise big productivity gains, but uneven uptake could widen skill and income gaps. We train a neural classifier to spot AI-generated Python functions in over 30 million GitHub commits by 170,000 developers,…
Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…
Context: Test-driven development (TDD) is a widely employed software development practice that involves developing test cases based on requirements prior to writing the code. Although various methods for automated test case generation have…
As code generation becomes increasingly central to improving software development efficiency, modern code models are largely trained and evaluated on code with natural-language descriptions. In real projects, developers often implement…
Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the known molecules seen in training. We find that a key limitation is…
We conducted a systematic literature review on automated grading and feedback tools for programming education. We analysed 121 research papers from 2017 to 2021 inclusive and categorised them based on skills assessed, approach, language…
The increasing use of information technology has led to a significant share of energy consumption and carbon emissions from data centers. These contributions are expected to rise with the growing demand for big data analytics, increasing…
We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…
Generative AI (GenAI) has demonstrated remarkable capabilities in code generation, and its integration into complex product modeling and simulation code generation can significantly enhance the efficiency of the system design phase in…
Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in…
Artificial Intelligence (AI)-driven code generation tools are increasingly used throughout the software development lifecycle to accelerate coding tasks. However, the security of AI-generated code using Large Language Models (LLMs) remains…
The rise of machine learning (ML) and its integration into software systems has drastically changed development practices. While software engineering traditionally focused on manually created code artifacts with dedicated processes and…
The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs to enhance code…
A compiler processes the code written in a high level language and produces machine executable code. The compiler writers often face the challenge of keeping the compilation times reasonable. That is because aggressive optimization passes…
Context. In less than a year practitioners and researchers witnessed a rapid and wide implementation of Generative Artificial Intelligence. The daily availability of new models proposed by practitioners and researchers has enabled quick…
Large language models have demonstrated great potential to assist programmers in generating code. For such human-AI pair programming scenarios, we empirically demonstrate that while generated code is most often evaluated in terms of their…