Related papers: Outline, Then Details: Syntactically Guided Coarse…

Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions,…

Structural nonlinearity can be harnessed to program complex functionalities in robotic devices. However, it remains a challenge to design nonlinear systems that will accomplish a specific, desired task. The responses that we typically…

Programming languages are emerging as a challenging and interesting domain for machine learning. A core task, which has received significant attention in recent years, is building generative models of source code. However, to our knowledge,…

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…

Program synthesis is challenging largely because of the difficulty of search in a large space of programs. Human programmers routinely tackle the task of writing complex programs by writing sub-programs and then analyzing their intermediate…

Program synthesis is the process of automatically translating a specification into computer code. Traditional synthesis settings require a formal, precise specification. Motivated by computer education applications where a student learns to…

Algorithmic reasoning refers to the ability to understand the complex patterns behind the problem and decompose them into a sequence of reasoning steps towards the solution. Such nature of algorithmic reasoning makes it a challenge for…

Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain…

Due to the development of pre-trained language models, automated code generation techniques have shown great promise in recent years. However, the generated code is difficult to meet the syntactic constraints of the target language,…

With the presence of online collaborative tools for software developers, source code is shared and consulted frequently, from code viewers to merge requests and code snippets. Typically, code highlighting quality in such scenarios is…

This work introduces (1) a technique that allows large language models (LLMs) to leverage user-provided code when solving programming tasks and (2) a method to iteratively generate modular sub-functions that can aid future code generation…

Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…

Chain-of-thought (CoT) has emerged as a groundbreaking tool in NLP, notably for its efficacy in complex reasoning tasks, such as mathematical proofs. However, its application in code generation faces a distinct challenge, i.e., although the…

LLMs are widely used in complex AI applications. These applications underscore the need for LLM outputs to adhere to a specific format, for their integration with other components in the systems. Typically the format rules e.g., for data…

During software front-end development, the work to convert Graphical User Interface(GUI) image to the corresponding front-end code is an inevitable tedious work. There have been some attempts to make this work to be automatic. However, the…

Code summarization aims to generate concise natural language descriptions for source code. The prevailing approaches adopt transformer-based encoder-decoder architectures, where the Abstract Syntax Tree (AST) of the source code is utilized…

Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent. However, given NL is informal, it does not lend easily to checking…

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Multimodal large language models (MLLMs) have streamlined front-end interface development by automating code generation. However, these models also introduce challenges in ensuring code quality. Existing approaches struggle to maintain both…

Developing models that can automatically generate detailed code explanation can greatly benefit software maintenance and programming education. However, existing code-to-text generation models often produce only high-level summaries of code…