Related papers: Divide-and-Conquer Meets Consensus: Unleashing the…

The recently released GPT-4 Code Interpreter has demonstrated remarkable proficiency in solving challenging math problems, primarily attributed to its ability to seamlessly reason with natural language, generate code, execute code, and…

Code generation is a latency-sensitive task that demands high timeliness. However, with the growing interest and inherent difficulty in repository-level code generation, most existing code generation studies focus on improving the…

Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests,…

Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations satisfy specifications requires constructing machine-checkable proofs, a task that remains beyond…

Code generation remains a challenging task that requires precise and structured reasoning. Existing Test Time Scaling (TTS) methods, including structured tree search, have made progress in exploring reasoning paths but still face two major…

Existing methods for code generation use code snippets as seed data, restricting the complexity and diversity of the synthesized data. In this paper, we introduce a novel feature tree-based synthesis framework, which revolves around…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

Large language models (LLMs) have shown impressive performance in reasoning benchmarks with the emergence of Chain-of-Thought (CoT), particularly in multi-choice question (MCQ). However, current works equally resolve questions regardless of…

As large language models (LLMs) play an increasingly important role in code generation, enhancing both correctness and efficiency has become crucial. Current methods primarily focus on correctness, often overlooking efficiency. To address…

Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks. However, their performance tends to falter when confronted with more challenging programming problems. We observe that…

Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constraints remains a significant challenge. Our empirical analysis reveals two key observations:…

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…

The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it is difficult to utilize the useful information scattered in…

When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, we…

This paper presents FunCodec, a fundamental neural speech codec toolkit, which is an extension of the open-source speech processing toolkit FunASR. FunCodec provides reproducible training recipes and inference scripts for the latest neural…

Deep learning is widely used to uncover hidden patterns in large code corpora. To achieve this, constructing a format that captures the relevant characteristics and features of source code is essential. Graph-based representations have…

Code review is a fundamental process in software development that plays a critical role in ensuring code quality and reducing the likelihood of errors and bugs. However, code review might be complex, subjective, and time-consuming. Comment…

Divide-and-conquer is a general strategy to deal with large scale problems. It is typically applied to generate ensemble instances, which potentially limits the problem size it can handle. Additionally, the data are often divided by random…

Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications. This issue is also observed in…