Related papers: TRACED: Execution-aware Pre-training for Source Co…

Understanding when and how linguistic knowledge emerges during language model training remains a central challenge for interpretability. Most existing tools are post hoc, rely on scalar metrics, or require nontrivial integration effort,…

Multi-threaded programs are expected to improve responsiveness and conserve resources by dividing an application process into multiple threads for concurrent processing. However, due to scheduling and the interaction of multiple threads,…

Learning from source code usually requires a large amount of labeled data. Despite the possible scarcity of labeled data, the trained model is highly task-specific and lacks transferability to different tasks. In this work, we present…

Code completion aims to help improve developers' productivity by suggesting the next code tokens from a given context. Various approaches have been proposed to incorporate abstract syntax tree (AST) information for model training, ensuring…

Predicting the runtime complexity of a programming code is an arduous task. In fact, even for humans, it requires a subtle analysis and comprehensive knowledge of algorithms to predict time complexity with high fidelity, given any code. As…

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…

Deep learning is being used extensively in a variety of software engineering tasks, e.g., program classification and defect prediction. Although the technique eliminates the required process of feature engineering, the construction of…

Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…

Artificial intelligence (AI) for software engineering (SE) tasks has recently achieved promising performance. In this paper, we investigate to what extent the pre-trained language model truly understands those SE tasks such as code search,…

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation…

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

Code writing is repetitive and predictable, inspiring us to develop various code intelligence techniques. This survey focuses on code search, that is, to retrieve code that matches a given query by effectively capturing the semantic…

Defects are common in software systems and can potentially cause various problems to software users. Different methods have been developed to quickly predict the most likely locations of defects in large code bases. Most of them focus on…

Source code comes in different shapes and forms. Previous research has already shown code to be more predictable than natural language as well as highlighted its statistical predictability at the token level: source code can be natural.…

Software engineers working with the same programming language (PL) may speak different natural languages (NLs) and vice versa, erecting huge barriers to communication and working efficiency. Recent studies have demonstrated the…

One major problem in maintaining a software system is to understand how many functional features in the system and how these features are implemented. In this paper a novel approach for locating features in code by semantic and dynamic…

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting…

Reimplementing solutions to previously solved software engineering problems is not only inefficient but also introduces inadequate and error-prone code. Many existing methods achieve impressive performance on this issue by using…

Large Language Models (LLMs) show promising performance on various programming tasks, including Automatic Program Repair (APR). However, most approaches to LLM-based APR are limited to the static analysis of the programs, while disregarding…

Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come…