相关论文: Unity is Strength: Cross-Task Knowledge Distillati…

This paper describes an approach to improve code comments along different quality axes by rewriting those comments with customized Artificial Intelligence (AI)-based tools. We conduct an empirical study followed by grounded theory…

Code generation with large language models often relies on multi-stage human-in-the-loop refinement, which is effective but very costly - particularly in domains such as frontend web development where the solution quality depends on…

A cross-domain recommendation has shown promising results in solving data-sparsity and cold-start problems. Despite such progress, existing methods focus on domain-shareable information (overlapped users or same contexts) for a knowledge…

Code review is an effective software quality assurance activity; however, it is labor-intensive and time-consuming. Thus, a number of generation-based automatic code review (ACR) approaches have been proposed recently, which leverage deep…

Code comments serve a crucial role in software development for documenting functionality, clarifying design choices, and assisting with issue tracking. They capture developers' insights about the surrounding source code, serving as an…

We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision. This…

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Source code summarizing is a task of writing short, natural language descriptions of source code behavior during run time. Such summaries are extremely useful for software development and maintenance but are expensive to manually…

Discrete diffusion models are a powerful, emerging paradigm for code generation. They construct programs through iterative refinement of partially corrupted token sequences and enable parallel token refinement. Importantly, this paradigm…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches select complete reasoning traces post-hoc, overlooking…

Code generation aims to generate a code snippet automatically from natural language descriptions. Generally, the mainstream code generation methods rely on a large amount of paired training data, including both the natural language…

Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue…

To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison. A good review needs to be knowledgeable, namely that…

This paper aims to explore the potential of combining Deep Reinforcement Learning (DRL) with Knowledge Distillation (KD) by distilling various DRL algorithms and studying their distillation effects. By doing so, the computational burden of…

Content moderation typically combines the efforts of human moderators and machine learning models. However, these systems often rely on data where significant disagreement occurs during moderation, reflecting the subjective nature of…

We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…

Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with…

Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…

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…