Related papers: Incremental Live Programming via Shortcut Memoizat…

Deep learning research over the past years has shown that by increasing the scope or difficulty of the learning problem over time, increasingly complex learning problems can be addressed. We study incremental learning in the context of…

Software visualizations are usually realized as standalone and isolated tools that use embedded code viewers within the visualization. In the context of program comprehension, only few approaches integrate visualizations into code editors,…

Despite its huge number of variants, standard Low-Rank Adaptation (LoRA) is still a dominant technique for parameter-efficient fine-tuning (PEFT). Nonetheless, it faces persistent challenges, including the pre-selection of an optimal rank…

Recent studies report that many machine reading comprehension (MRC) models can perform closely to or even better than humans on benchmark datasets. However, existing works indicate that many MRC models may learn shortcuts to outwit these…

Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines. Existing models are typically post-trained using reinforcement learning (RL) from general-purpose LLMs using "human…

Personalized programming tutoring, such as exercise recommendation, can enhance learners' efficiency, motivation, and outcomes, which is increasingly important in modern digital education. However, the lack of sufficient and high-quality…

As extended reality (XR) is redefining how users interact with computing devices, research in human action recognition is gaining prominence. Typically, models deployed on immersive computing devices are static and limited to their default…

Generative AI is changing the way that many disciplines are taught, including computer science. Researchers have shown that generative AI tools are capable of solving programming problems, writing extensive blocks of code, and explaining…

Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency to overwrite previously acquired knowledge with new…

In industrial and open-source software engineering tasks, developers often perform project-wise code editing tasks, including feature enhancement, refactoring, and bug fixing, where the leading AI models are expected to support 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…

Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated…

The emergence of large reasoning models demonstrates that scaling inference-time compute significantly enhances performance on complex tasks. However, it often falls into another trap: overthinking simple problems, where repetitive…

Code Language Models (CodeLLMs) traditionally learn attention based solely on statistical input-output token correlations ("machine attention"). In contrast, human developers rely on intuition, selectively fixating on semantically salient…

Neural program embedding can be helpful in analyzing large software, a task that is challenging for traditional logic-based program analyses due to their limited scalability. A key focus of recent machine-learning advances in this area is…

This work proposes a minimal computational model for learning structured memories of multiple object classes in an incremental setting. Our approach is based on establishing a closed-loop transcription between the classes and a…

Code editing constitutes a fundamental practice in software development, wherein developers modify existing codebases according to natural language requirements. Accurate code editing necessitates a comprehensive understanding of both the…

We introduce a new approach to take into account the memory architecture and the memory mapping in the High- Level Synthesis of Real-Time embedded systems. We formalize the memory mapping as a set of constraints used in the scheduling step.…

Higher-order logic programming is an interesting extension of traditional logic programming that allows predicates to appear as arguments and variables to be used where predicates typically occur. Higher-order characteristics are indeed…

Crosstalk computing, involving engineered interference between nanoscale metal lines, offers a fresh perspective to scaling through co-existence with CMOS. Through capacitive manipulations and innovative circuit style, not only primitive…