Related papers: Does Coding in Pythonic Zen Peak Performance? Prel…
Large Language Models (LLMs) have demonstrated significant capability in code generation, but their potential in code efficiency optimization remains underexplored. Previous LLM-based code efficiency optimization approaches exclusively…
Python has become the de-facto language for training deep neural networks, coupling a large suite of scientific computing libraries with efficient libraries for tensor computation such as PyTorch or TensorFlow. However, when models are used…
The increasing electricity demands of personal computers, communication networks, and data centers contribute to higher atmospheric greenhouse gas emissions, which in turn lead to global warming and climate change. Therefore the energy…
Python has become a popular programming language because of its excellent programmability. Many modern software packages utilize Python for high-level algorithm design and depend on native libraries written in C/C++/Fortran for efficient…
Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, yet this often entails longer contexts and numerous reasoning token costs. In this paper, we propose an efficient test-time…
Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly understood. We introduce PyLang, a minimal imperative…
Programs are a kind of communication to both computers and people, hence as students are trained to write programs they need to learn to write well-designed, readable code rather than code that simply functions correctly. The difficulty in…
Python is known to be a versatile language, well suited both for beginners and advanced users. Some elements of the language are easier to understand than others: some are found in any kind of code, while some others are used only by…
Python data science libraries such as Pandas and NumPy have recently gained immense popularity. Although these libraries are feature-rich and easy to use, their scalability limitations require more robust computational resources. In this…
Pythonic idioms are highly valued and widely used in the Python programming community. However, many Python users find it challenging to use Pythonic idioms. Adopting a rule-based approach or LLM-only approach is not sufficient to overcome…
Large Language Models (LLMs) achieve impressive accuracy on mathematical reasoning benchmarks, yet their performance drops when problems are modified with simple changes like different names or numbers. Code execution methods, which let…
Recently, dynamically typed languages, such as Python, have gained unprecedented popularity. Although these languages alleviate the need for mandatory type annotations, types still play a critical role in program understanding and…
We investigate how code obfuscation influences human understanding of programs through an output-prediction task. To study this effect, we construct multiple levels of obfuscation, ranging from unobfuscated code to transformations involving…
Large language models (LLMs) have demonstrated unparalleled prowess in mimicking human-like text generation and processing. Among the myriad of applications that benefit from LLMs, automated code generation is increasingly promising. The…
Python is widely adopted across various domains, especially in Machine Learning (ML) and traditional software projects. Despite its versatility, Python is susceptible to performance smells, i.e., suboptimal coding practices that can reduce…
Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…
Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning…
Currently, Python is one of the most widely used languages in various application areas. However, it has limitations when it comes to optimizing and parallelizing applications due to the nature of its official CPython interpreter,…
The paper examines the handling times of software vulnerabilities in CPython, the reference implementation and interpreter for the today's likely most popular programming language, Python. The background comes from the so-called…
With the advent of large language models (LLMs) like GPT-3, a natural question is the extent to which these models can be utilized for source code optimization. This paper presents methodologically stringent case studies applied to…