Related papers: Towards an open-source landscape for 3D CSEM model…
The British Geological Survey's global geomagnetic model, Model of the Earth's Magnetic Environment (MEME), is an important tool for calculating the earth's magnetic field, which is continually in flux. Whilst the ability to collect data…
The rise of large language models (LLMs) has introduced transformative potential in automated code generation, addressing a wide range of software engineering challenges. However, empirical evaluation of LLM-based code generation lacks…
Recent advancements in reasoning-based Large Language Models (LLMs), particularly their potential through test-time scaling, have created significant opportunities for distillation in code generation and critique. However, progress in both…
AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geometric vision. If models could reliably write such code, the research of our…
Large language models (LLMs) are increasingly used for generating parallel scientific codes, with a primary focus on generating functionally correct code. Recent work has focused on generating performant code, with an emphasis on its…
Computational methods that operate on three-dimensional molecular structure have the potential to solve important questions in biology and chemistry. In particular, deep neural networks have gained significant attention, but their…
Program representation learning is a fundamental task in software engineering applications. With the availability of "big code" and the development of deep learning techniques, various program representation learning models have been…
General large language models (LLMs), represented by ChatGPT, have demonstrated significant potential in tasks such as code generation in software engineering. This has led to the development of specialized LLMs for software engineering,…
Code completion is widely used by software developers to provide coding suggestions given a partially written code snippet. Apart from the traditional code completion methods, which only support single token completion at minimal positions,…
Context. Large language models (LLMs) are increasingly applied to code-generating tasks (CGTs) in software engineering. While reported results are promising, the broader effects of such application and their integration into real-world…
Computer-based systems have solved several domain problems, including industrial, military, education, and wearable. Nevertheless, such arrangements need high-quality software to guarantee security and safety as both are mandatory for…
Code reasoning tasks are becoming prevalent in large language model (LLM) assessments. Yet, there is a dearth of studies on the impact of real-world complexities on code reasoning, e.g., inter- or intra-procedural dependencies, API calls,…
The increasing development of LLMs in code generation has drawn significant attention among researchers. To enhance LLM-based code generation ability, current efforts are predominantly directed towards collecting high-quality datasets and…
This paper introduces Code-Vision, a benchmark designed to evaluate the logical understanding and code generation capabilities of Multimodal Large Language Models (MLLMs). It challenges MLLMs to generate a correct program that fulfills…
Is natural-language-driven earth observation data analysis now feasible with the assistance of Large Language Models (LLMs)? For open science in service of public interest, feasibility requires reliably high accuracy, interactive latencies,…
Electromagnetic simulations form an indispensable part of the design and optimization process for superconducting quantum devices. Although several commercial platforms exist, open-source alternatives optimized for high-performance…
Assisting LLMs with code generation improved their performance on mathematical reasoning tasks. However, the evaluation of code-assisted LLMs is generally restricted to execution correctness, lacking a rigorous evaluation of their generated…
Electronic structure simulation (ESS) has been used for decades to provide quantitative scientific insights on an atomistic scale, enabling advances in chemistry, biology, and materials science, among other disciplines. Following standard…
In energy modelling, open data and open source code can help enhance traceability and reproducibility of model exercises which contribute to facilitate controversial debates and improve policy advice. While the availability of open power…
Many socio-economical critical domains (such as sustainability, public health, and disasters) are characterized by highly complex and dynamic systems, requiring data and model-driven simulations to support decision-making. Due to a large…