Related papers: Safurai-Csharp: Harnessing Synthetic Data to impro…

We present libsharp, a code library for spherical harmonic transforms (SHTs), which evolved from the libpsht library, addressing several of its shortcomings, such as adding MPI support for distributed memory systems and SHTs of fields with…

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A particularly exciting aspect of LLMs is their knack for…

In the rapidly evolving industry of software development, coding efficiency and accuracy play significant roles in delivering high-quality software. Various code suggestion and completion tools, such as CodeBERT from Microsoft and GPT-3.5…

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first…

Code explanation plays a crucial role in the software engineering domain, aiding developers in grasping code functionality efficiently. Recent work shows that the performance of LLMs for code explanation improves in a few-shot setting,…

In this study, we present a novel dataset for training machine learning models translating between OpenMP Fortran and C++ code. To ensure reliability and applicability, the dataset is created from a range of representative open-source…

High-Level Synthesis (HLS) improves IC development productivity by enabling hardware design from C-like languages. However, strict coding constraints and design-specific optimizations limit its widespread adoption. While recent efforts…

Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance. However, previous Code LLMs are typically fine-tuned on single-source data with limited quality…

Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In…

Although Large Language Models (LLMs) show promising solutions to automated code generation, they often produce insecure code that threatens software security. Current approaches (e.g., SafeCoder) to improve secure code generation are…

Large language models (LLMs) are increasingly being used for the task of automated code translation, which has important real-world applications. However, most existing approaches use only the source code of a program as an input to an LLM,…

Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual…

Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor…

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…

Technical Q&A sites are valuable for software developers seeking knowledge, but the code snippets they provide are often uncompilable and incomplete due to unresolved types and missing libraries. This poses a challenge for users who wish to…

AI-powered coding assistants such as GitHub's Copilot and OpenAI's ChatGPT have achieved notable success in automating code generation. However, these tools rely on pre-trained Large Language Models (LLMs) that are typically trained on…

Programmable Logic Devices (PLDs) continue to grow in size and currently contain several millions of gates. At the same time, research effort is going into higher-level hardware synthesis methodologies for reconfigurable computing that can…

Over the past few years, improving LLM code generation capabilities has been a key focus in NLP research. Despite Bengali having 242 million native speakers worldwide, it receives little attention when it comes to training LLMs. More…