Natural attack for pre-trained models of code

Z Yang, J Shi, J He, D Lo - … of the 44th International Conference on …, 2022 - dl.acm.org
Pre-trained models of code have achieved success in many important software engineering
tasks. However, these powerful models are vulnerable to adversarial attacks that slightly …

Efficient and green large language models for software engineering: Vision and the road ahead

J Shi, Z Yang, D Lo - ACM Transactions on Software Engineering and …, 2024 - dl.acm.org
Large Language Models (LLMs) have recently shown remarkable capabilities in various
software engineering tasks, spurring the rapid growth of the Large Language Models for …

Ptm4tag: sharpening tag recommendation of stack overflow posts with pre-trained models

J He, B Xu, Z Yang, DG Han, C Yang, D Lo - Proceedings of the 30th …, 2022 - dl.acm.org
Stack Overflow is often viewed as one of the most influential Software Question & Answer
(SQA) websites, containing millions of programming-related questions and answers. Tags …

Compressing pre-trained models of code into 3 mb

J Shi, Z Yang, B Xu, HJ Kang, D Lo - Proceedings of the 37th IEEE/ACM …, 2022 - dl.acm.org
Although large pre-trained models of code have delivered significant advancements in
various code processing tasks, there is an impediment to the wide and fluent adoption of …

Greening large language models of code

J Shi, Z Yang, HJ Kang, B Xu, J He, D Lo - Proceedings of the 46th …, 2024 - dl.acm.org
Large language models of code have shown remarkable effectiveness across various
software engineering tasks. Despite the availability of many cloud services built upon these …

Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs

J Shi, Z Yang, J He, B Xu, D Kim, DG Han… - ACM Transactions on …, 2024 - dl.acm.org
Given the increasing adoption of modern AI-enabled control systems, ensuring their safety
and reliability has become a critical task in software testing. One prevalent approach to …

VarGAN: Adversarial Learning of Variable Semantic Representations

Y Lin, C Wan, S Bai, X Gu - IEEE Transactions on Software …, 2024 - ieeexplore.ieee.org
Variable names are of critical importance in code representation learning. However, due to
diverse naming conventions, variables often receive arbitrary names, leading to long-tail, out …

PTM4Tag+: Tag recommendation of stack overflow posts with pre-trained models

J He, B Xu, Z Yang, DG Han, C Yang, J Liu… - Empirical Software …, 2025 - Springer
Stack Overflow is one of the most influential Software Question & Answer (SQA) websites,
hosting millions of programming-related questions and answers. Tags play a critical role in …

Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead

J Shi, Z Yang, D Lo - arxiv preprint arxiv:2404.04566, 2024 - arxiv.org
Large Language Models (LLMs) have recently shown remarkable capabilities in various
software engineering tasks, spurring the rapid growth of the Large Language Models for …

[КНИГА][B] Modeling Source Code For Developers

KR Jesse - 2023 - search.proquest.com
Software Engineering practices are changing in an age of artificial intelligence. While the
core activities of design, develop, maintain, test and evaluate remain, the methods used in …