Large language models for software engineering: A systematic literature review

X Hou, Y Zhao, Y Liu, Z Yang, K Wang, L Li… - ACM Transactions on …, 2024 - dl.acm.org
Large Language Models (LLMs) have significantly impacted numerous domains, including
Software Engineering (SE). Many recent publications have explored LLMs applied to …

A survey on large language models for software engineering

Q Zhang, C Fang, Y **e, Y Zhang, Y Yang… - arxiv preprint arxiv …, 2023 - arxiv.org
Software Engineering (SE) is the systematic design, development, maintenance, and
management of software applications underpinning the digital infrastructure of our modern …

Mapcoder: Multi-agent code generation for competitive problem solving

MA Islam, ME Ali, MR Parvez - arxiv preprint arxiv:2405.11403, 2024 - arxiv.org
Code synthesis, which requires a deep understanding of complex natural language problem
descriptions, generation of code instructions for complex algorithms and data structures, and …

Moodv2: Masked image modeling for out-of-distribution detection

J Li, P Chen, S Yu, S Liu, J Jia - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
Artificial lights commonly leave strong lens flare artifacts on the images captured at night,
degrading both the visual quality and performance of vision algorithms. Existing flare …

Quickllama: Query-aware inference acceleration for large language models

J Li, H Shi, X Jiang, Z Li, H Xu, J Jia - arxiv preprint arxiv:2406.07528, 2024 - arxiv.org
The capacity of Large Language Models (LLMs) to comprehend and reason over long
contexts is pivotal for advancements in diverse fields. Yet, they still stuggle with capturing …

Tagclip: Improving discrimination ability of open-vocabulary semantic segmentation

J Li, P Chen, S Qian, S Liu, J Jia - arxiv preprint arxiv:2304.07547, 2023 - arxiv.org
Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-
level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch …

TagCLIP: improving discrimination ability of zero-shot semantic segmentation

J Li, P Chen, S Qian, S Liu, J Jia - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-
level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch …

CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging

MA Islam, ME Ali, MR Parvez - arxiv preprint arxiv:2502.05664, 2025 - arxiv.org
Large Language Models (LLMs) have made significant strides in code generation and
problem solving. Current approaches employ external tool-based iterative debuggers that …

Exploring the Potential of Llama Models in Automated Code Refinement: A Replication Study

G Caumartin, Q Qin, S Chatragadda, J Panjrolia… - arxiv preprint arxiv …, 2024 - arxiv.org
Code reviews are an integral part of software development and have been recognized as a
crucial practice for minimizing bugs and favouring higher code quality. They serve as an …