Large Language Model (LLM) services expose a large configuration space that critically affects performance, yet tuning these configurations on hardware (e.g., NVIDIA GPUs) is prohibitively expensive. Simulation offers a scalable alternative, but state-of-the-art simulators suffer from a fundamental software engineering...
Yu-Jie Huang, Jia-Zhen Gu, Zhihan Jiang et al.· Proceedings of the 41st IEEE...· 0 citations
Browser extensions can pose significant privacy risks to end users due to their complex permission mechanisms and high privilege levels. Modern websites increasingly embed sensitive personal data within HTML elements, making such threats even more insidious. Although prior studies have examined browser extension privac...
Zi-Lun Wang, Ze-Yang Zhuang, Ming-Xue Zhang et al.· Proceedings of the 41st IEEE...· 0 citations
Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented language for text-to-material generation with pretrained language models. Each program composes alpha-masked layers whose shared spatial expressions define coverage and physic...
This work proposes a framework for quality-aware preference learning that guides LLMs toward generating criteria-compliant code and introduces a hybrid optimization objective that combines ranking loss with language modeling loss and KL divergence to enable effective comparative optimization.
Liang Lu, Yuan Jiang, Christoph Treude et al.· 2 citations
This work proposes AutoScope, a novel framework that leverages static code knowledge to enable structurally safe span-level sampling and introduces the concept of span-level sampling, a fine-grained paradigm that retains only essential spans rather than full traces.
Yu-Lun Wu, Guangba Yu, Zhihan Jiang et al.· ACM Transactions on Software...· 0 citations
This work proposes ComUICoder, a component-based UI code generation framework that emphasizes semantic-aware segmentation, code reuse, and fine-grained refinement and significantly improves overall generation quality and code reusability on complex multipage websites.
Jingyu Xiao, Jiantong Qin, Shuo-Qiu Li et al.· Proceedings of the 32nd ACM...· 1 citation
System logs are critical for software reliability. While many automated log-based anomaly detection methods exist, they often falter in large-scale cloud systems due to high resource consumption and poor adaptability to evolving logs. In this paper, we present SeaLog, an accurate, lightweight, and adaptive log-based an...
Jinyang Liu, Jun-Jie Huang, Zhihan Jiang et al.· ACM Transactions on Software...· 0 citations
Results show that combining layout compaction, adaptive configuration, and instruction-aware pruning can make multimodal code understanding more efficient, and propose CodeShrink, an adaptive visual compression framework with three components.
Wenxin Tang, Jingyu Xiao, Zhen-Yu Liu et al.· arXiv.org· 1 citation
VisualRepair is proposed, an MLLM-based framework for visual software issue repair comprising two core modules: Image Type-aware Tool Calling (ITTC), which classifies input images and dynamically invokes a tailored tool-calling chain for robust visual interpretation, and Dynamic Test-time Region Focusing (DTRF), which...
This work proposes ComUICoder, a component-based UI code generation framework that emphasizes semantic-aware segmentation, code reuse, and fine-grained refinement and significantly improves overall generation quality and code reusability on complex multipage websites.
Jingyu Xiao, Jiantong Qin, ShuoQiu Li et al.· Proceedings of the 32nd ACM...· 1 citation
This work proposes MicroAgent, a Context-Augmented Multi-Agent Framework for Microservice Decomposition, a Context-Augmented Multi-Agent Framework for Microservice Decomposition that divides the decomposition process into five distinct subtasks and assigns each to a specialized agent.
Zishan Su, Junjie Huang, Shiwen Shan et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
