From the 1 of 24 linked papers with an AI index.
24 papers
LEGOUI: Designing with UI-DSL Bricks to Balance Transparency and Controllability
Yinsi Zhou, Mingyue Yuan, Hongyue Xu +8
Generative user interface design tools enable rapid prototyping but often operate as black boxes with limited transparency and controllability. When outputs diverge from the design…
Lossless Tensor Compression as Program Synthesis
Jieke Shi, Junda He, Wenjia Jiang +11
Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requiremen…
SkillGuard: A Permission-Centric Framework for Agent Skill Security
Shidong Pan, Xiaoyu Sun, Tianyi Zhang +3
The paper introduces SkillGuard, a permission‑centric framework that treats LLM agent skills as executable artifacts with explicit permissions, regulating both their influence on c…
The Creation and Analysis of Government AI Transparency Statements in Australia
Shidong Pan, Haochen Gong, Boming Xia +3
Governments increasingly deploy AI in public services, making transparency essential for accountability and public trust. Australia's Standard for AI Transparency Statements (AITS)…
Many a Little Makes a Mickle: A Code-Centric Empirical Study of Data Minimization Principle in Android App Development
Dianshu Liao, Shidong Pan, Zhenchang Xing +1
Modern mobile applications consume large amounts of data to function, raising significant privacy concerns and regulatory challenges. While prior work has primarily focused on dete…
Analyzing Codes of Conduct for Online Safety in Video Games at Scale
Jiuming Jiang, Shidong Pan, Daniel W Woods +1
Online video games have become major online social spaces where users interact, compete, and create together. These spaces, however, expose users to a wide spectrum of online harms…