activity
20242026
most citedIndustry Practitioners Perspectives on AI Model Quality: Perceptions, Challenges, and Solutions

5 citations · 5 across the 1 of their papers we have counts for

collaborators
Showing cs.SEShow all

7 papers · 1 filter

cs.SE2026

Learning from the Test: Self-Referential Differential Testing for Deep RL Agents

Junda He, Jieke Shi, Zhou Yang +2

Deep Reinforcement Learning (DRL) has achieved significant success in complex decision-making problems. As DRL systems are increasingly deployed in real-world applications, ensurin…

cs.SE20265 cited

Industry Practitioners Perspectives on AI Model Quality: Perceptions, Challenges, and Solutions

Chenyu Wang, Zhou Yang, Yunbo Lyu +3

Artificial Intelligence (AI) is now used across nearly every industry, making AI model quality essential for building reliable and trustworthy systems. Historically, correctness ha…

cs.SE2025

Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies

Jieke Shi, Junda He, Zhou Yang +2

With the increasing use of neural policies in control systems, ensuring their safety and reliability has become a critical software engineering task. One prevalent approach to ensu…

cs.SE2024

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

Jieke Shi, Zhou Yang, David Lo

Large Language Models (LLMs) have recently shown remarkable capabilities in various software engineering tasks, spurring the rapid growth of the Large Language Models for Software…

cs.SE2024

Hotfixing Large Language Models for Code

Zhou Yang, David Lo

Large Language Models for Code (LLM4Code) have become an integral part of developers' workflows, assisting with tasks such as code completion and generation. However, these models…

cs.SE2024

Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models

Zhou Yang, Zhipeng Zhao, Chenyu Wang +4

Given large-scale source code datasets available in open-source projects and advanced large language models, recent code models have been proposed to address a series of critical s…