7 citations · 12 across the 9 of their papers we have counts for
10 papers
TileCas: Cascading Kernel Development Across Programming Abstractions
Xinyu Xiao, Zihe Song, Dezhi Ran +2
Programming abstractions have traditionally been designed for humans, but code generation is increasingly performed by models and autonomous agents. We investigate abstractions for…
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
Shanghao Li, Jinda Han, Yibo Wang +5
In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token represen…
Characterizing Real-World Bugs in Tile Programs for Automated Bug Detection
Ravishka Rathnasuriya, Zihe Song, Nidhi Majoju +4
Tile-based programming frameworks are increasingly adopted to write high-performance GPU kernels in domains such as deep learning and scientific computing. While these frameworks e…
AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?
Dezhi Ran, Yuan Cao, Mengzhou Wu +10
Large language models (LLMs) have demonstrated remarkable capability in function-level code generation tasks. Unlike isolated functions, real-world applications demand reasoning ov…
Efficiency Robustness of Dynamic Deep Learning Systems
Ravishka Rathnasuriya, Tingxi Li, Zexin Xu +4
Deep Learning Systems (DLSs) are increasingly deployed in real-time applications, including those in resourceconstrained environments such as mobile and IoT devices. To address eff…
An Empirical Analysis of Compatibility Issues for Industrial Mobile Games
Zihe Song, Yingfeng Chen, Lei Ma +4
Detecting and fixing compatibility issues is critical for mobile game development. The rapid evolution of mobile operating systems and device fragmentation make it challenging for…
Can You Mimic Me? Exploring the Use of Android Record & Replay Tools in Debugging
Zihe Song, S M Hasan Mansur, Ravishka Rathnasuriya +4
Android User Interface (UI) testing is a critical research area due to the ubiquity of apps and the challenges faced by developers. Record and replay (R&R) tools facilitate manual…
WEFix: Intelligent Automatic Generation of Explicit Waits for Efficient Web End-to-End Flaky Tests
Xinyue Liu, Zihe Song, Weike Fang +2
Web end-to-end (e2e) testing evaluates the workflow of a web application. It simulates real-world user scenarios to ensure the application flows behave as expected. However, web e2…
NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
Simin Chen, Zihe Song, Mirazul Haque +2
Neural image caption generation (NICG) models have received massive attention from the research community due to their excellent performance in visual understanding. Existing work…
An Empirical Analysis of UI-based Flaky Tests
Alan Romano, Zihe Song, Sampath Grandhi +2
Flaky tests have gained attention from the research community in recent years and with good reason. These tests lead to wasted time and resources, and they reduce the reliability o…