4 papers
How Far Can VLMs Go for Visual Bug Detection? Studying 19,738 Keyframes from 41 Hours of Gameplay Videos
Wentao Lu, Alexander Senchenko, Alan Sayle +2
Video-based quality assurance (QA) for long-form gameplay video is labor-intensive and error-prone, yet valuable for assessing game stability and visual correctness over extended p…
Automated Bug Frame Retrieval from Gameplay Videos Using Vision-Language Models
Wentao Lu, Alexander Senchenko, Abram Hindle +1
Modern game studios deliver new builds and patches at a rapid pace, generating thousands of bug reports, many of which embed gameplay videos. To verify and triage these bug reports…
Predicting Defective Visual Code Changes in a Multi-Language AAA Video Game Project
Kalvin Eng, Abram Hindle, Alexander Senchenko
Video game development increasingly relies on using visual programming languages as the primary way to build video game features. The aim of using visual programming is to move gam…
Identifying Defect-Inducing Changes in Visual Code
Kalvin Eng, Abram Hindle, Alexander Senchenko
Defects, or bugs, often form during software development. Identifying the root cause of defects is essential to improve code quality, evaluate testing methods, and support defect p…