A large-scale empirical study of 1.02 million pull requests across 207 open-source projects, tracing how successive generations of generative AI technology have reshaped code review efficiency and quality.
A large-scale empirical study of 278,790 code review conversations across 300 open-source projects, comparing AI agents and human reviewers in collaborative agentic code review workflows.
A patented autonomous robot system for picking and transporting objects, combining perception, planning, and manipulation for industrial automation.
An empirical study of 82,845 real-world developer–LLM conversations examining how interaction patterns affect generated code quality across 20+ programming languages.