Papers
1
Total Citations
7
H-Index
1
About
Zhe Xue is a researcher whose work bridges vision and language, with a focus on advancing machine understanding through question generation. His key research areas include visual question generation (VQG), visual question answering (VQA), and multimodal reasoning. Xue’s major contribution lies in rethinking VQG as an inferential task rather than a simple reversal of VQA. In his most cited paper, "Inferential Visual Question Generation" (2022, 7 citations), he proposed a novel framework that generates challenging, context-aware questions requiring deeper reasoning—moving beyond superficial data-driven approaches. This work highlights the limitations of existing VQG methods that rely on VQA datasets, which often produce trivial queries. By emphasizing inference, Xue’s approach aims to create questions that can truly test both robotic and human intelligence. Though early in his career, his research has already garnered attention for its innovative perspective on making AI more inquisitive and capable of generating meaningful, non-obvious questions. His work holds promise for applications in education, human-robot interaction, and robust AI evaluation.
Research Focus
Key Achievements
Top Papers
- 1Inferential Visual Question Generation7 citations · 2022