Xiaojun Lv

Papers

Total Citations

H-Index

About

Xiaojun Lv is a researcher at the forefront of human-computer interaction, with a primary focus on multimodal named entity recognition (NER) and object determination. His most-cited work, "MLNet: a multi-level multimodal named entity recognition architecture" (2023, 7 citations), addresses a critical challenge in enabling robots to accurately identify talking objects—a prerequisite for downstream tasks like decision-making and recommendation. By introducing a multi-level architecture that integrates visual and textual cues, Lv’s research enhances machines’ ability to understand context and disambiguate entities in dynamic environments. This contribution is particularly impactful for advancing autonomous systems and interactive AI, where precise object recognition is essential. Though early in his career, Lv’s work has already garnered attention for its practical implications in robotics and human-centered AI. His achievements highlight a commitment to bridging the gap between language understanding and real-world interaction, positioning him as a promising voice in multimodal learning and intelligent system design.