Xulei Yang

Agency for Science, Technology and Research, Institute for Infocomm Research, Tianjin Polytechnic University

Papers

Total Citations

H-Index

About

Xulei Yang is a researcher pushing the boundaries of computer vision and robotics, with a focus on grounding language in 3D environments and advancing autonomous surgical systems. His most impactful work, "SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding" (2025, 13 citations), tackles a critical limitation in 3D visual grounding (3DVG)—the reliance on annotated datasets and predefined object categories. By enabling models to locate objects in 3D scenes from textual descriptions without prior training on specific objects, Yang’s approach significantly enhances scalability and adaptability, with direct applications in augmented reality and robotics. He further explores procedural planning in robotic surgery through his work "See, Predict, Plan: Diffusion for Procedure Planning in Robotic Surgical Videos" (2024, 4 citations), integrating diffusion models to predict surgical actions. Earlier, his comprehensive survey on CNN-based cancer diagnosis systems (2018, 3 citations) synthesized key technologies from miniature diagnostic robots to expert systems, highlighting his foundational contributions to medical AI. Yang’s research consistently bridges theoretical innovation and real-world deployment, making him a notable figure in vision-language understanding and surgical robotics.