Xiyang Wu
Scholar

Xiyang Wu

Google Scholar ID: sI05dqQAAAAJ
University of Maryland
Reinforcement LearningRoboticsLarge Language ModelVision Language Model
Citations & Impact
All-time
Citations
758
 
H-index
8
 
i10-index
8
 
Publications
13
 
Co-authors
14
list available
Resume (English only)
Academic Achievements
  • Publications:
  • - VideoHallu accepted by NeurIPS 2025
  • - One paper accepted by IROS 2025
  • - AUTOHALLUSION accepted by EMNLP 2024
  • - LANCAR and AGL-NET accepted by IROS 2024
  • - One paper accepted by VLADR Workshop at CVPR 2024
  • - HallusionBench accepted by CVPR 2024
  • - iPLAN awarded Best Paper Award by MRS Workshop at IROS 2023
  • - iPLAN accepted by CoRL 2023 with Oral Presentation (Accept Rate: 6.6%)
  • - One paper accepted by Digital Signal Processing
Research Experience
  • Currently a Ph.D. student in Electrical and Computer Engineering at the University of Maryland, College Park, and a member of the GAMMA group. Research focuses on multi-modal foundation models, hallucination detection and mitigation, and physical reasoning. Additionally, works on integrating neural networks and large language models into robotic decision-making and navigation.
Education
  • Ph.D. in Electrical and Computer Engineering, University of Maryland, College Park, 2021-2026 (Expected)
  • M.S. in Electrical and Computer Engineering, Georgia Institute of Technology, 2019-2021
  • B.Eng. in Electrical Engineering (Honors Class), Tianjin University, 2015-2019
  • Advisors: Prof. Dinesh Manocha (Ph.D.), Prof. Matthew Gombolay (M.S.), Prof. Xiaodong Zhang (B.Eng.)
Background
  • Research interests include robotics, embodied AI, reinforcement learning, multi-modality, and vision language models. Focuses on multi-modal foundation models, especially hallucination detection, mitigation, and physical reasoning under complex real-world conditions. Also explores the integration of neural networks and large language models into robotic decision-making and navigation.
Miscellany
  • Actively seeking internships and full-time opportunities.