Biosketch
Jingpei started his PhD at the Chair of Database Systems and Data Mining at LMU to work on the topic of “Large Language Models for Long-horizon Task Planning” in June 2023. At the meanwhile, he became a relAI member. Before that, he obtained his Bachelor’s degree in Mechanical Engineering at Tongji University in China and a Master’s degree in Robotics, Cognition, Intelligence (RCI) at the Technical University of Munich.
relAI Research
Towards Reliable Video Understanding with Large Language Models
My research focuses on reliable video understanding using video large language models (VideoLLMs), with an emphasis on spatio-temporal grounding and hallucination mitigation. In spatio-temporal grounding, we evaluate whether models accurately comprehend object interactions across time and space for precise localization and reasoning. Simultaneously, we address video hallucination by identifying and reducing inconsistencies in generated responses, enhancing the trustworthiness of model outputs. Through these efforts, we aim to develop more reliable and explainable video LLMs.