Published multiple papers, including in NeurIPS 2025, IJCAI 2025, ICLR 2026, EMNLP 2025, AAAI 2026, CVPR 2025, and others. Won several best paper awards, such as at DDLI Workshop @ IJCAI 2025 and Responsible GenAI Workshop @ CVPR 2025. Organized multiple workshops and gave invited talks at various international conferences.
Research Experience
Currently a Senior Research Scientist at Google, working on enhancing the reliability and robustness of AI agents. Previously worked in the Gemini Safety team at DeepMind, ensuring the safety of foundation models. Served as a Postdoctoral Researcher in the Torr Vision Group at the University of Oxford.
Education
Ph.D. in 2022 from the Tresp Lab at the University of Munich, Germany, advised by Prof. Volker Tresp; Postdoctoral Researcher in the Torr Vision Group at the University of Oxford, UK, in 2023, led by Prof. Philip Torr.
Background
Senior Research Scientist, focusing on advancing the reliability and safety of AI technologies. Also a Senior Research Fellow at the University of Oxford. Research interests include interpretability, robustness, privacy, and safety of visual perception, foundation model-based understanding and reasoning, robotic policy and planning, and their fusion towards general intelligence systems.