Xinpeng Wang

Xinpeng Wang is a highly skilled researcher with a focus on artificial intelligence and natural language processing. Xinpeng Wang holds a Master of Science in Robotics Cognition Intelligence from the Technical University of Munich and has completed studies in Mechatronics, Robotics, and Automation Engineering at Dalian University of Technology. Xinpeng Wang has experience as a Student Researcher at the Technical University of Munich, where work involved indoor scene generation with transformers, and served as a Teaching Assistant for Deep Learning courses. Xinpeng Wang has interned as a Research Scientist at Meta and as an Applied Scientist Intern at Amazon. Currently, Xinpeng Wang is a Doctoral Researcher at Ludwig-Maximilians-Universität München, focusing on Language Model Alignment, and has also been appointed as a Visiting Scholar at New York University, working on detecting deceptive chain of thought in reward hacking.