Chen Zhang

Chen Bo Calvin Zhang is a promising young researcher in the field of artificial intelligence and machine learning. He is currently a research intern at the Center for Human-Compatible AI (CHAI), where he works with Micah Carroll on reinforcement learning and robustness of large language models.1

Educational Background

Zhang has a strong academic foundation:

• MSc in Data Science from ETH Zurich, where he focused on preference-based reinforcement learning1
• BSc (Hons) in Computer Science and Mathematics from the University of Manchester1

During his time at the University of Manchester, Zhang conducted research on adversarial attacks in deep reinforcement learning under the supervision of Tingting Mu.1

Research Interests

Zhang's research interests primarily revolve around:

• Safe generalization in sequential decision making
• AI alignment
• Applications to autonomous agents and robotics1

His goal is to develop algorithms that enable agents to make reliable and safe decisions over long time horizons, even in complex and unpredictable environments.1

Professional Experience

Zhang's professional journey includes:

• Current research internship at CHAI
• Previous position as a visiting scholar at MIT, where he focused on online learning and reward design for reinforcement learning1

Achievements

Zhang has been recognized for his work in the field:

• Selected as one of the top 10 individuals in Computer Science by Nova2
• Published papers in workshops at prestigious conferences like ICML1

Chen Bo Calvin Zhang is actively involved in the AI research community, with a presence on various platforms including Google Scholar, Twitter, GitHub, and LinkedIn.1 His LinkedIn username is indeed chenbocalvinzhang, as mentioned in the query.