Ziqian Zhong
Hi! I'm Ziqian Zhong. I studied computer science and math in MIT. I'm currently a PhD student at Carnegie Mellon
University where I am very fortunate to be advised by
Aditi Raghunathan. Before that, I worked as a research scientist at Pika where I led the development of Pika 2.0.
Transformers and other large language models are powerful yet complex systems with significant unexplored potential and risks. While these models are becoming increasingly advanced, the sad reality is that our current understanding of their mechanisms, behaviors, and limitations are extremely narrow and fragile. My research seeks to advance principled approaches to enhance their robustness, controllability, and alignment with human values. [Resume]
Research Interest: Understanding, improving, and aligning large language models.
Transformers and other large language models are powerful yet complex systems with significant unexplored potential and risks. While these models are becoming increasingly advanced, the sad reality is that our current understanding of their mechanisms, behaviors, and limitations are extremely narrow and fragile. My research seeks to advance principled approaches to enhance their robustness, controllability, and alignment with human values. [Resume]
