Siqi Chai is a graduate student at Carnegie Mellon University pursuing master’s in Computer Vision. He obtained his Bachelor’s degree in Computer Science and Engineering at University of California, Davis. Previsouly he interned at Horizon Robotics, Cupertino, where he worked with the perception and prediction team and researched in the field of autonomous vehicles. His current interest is in E2E methods for robotics.
Xuanbai is a first-year Master of Science in Computer Vision student (MSCV) student at Robotics Institute, Carnegie Mellon University, who will graduate in May, 2023. He is under the supervision of Prof. Fernando De la Torre. He completed his Bachelor of Engineering degree in Nankai University, China. He was once as an exchange student at University of California, Berkeley, under the supervision of Prof. Kurt Keutzer and Dr. Sicheng Zhao. He also worked as an intern in Sensetime and Amazon Web Service. He serves as a reviewer for IEEE Transactions on Cybernetics. His interests now lie in the fairness in Artificial Intelligence.
Fernando De la Torre
Fernando De la Torre received his B.Sc. degree in Telecommunications, as well as his M.Sc. and Ph. D degrees in Electronic Engineering from La Salle School of Engineering at Ramon Llull University, Barcelona, Spain in 1994, 1996, and 2002, respectively. He has been a research faculty member in the Robotics Institute at Carnegie Mellon University since 2005. In 2014 he founded FacioMetrics LLC to license technology for facial image analysis (acquired by Facebook in 2016). His research interests are in the fields of Computer Vision and Machine Learning. In particular, applications to human health, augmented reality, virtual reality, and methods that focus on the data (not the model). He is directing the Human Sensing Laboratory (HSL).
This project is sponsored by Google and the CMU human sensing lab (HSL). The goal of this project is to investigate in fair generative models and inclusive AI. In the current phase, we focused on debiasing human centric attributes in the SOTA generative model of Stable Diffusion. The expected outcome by the end of this phase is a advantageous and scaleable debiasing method.