Jiaqi Lv / 吕 佳祺
Home
[ Short Bio, News, Research Interests, Job Experience, Education ]
 |
Jiaqi Lv, D.Eng.
Associate Professor,
E-mail: is.jiaqi.lv at gmail.com & jiaqi.lv at seu.edu.cn |
I'm always looking for highly self-motivated undergraduate/master students! (see this link). Reach me if you are interested.
Short Bio
I'm currently an Associate Researcher at PALM Lab, the School of Computer Science and Engineering, Southeast University (SEU), Nanjing, China. My research focuses on building reliable and efficient artificial intelligence systems. In the field of weakly supervised learning, we aim to reducing the reliance on extensively annotated datasets without sacrificing the models' reliability, and explore its evolving role in the era of foundation models. The ultimate goal is to make machine learning a tool for enhancing human decisions without compromising our ethical values or privacy. Simultaneously, I delve into model evolution, a research direction aimed at dismantling the barriers between disparate model architectures and scales. We hope to establish a novel paradigm for model training and development, significantly curtailing the computational costs of large-scale models while bolstering their deployment flexibility in diverse, real-world scenarios.
I received my Bachelor's and Doctorate degrees at SEU, under the guidance of Prof. Xin Geng. Following my graduation in 2021, I embarked on a postdoctoral journey at the RIKEN Center for Advanced Intelligence Project, Japan, collaborating with esteemed scholars such as Prof. Masashi Sugiyama and Dr. Gang Niu. This enriching experience spanned two years, after which I returned to my alma mater, SEU.
Research Interests
Weakly supervised learning (including but not limited to semi-supervised learning, partial-label learning, and label-noise learning)
Model Evolution (including but not limited to model initialization, knowledge transfer and model scaling)