|
I am a visiting scholar at USC, advised by Gaurav Sukhatme and Joseph Lim. I received my master's degree in Electronic Engineering from the University of Calgary. Before that, I completed my B.Eng. in Software Engineering at Zhejiang University of Technology. My main research goal is to advance robots’ ability to autonomously learn, adapt, and engage with the complexities of the real world. I strive to push the limits of robotics by developing innovative machine learning and adaptive control algorithms. Email / CV / Google Scholar / Twitter / Github |
|
|
|
|
|
|
Jesse Zhang, Jiahui Zhang, Karl Pertsch, Ziyi Liu, Xiang Ren, Minsuk Chang, Shao-Hua Sun, Joseph J. Lim, CoRL 2023 (Oral) OpenReview / code Our approach BOSS (BOotStrapping your own Skills) learns to accomplish new tasks by performing "skill bootstrapping," where an agent with a set of primitive skills interacts with the environment to practice new skills without receiving reward feedback for tasks outside of the initial skill set. This bootstrapping phase is guided by large language models that inform the agent of meaningful skills to chain together. Through this process, BOSS builds a wide range of complex and useful behaviors from a basic set of primitive skills. |
|
Jie Yang, Ziyi Liu, Mengchen Lin, Svetlana Yanushkevich, Orly Yadid-Pecht Preprint, 2021 arXiv / code We propose a reformulated Laplacian neural network to pursue more stable and smoother tone-mapping results. |
|
Ziyi Liu, Jie Yang, Mengchen Lin, Kenneth Kam Fai Lai, Svetlana Yanushkevich, Orly Yadid-Pecht Preprint, 2021 arXiv / code We propose the first WDR database for face detection, which contains a total of 398 16-bit megapixel grayscale wide dynamic range images collected from 29 subjects. The database is annotated with bounding boxes and landmarks. We also provide the ground truth of the face detection results. |
|
© 2023 Ziyi Liu. A fork of Jon Barron's website. |