avatar

Biao Liu

Ph.D. Student
Southeast University
liubiao01 (at) seu.edu.cn, biaoliu (at) seu.edu.cn


About Me

I received the BSc degree in computer science from Nanjing University of Science and Technology, China in 2021. Currently, I am a PhD student (supervised by Prof. Xin Geng) in the School of Computer Science and Engineering at Southeast University, China. My main research interests include machine learning and data mining, especially in weakly supervised learning. Additionally, I am exploring the application of techniques from weakly supervised learning to AI alignment, focusing on developing alignment methods in scenarios where data is missing or of low quality.

Research Interests

Publications

Conference

  1. Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning
    Biao Liu, Ning Xu, Xiangyu Fang, Xin Geng
    International Conference on Machine Learning (ICML), 2024.
    PDF Project Page BibTex CCF-A
  2. Revisiting Pseudo-Label for Single-Positive Multi-Label Learning
    Biao Liu, Ning Xu, Jiaqi Lv, Xin Geng
    International Conference on Machine Learning (ICML), 2023.
    PDF Project Page BibTex CCF-A
  3. Progressive Purification for Instance-Dependent Partial Label Learning
    Ning Xu, Biao Liu, Jiaqi Lv, Xin Geng
    International Conference on Machine Learning (ICML), 2023.
    PDF Project Page BibTex CCF-A
  4. Variational Label-Correlation Enhancement for Congestion Prediction
    Biao Liu*, Congyu Qiao*, Ning Xu, Xin Geng, Ziran Zhu, Jun Yang (*Equal contribution)
    Asia and South Pacific Design Automation Conference (ASP-DAC), 2024.
    PDF Project Page BibTex Oral

Journal

  1. On the Robustness of Average Losses for Partial-Label Learning
    Jiaqi Lv, Biao Liu, Lei Feng, Ning Xu, Miao Xu, Bo An, Gang Niu, Xin Geng, Masashi Sugiyama
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    PDF Project Page BibTex CCF-A
  2. Instance-Dependent Inaccurate Label Distribution Learning
    Zhiqiang Kou, Jing Wang, Yuheng Jia, Biao Liu, Xin Geng
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
    PDF Project Page BibTex CCF-B

Preprint

  1. Can Class-Priors Help Single-Positive Multi-Label Learning?
    Biao Liu, Ning Xu, Jie Wang, Xin Geng
    PDF
  2. Progressively Label Enhancement for Large Language Model Alignment
    Biao Liu, Ning Xu, Xin Geng
    PDF

Services

Conference Reviewers

Journal Reviewers


Powered by Jekyll and Minimal Light theme.