---

Brief Biography

I received the Ph.D. degree from the Australian Artificial Intelligence Institute (AAII), University of Technology Sydney (UTS) in March 2025, supervised by Prof. Ivor W Tsang and Prof. Yu Zhang. I received my B.S. degree in Mathematics and Applied Mathematics from Southern University of Science and Technology (SUSTC) in 2018 and my M.S. degree in Computational Mathematics from Harbin Institute of Technology (HIT) in 2020. My research interests include Embodied AI, Machine Learning, and Optimization, especially in Vision-Language-Action (VLA) models, multi-task learning, meta-learning, and black-box optimization.


News:
2026.02: One paper got accepted by CVPR 2026.
2025.01: One paper got accepted by ICLR 2025.
2024.07: One paper got accepted by Artificial Intelligence (AIJ).
2024.01: One paper got accepted by ICLR 2024.

---

Selected Publications

(*: equal contribution, #: corresponding author, full list: Google Scholar.)

• Journal Papers:

• Dual-Balancing for Multi-Task Learning.
  Baijiong Lin, Weisen Jiang, Feiyang Ye, Yu Zhang, Pengguang Chen, Ying-Cong Chen, Shu Liu, James Kwok.
  Neural Networks (NN), 2025.

• A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting.
  Jinjing Zhu, Feiyang Ye, Qiao Xiao, Pengxin Guo, Yu Zhang, Qiang Yang.
  IEEE Transactions on Image Processing (TIP), 2024.

• Multi-Objective Meta-Learning.
  Feiyang Ye, Baijiong Lin, Zhixiong Yue, Yu Zhang, and Ivor W. Tsang.
  Artificial Intelligence (AIJ), 2024.

• Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning.
  Baijiong Lin, Feiyang Ye, Yu Zhang, and Ivor W. Tsang.
  Transactions on Machine Learning Research (TMLR), 2022.

• Conference Papers:

• AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention.
  Lei Xiao, Jifeng Li, Juntao Gao, Feiyang Ye^#, Yan Jin, Jingjing Qian, Jing Zhang, Yong Wu, Xiaoyuan Yu^#.
  In Computer Vision and Pattern Recognition Conference (CVPR), 2026.

• Sharpness-Aware Black-Box Optimization.
  Feiyang Ye^*, Yueming Lyu^*, Xuehao Wang, Masashi Sugiyama, Yu Zhang, and Ivor W. Tsang.
  In International Conference on Learning Representations (ICLR), 2025.

• MTSAM: Multi-Task Fine-Tuning for Segment Anything Model.
  Xuehao Wang, Zhan Zhuang, Feiyang Ye, and Yu Zhang.
  In International Conference on Learning Representations (ICLR), 2025.

• Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting.
  Jinliang Deng, Feiyang Ye, Du Yin, Xuan Song, Ivor W. Tsang, and Hui Xiong.
  In Conference on Neural Information Processing Systems (NeurIPS), 2024, spotlight.

• FedLPA: Personalized One-shot Federated Learning with Layer-Wise Posterior Aggregation.
  Xiang Liu, Liangxi Liu, Feiyang Ye, Yunheng Shen, Xia Li, Linshan Jiang, Jialin Li.
  In Conference on Neural Information Processing Systems (NeurIPS), 2024.

• A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization.
  Feiyang Ye, Baijiong Lin, Xiaofeng Cao, Yu Zhang, and Ivor W. Tsang.
  In European Conference on Artificial Intelligence (ECAI), 2024.

• Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning.
  Feiyang Ye^*, Yueming Lyu^*, Xuehao Wang, Yu Zhang, and Ivor W. Tsang.
  In International Conference on Learning Representations (ICLR), 2024.

• Multi-Task Learning via Time-Aware Neural ODE.
  Feiyang Ye^*, Xuehao Wang^*, Yu Zhang, and Ivor W. Tsang.
  In International Joint Conference on Artificial Intelligence (IJCAI), 2023.

• Multi-Objective Meta Learning.
  Feiyang Ye^*, Baijiong Lin^*, Zhixiong Yue, Pengxin Guo, Qiao Xiao, Yu Zhang.
  In Conference on Neural Information Processing Systems (NeurIPS), 2021.

• Preprints:

• One-Token Verification for Reasoning Correctness Estimation.
  Zhan Zhuang, Xiequn Wang, Zebin Chen, Feiyang Ye, Ying Wei, Kede Ma, Yu Zhang.

• Know Your Step: Faster and Better Alignment for Flow Matching Models via Step-aware Advantages.
  Zhixiong Yue, Zixuan Ni, Feiyang Ye, Jinshan Zhang, Sheng Shen, Zhenpeng Mi.

• Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation.
  Juntao Gao, Feiyang Ye^#, Jing Zhang^#, Wenjing Qian.

• HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models.
  Xin Yan, Zhenglin Wan, Feiyang Ye, Xingrui Yu, Hangyu Du, Yang You, and Ivor W. Tsang.

• Deep Safe Multi-Task Learning.
  Zhixiong Yue^*, Feiyang Ye^*, Yu Zhang, Christy Liang, Ivor W. Tsang.

---

Professional Service

• Journal Reviewer:

• IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)

• IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)

• Journal of Artificial Intelligence Research (JAIR)

• Applied Soft Computing Journal

• Conference Reviewer:

• ICML (2025/2026), NeurIPS (2024/2025/2026), ICLR (2025/2026), AAAI (2026), AISTATS (2025/2026), CVPR (2026), ECCV (2026)

---

Experience

• Li Auto Inc., Hangzhou, China. / Senior Algorithm Engineer. 2025.5 - Present

• RIKEN Center for Advanced Intelligence Project, Tokyo, Japan. / Research Intern. 2024.8 - 2024.11

• RIKEN-AIP Overseas Student Collaboration Program / Supervised by Prof. Masashi Sugiyama.

• Tencent CSIG, Beijing, China. / Research Intern. 2024.3 - 2024.7

• Agency for Science, Technology and Research (A*STAR), Singapore. / Research Intern. 2022.8 - 2023.8

• HUAWEI 2012 Laboratory, Shenzhen, China. / Research Intern. 2019.12 - 2020.2