王一博 Yibo Wang Ph.D. Student, LAMDA Group School of Artificial Intelligence Building of Computer Science and Technology Nanjing University, Nanjing 210023, China Supervisor: Prof. Lijun Zhang Email:wangyb@lamda.nju.edu.cn Laboratory: Building of Computer Science and Technology, Xianlin Campus of Nanjing University

Biography

Currently I am a second year Ph.D. student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, which is led by professor Zhi-Hua Zhou.

• Sep 2023 - Now : Admitted to study for a Ph.D. degree in School of Artificial Intelligence, Nanjing University.

• Sep 2021 - Jun 2023 : Admitted to study for a M.Sc. degree in Nanjing University without entrance examination.

• Sep 2017 - Jun 2021 : Receive my B.Sc. degree from Department of Computer Science and Technology, Nanjing University.

Research Interests

I was interested in Machine Learning and Online Optimization Theory. But now, I am devoted to investigating Large Language Model (LLM), especially multimodality, reasoning and its optimization theory. Please feel free to contact me if you are also interested in LLM.

Preprints

1. Universal Online Convex Optimization Meets Second-order Bounds [PDF, arXiv]
   Lijun Zhang^♣, Yibo Wang, Guanghui Wang, Jinfeng Yi, and Tianbao Yang (♣ indicates my supervisor)
   ​
2. Projection-free Online Learning with Arbitrary Delays [arXiv]
   Yuanyu Wan, Yibo Wang, Chang Yao, Wei-Wei Tu, and Lijun Zhang

Publications

1. Revisiting Stochastic Multi-Level Compositional Optimization [Official Version]
   Wei Jiang, Sifan Yang, Yibo Wang, Tianbao Yang, and Lijun Zhang
   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear, 2025.
   
   
2. Normalized Adaptive Variance Reduction Method
   Wei Jiang, Sifan Yang, Yibo Wang, and Lijun Zhang
   Journal of Software, to appear, 2025.
   
   
3. Revisiting Projection-Free Online Learning with Time-Varying Constraints [PDF, arXiv, Bibtex, Official Version]
   Yibo Wang, Yuanyu Wan, and Lijun Zhang
   In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), pages 21339-21347, 2025.
   
   
4. Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation [PDF, Bibtex, Official Version]
   Yibo Wang, Yingchun Jian, Wenhao Yang, Shiyin Lu, Lei Shen, Bing Wang, Xiaoyi Zeng, and Lijun Zhang
   In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025), pages 12757-12765, 2025.
   
   
5. Online Composite Optimization Between Stochastic and Adversarial Environments [PDF, Bibtex, Official Version]
   Yibo Wang, Sijia Chen, Wei Jiang, Wenhao Yang, Yuanyu Wan, and Lijun Zhang
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 94808-94850, 2024.
   
   
6. Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees [PDF, arXiv, Bibtex, Official Version]
   Sijia Chen*, Yibo Wang*, Yi-Feng Wu, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, and Lijun Zhang (* indicates equal contribution)
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 106555-106581, 2024.
   
   
7. Universal Online Convex Optimization with 1 Projection per Round [PDF, arXiv, Bibtex, Official Version]
   Wenhao Yang, Yibo Wang, Peng Zhao, and Lijun Zhang
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 31438-31472, 2024.
   
   
8. Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions [PDF, arXiv, Bibtex, Official Version]
   Wei Jiang, Sifan Yang, Yibo Wang, and Lijun Zhang
   In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pages 22047-22080, 2024.
   
   
9. High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails [PDF, Bibtex]
   Langqi Liu, Yibo Wang, and Lijun Zhang
   In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 32122-32138, 2024.
   
   
10. Small-loss Adaptive Regret for Online Convex Optimization [PDF, Bibtex]
    Wenhao Yang, Wei Jiang, Yibo Wang, Ping Yang, Yao Hu, and Lijun Zhang
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 56156-56195, 2024.
    
    
11. Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization [PDF, Bibtex]
    Wei Jiang, Sifan Yang, Wenhao Yang, Yibo Wang, Yuanyu Wan, and Lijun Zhang
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 21962-21987, 2024.
    
    
12. Not All Embeddings are Created Equal: Towards Robust Cross-domain Recommendation via Contrastive Learning [PDF, Bibtex]
    Wenhao Yang, Yingchun Jian, Yibo Wang, Shiyin Lu, Lei Shen, Bing Wang, Haihong Tang and Lijun Zhang
    In Proceedings of the ACM Web Conference 2024 (WWW 2024), pages 3195-3206, 2024.
    
    
13. Projection-Free Bandit Convex Optimization over Strongly Convex Sets [PDF, Bibtex, Official Version]
    Chenxu Zhang, Yibo Wang, Peng Tian, Xiao Cheng, and Yuanyu Wan
    In Proceedings of The 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2024), pages 118-129, 2024.
    
    
14. Non-stationary Projection-Free Online Learning with Dynamic and Adaptive Regret Guarantees [PDF, arXiv, Bibtex, Official Version]
    Yibo Wang, Wenhao Yang, Wei Jiang, Shiyin Lu, Bing Wang, Haihong Tang, Yuanyu Wan, and Lijun Zhang
    In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), pages 15671-15679, 2024.
    
    
15. Distributed Projection-Free Online Learning for Smooth and Convex Losses [PDF, Supplementary, Bibtex, Official Version] (Oral)
    Yibo Wang*, Yuanyu Wan*, Shimao Zhang, and Lijun Zhang (* indicates equal contribution)
    In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023), pages 10226-10234, 2023.
    
    
16. Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [PDF, arXiv, Bibtex]
    Wei Jiang, Gang Li, Yibo Wang, Lijun Zhang, and Tianbao Yang
    In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pages 32499-32511, 2022.
    
    
17. Optimal Algorithms for Stochastic Multi-Level Compositional Optimization [PDF, Bibtex]
    Wei Jiang, Bokun Wang, Yibo Wang, Lijun Zhang, and Tianbao Yang
    In Proceedings of the 39th International Conference on Machine Learning (ICML 2022), pages 10195-10216, 2022.

Awards & Honors

• Outstanding Student of Nanjing University, Nanjing, 2024.

• Excellent Rating in the Doctoral Qualify Examination (Top 15% of all PhD candidates), 2024.

• Tencent Scholarship, Nanjing, 2024.

• The First Class Academic Scholarship of Nanjing University, Nanjing, 2021, 2022, 2023, 2024.

• Excellent Student of Nanjing University, Nanjing, 2022.

• Excellent Graduate of Nanjing University, Nanjing, 2021.

Teaching Assistant

• Optimization Methods (With Prof. Lijun Zhang; For Undergraduate Students, Fall, 2023)

• Optimization Methods (With Prof. Lijun Zhang; For Undergraduate Students, Fall, 2022)

Academic Services

• Reviewer for Conferences: NeurIPS 2025, 2024, 2023; ICML 2025; ICLR 2025, 2024; AISTATS 2025, 2024, 2023; UAI 2025, 2024; WWW 2025, 2024; ECAI 2024.

• Reviewer for Journals: Information Sciences, Neurocomputing.

Correspondence

Email: wangyb@lamda.nju.edu.cn

Address: National Key Laboratory for Novel Software Technology, Nanjing University, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China.

(南京市栖霞区仙林大道163号, 南京大学仙林校区, 软件新技术国家重点实验室, 210023.)