Hello! I am a Ph.D student at Institute of Automation, Chinese Academy of Sciences (CASIA). Before that, I got B.Eng from Beijing Institute of Technology.
My research interests mainly lie in Post Training of Multimodal Large Language Models (SFT, RLHF, RLVR, OPD), Model Editing (continual learning and machine unlearning), and Computer Vision. I have published papers at top AI conferences with total Google Scholar citations 0+ 
To know more about me, please visit my Google Scholar and GitHub. Any discussion is welcome via E-mail.
🔥 News
- 2026.01: 🎉🎉 Practical Continual Forgetting is accepted by IEEE T-PAMI 2026!
- 2025.06: 🎉🎉 MLLM-CL is released, a benchmark for continual learning in multimodal large language models. [Code]
- 2025.02: 🎉🎉 MRS Sampler is accepted by ICLR 2025 as a spotlight!
- 2024.09: 🎉🎉 OpenSatMap is accepted by NeurIPS 2024 Datasets and Benchmarks Track. [Code]
- 2024.03: 🎉🎉 GS-LoRA and LingoCL are accepted by CVPR 2024. [Code]
📝 Publications
Journal Papers
Practical Continual Forgetting for Pre-trained Vision Models
Hongbo Zhao, Fei Zhu, Bolin Ni, Feng Zhu, Gaofeng Meng, Zhaoxiang Zhang
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2026
Conference Papers
Continual Forgetting for Pre-trained Vision Models
Hongbo Zhao, Bolin Ni, Junsong Fan, Yuxi Wang, Yuntao Chen, Gaofeng Meng, Zhaoxiang Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
Hongbo Zhao, Lue Fan, Yuntao Chen, Haochen Wang, Xiaojuan Jin, Yixin Zhang, Gaofeng Meng, Zhaoxiang Zhang
Neural Information Processing Systems (NeurIPS), 2024 (Datasets and Benchmarks Track)
MRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers
Ao Li, Wei Fang, Hongbo Zhao, Le Lu, Ge Yang, Minfeng Xu
International Conference on Learning Representations (ICLR), 2025 (Spotlight)
Enhancing Visual Continual Learning with Language-Guided Supervision
Bolin Ni, Hongbo Zhao, Chenghao Zhang, Ke Hu, Gaofeng Meng, Zhaoxiang Zhang, Shiming Xiang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
Song Lai, Haohan Zhao, Rong Feng, Changyi Ma, Wenzhuo Liu, Hongbo Zhao, Xi Lin, Dong Yi, Qingfu Zhang, Hongbin Liu, et al.
International Conference on Machine Learning (ICML), 2026
Preprints
MLLM-CL: Continual Learning for Multimodal Large Language Models
Hongbo Zhao, Fei Zhu, Haiyang Guo, Meng Wang, Rundong Wang, Gaofeng Meng, Zhaoxiang Zhang
arXiv preprint, 2025
VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
Hongbo Zhao, Meng Wang, Fei Zhu, Wenzhuo Liu, Bolin Ni, Fanhu Zeng, Gaofeng Meng, Zhaoxiang Zhang
arXiv preprint, 2025
MCITLib: Multimodal Continual Instruction Tuning Library and Benchmark
Haiyang Guo, Fei Zhu, Hongbo Zhao, Fanhu Zeng, Wenzhuo Liu, Shijie Ma, Da-Han Wang, Xu-Yao Zhang
arXiv preprint, 2025
A Comprehensive Survey on Continual Learning in Generative Models
Haiyang Guo, Fanhu Zeng, Fei Zhu, Jiayi Wang, Xukai Wang, Jingang Zhou, Hongbo Zhao, Wenzhuo Liu, Shijie Ma, Xu-Yao Zhang, et al.
arXiv preprint, 2025
📖 Education
- 2022.09 - Present, Ph.D. in Pattern Recognition and Intelligent System, Institute of Automation, Chinese Academy of Sciences (CASIA).
- 2018.09 - 2022.07, B.Eng. in Automation, Beijing Institute of Technology (BIT).
🎖 Academic Activities
Conference Reviewer: CVPR, ICCV, ECCV, ICML, NeurIPS, ICLR, AISTATS
Journal Reviewer: T-PAMI, IJCV, T-MM, SCIENTIA SINICA Informationis