|
Hongbao Zhang | 张洪宝 Currently,I am a second year M.S student at The Chinese University of Hong Kong (Shenzhen), supervised by Prof. Baoyuan Wu. Besides, during my first year, I worked with Prof. Rui Shen. in LLM powered Accounting Research. and Prof. Ka Wai Tsang. in Biostatistics. Prior to that, I obtained B.A. in Economics from Xiamen University. I finished my undergraduate thesis in quantitative finance under the guidance of Prof. Haiqiang Chen. Through these diverse research experiences, I discovered my passion for doing deep research, solidifying my commitment to making it my lifelong pursuit. Research Interests: Trustworthy ML, Multimodal Large Language Models, AI Application in Finance. I hope to make Science a good companion to everyone. |
|
Research | |
|
HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing
Zihao Zhu*, Hongbao Zhang*, Guanzong Wu, Siwei Lyu, Baoyuan Wu arXiv Paper Visual-textual inconsistency (VTI) evaluation is critical for cleansing vision-language data. This paper introduces HMGIE, a hierarchical framework to evaluate and address inconsistencies in image-caption pairs across accuracy and completeness dimensions. Extensive experiments validate its effectiveness on multiple datasets, including the newly constructed MVTID dataset. |
|
BoT: Breaking Long Thought Processes of o1-like Large Language Models through Backdoor Attack
Zihao Zhu*, Hongbao Zhang*, Mingda Zhang, Ruotong Wang, Guanzong Wu, Ke Xu, Baoyuan Wu arXiv Paper This paper introduces BoT (Break CoT), a novel backdoor attack targeting the long thought processes of o1-like large language models. BoT selectively breaks intrinsic reasoning mechanisms, forcing models to generate immediate answers without thought processes when triggered, while maintaining normal reasoning capabilities for clean inputs. Extensive experiments on open-source o1-like models, including DeepSeek-R1, demonstrate high attack success rates, highlighting critical safety risks in current models. |
Education
|
Experience
|
Miscs
|
|
This website template was borrower from Jonathon Barron. |