I am a senior undergraduate student in Data Science at Tongji University, where I have the privilege of being advised by Prof. Zhihua Wei. Since February 2024, I have been an intern at HKUST (Guangzhou) under the mentorship of Dr. Xuming Hu. I am honored to have collaborated with distinguished researchers such as Weize Liu, Yibo Yan and Kaichen Huang.
My research interests lie at the intersection of multimodal and explainable AI, with an additional focus on generative models, machine unlearning, and differential privacy. Beyond my research, I am also deeply passionate about mathematics, programming, and data visualization.

🔥 News

  • 2025.06:  🎉🎉 Code of MMUnlearner released.
  • 2025.05:  🎉🎉 Two paper accepted by ACL’25 Findings, one paper accepted by ACL’25 (Industry) Oral!
  • 2025.02:  🎉🎉 One paper submitted to ACL’25.
  • 2024.09:  🎉🎉 Code of MMNeuron released.
  • 2024.09:  🎉🎉 One paper accepted by EMNLP’24!
  • 2024.06:  🎉🎉 One paper submitted to EMNLP’24.

📝 Publications

ACL'25 Findings
sym

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

Jiahao Huo, Yibo Yan, Xu Zheng, Yuanhuiyi Lyu, Xin Zou, Zhihua Wei, Xuming Hu

Project

  • Reformulate the task of multimodal MU in the era of MLLMs.
  • Aims to erase only the visual patterns associated with a given entity while preserving the corresponding textual knowledge encoded within the original parameters of the language model backbone.
  • Develop a novel geometry-constrained gradient ascent method MMUnlearner.
ACL'25 (Industry) Oral
sym

MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection

Yibo Yan, Shen Wang, Jiahao Huo, Philip S. Yu, Xuming Hu, Qingsong Wenpng

Project

  • Decomposes error detection into three phases
  • Each phase handled by a specialized agent: an image-text consistency validator, a visual semantic interpreter, and an integrative error analyzer.
EMNLP'24 main
sym

MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model

Jiahao Huo, Yibo Yan, Boren Hu, Yutao Yue, Xuming Hu

Project

  • Investigating the distribution of domain-specific neurons and the mechanism of how MLLMs process features from diverse domains.

📖 Educations

  • 2021.09 - 2025.07, Undergraduate Student, Tongji University.

💻 Internships

  • 2025.06 - present, Intern, Alibaba Group
  • 2025.05 - 2025.07, Visiting Student, Institute for Advanced Algorithms Research (IRRA), Shanghai
  • 2024.10 - 2025.03, Visiting Student, Technical University of Munich.
  • 2024.02 - 2024.10, Intern, HKUST(GZ).